"Steelmanning" the case for owning individual stocks

Have a question about your personal investments? No matter how simple or complex, you can ask it here.
User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Tue Feb 05, 2019 8:23 pm

averagedude wrote:
Sun Feb 03, 2019 2:29 pm
Im sure if you do some deep dives on etf's, that you can create a portfolio that would emulate closely to the factors that you desire and would be close to the performance that you would get if you selected a couple hundred individual stocks that is probably needed to satisfy your objectives.
sf_tech_saver wrote:
Tue Feb 05, 2019 3:45 am
Trying to beat the quant hedge funds by researching a few hours a week sounds wacky to me!
After some consideration I've decided to not pursue any filtering/quantification using fundamental data. It's expensive, adds a lot of complexity and it's outside of my expertise. I will rely on the ETF's themselves to do some of the filtering. I'm still in the preliminary exploration, however I do have some specific steps going forward.

>> Start witht SP100 stocks, they same sample has been very stable over the last 10-12 years.

>> Review the literature regarding back-testing, specifically how to properly correct for multiple comparisons.

>> The strategy will include:

1.) An evaluation period (a rolling window of calculations)
2.) A ranking and filtering procedure [features(momentum, volatility, relation to SP performance), frequency of rebalancing]
3.) A portfolio optimization procedure

>> Anybody interested can do this (and more ) using Python Pandas library. It's just amazing, created, maintained by an AQR researcher, now TwoSigma.

Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Thu Feb 07, 2019 10:48 pm

I spent some time working a bit with the data and have some observations to add:

>> Limiting myself to SP100 stocks is a mistake, it reduces the investable universe too much.
>> I was able to get SP500 stocks history in a few seconds using tiingo. I can't confirm that their data is 100% clean. Will need to run some scripts.
>> The dataset still needs to be adjusted for survivorship bias (aditions/deletions)

In terms of the stock selection:

>> Unsurprisingly, low vol stocks in SP500 tend to be utilities, REITS, consumer staples.
>> These stocks have higher dividends and it's a bit of an issue for my since this would be done in taxable
>> I was able to work out my first set of parameters for testing, it includes:
> Momentum Measures in different timeframes and with different approaches.
> Volatility
> A measure similar to "sharp ratio" in order to compare with index
>> Played around with some optimization methods. However, I'm not sure about this path.

What it's next:

>> Write the code for the back testing framework
>> See if I can implement this on Robinhood and save the $$$ commissions. However they lack MOC orders.

Resources:

Found this couple of books that could be handy.

1.) Market Timing with Moving Averages: The Anatomy and Performance of Trading Rules

2.) Smart Portfolios: A practical guide to building and maintaining intelligent investment portfolios

3.) References
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sun Feb 17, 2019 12:00 pm

I've had less time to work during the week. I'm ok to work at a slower pace only during the weekends. Some observations:

1. I started coding the backtesting framework. In a way this is basically building my own Portfolio Visualizer, except better.
2. I still need to write the script to clean data and also to adjust universe of stocks for survivorship bias
3. I'm using data from tiingo.com, but quandl looks interesting as well.
4. The Python portfolio optimizer library is extremely fast and easy to use. Recommended :beer

The PyPortfolioOpt library has a method to implement a different type of optimization I never seen before: Hierarchical Risk Parity
Building Diversified Portfolios that Outperform Out-of-Sample
Journal of Portfolio Management, 2016, Forthcoming

31 Pages Posted: 28 Dec 2015 Last revised: 24 May 2016
Marcos Lopez de Prado
AQR Capital Management, LLC; Cornell University - Operations Research & Industrial Engineering; RCC - Harvard University

Date Written: May 23, 2016

Abstract
This paper introduces the Hierarchical Risk Parity (HRP) approach. HRP portfolios address three major concerns of quadratic optimizers in general and Markowitz’s CLA in particular: Instability, concentration and underperformance.

HRP applies modern mathematics (graph theory and machine learning techniques) to build a diversified portfolio based on the information contained in the covariance matrix. However, unlike quadratic optimizers, HRP does not require the invertibility of the covariance matrix. In fact, HRP can compute a portfolio on an ill-degenerated or even a singular covariance matrix, an impossible feat for quadratic optimizers. Monte Carlo experiments show that HRP delivers lower out-of-sample variance than CLA, even though minimum-variance is CLA’s optimization objective. HRP also produces less risky portfolios out-of-sample compared to traditional risk parity methods.
Some of the math is above my head, but it's interesting nonetheless. Here's a link where they compare different techniques. Doesn't look compelling enough to me to deviate from equal weighting.

The takeaway from this week is that the barrier for entry to do your run your own systematic portfolio is very low. Really unbelievable. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Feb 23, 2019 4:27 pm

Good progress this week:

> It turns out I don't need to completely reinvent the wheel as there's a perfectly fine framework for portfolio testing: Backtrader
> Down the road, it's even possible to automate the excecution with a free commission broker: Alpaca.
> Found this nice paper offering some other ideas for portfolio selection, the new feature is the addition to Total Payout (Dividend + Share Repurchase)
> Along the same lines, the stock selection of these etf's could be useful

SPDR® Portfolio S&P 500® High Dividend ETF
SPDR® S&P® 500 Buyback ETF
iShares U.S. Dividend and Buyback ETF
Cambria Shareholder Yield ETF

> I was able to implement the method to maximize the diversification ratio, which is defined as:
The diversification ratio is the ratio of the weighted average of volatilities divided by the portfolio volatility
> I looked into the broker options:

1.) Interactive Brokers:
The Good: I already have an account, MOC orders, Good API
The Bad: Will cost around $250-$300 per year.

2.) Robinhood:
The Good: Free, I already have an account.
The Bad: No specific lot id, web interface is poor, No MOC order

3. Merrill Edge:
The Good: Free 30 trades (this should be enough)
The Bad: Open another account, park money 3 months before enjoy $0 commissions.

> Found this nice paper on risk parity an other optimization methods.
Risk Parity, Maximum Diversification, and Minimum Variance: An Analytic Perspective
Journal of Portfolio Management, Vol. 39, No. 3, pp. 39-53 (Spring 2013).

Posted: 1 Jan 2012 Last revised: 21 Nov 2013
Roger G Clarke
Ensign Peak Advisors

Harindra de Silva
Analytic Investors, Inc.

Steven Thorley
BYU Marriott School of Business

Date Written: June 1, 2012

Abstract
Analytic solutions to Risk Parity, Maximum Diversification, and Minimum Variance portfolios provide useful perspectives about their construction and composition. Individual asset weights depend on both systematic and idiosyncratic risk in all three risk-based portfolios, but systematic risk eliminates many investable assets in long-only constrained Maximum Diversification and Minimum Variance portfolios. On the other hand, all investable assets are included in Risk Parity portfolios, and idiosyncratic risk has little impact on the magnitude of the weights. The algebraic forms for optimal asset weights derived in this paper yield generalizable properties of risk-based portfolios, in contrast to empirical simulations that employ a specific set of historical returns, proprietary risk models, and multiple constraints. The analytic solutions reveal precisely how the various kinds of predicted risk impact the relative magnitude of security weights under each type of risk-based portfolio construction.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat May 18, 2019 12:37 pm

After running the portfolio live for 9 weeks, these are some takeaways:

1. Individual investors have an advantage over institutional money in terms of transactions costs, this is an overlooked fact. I was able to secure 100 free monthly trades with Bank of America - Merrill, this is more than enough for my frequent rebalancing needs.

2. Besides having a good stocks screening process, the next two most critical steps are:

>> Rebalancing: I have discovered inspired by this post, that rebalancing done right is a source of alpha, here I'm strictly talking way beyond the traditional naive schemes of threshold or periodic excecution. What I have discovered is that this is an event based process in which the validation has to be performed at least daily.

>> Sector constrains: Much of the factors performance is interrelated with specific sectors idiosyncrasies. Initially I had decided to use just ranking but I've discovered through research and live performance that the best path is to have a sound policy in terms of sector constrain. This has been the most difficult thing to make into an adaptive algorithm

3. This whole process has made me A LOT LESS of an skeptic for outperformance, and to be honest is making me view holding of normal market cap indexes as a subpar option.

4. Controlling for quality is the easiest and index providers do the work for you.

5. It's remarkable the level of diversification you can achieve with only 25 holdings.

6. I want to evaluate performance after the portfolio has been exposed to more regimes and then if all is looking good perhaps run all my equity holding in my retirement portfolio + trading portfolio in the same way.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
nedsaid
Posts: 11882
Joined: Fri Nov 23, 2012 12:33 pm

Re: "Steelmanning" the case for owning individual stocks

Post by nedsaid » Sat May 18, 2019 1:18 pm

Hdas, your thread is very interesting. If you generate alpha doing what you are doing, more power to you.

Some observations. You seem to have evolved from individual stocks to ETFs. It seems like you are sort of like, well you know, factor investing. Letting the ETFs doing the screening for you. Pretty much you are saying that you have run up the white flag and admitting that you couldn't do individual security selection better than the ETFs.

When folks talk about trading, it gives me pause. I have posted often about the "Nedsaid effect." That is the phenomenon of incorrect sell/buy decisions. There is a large tendency for the investment that you sell to do better than what you buy to replace, at least in the shorter term. It seems that the ratio of incorrect sell/buy decisions to correct sell/buy decisions is at a ratio of 2:1 or even 3:1. Even professional investors get plagued by this.

Why does the "Nedsaid effect" exist? One is investor impatience. Strategies and investments tend to start performing again when enough people give up and throw in the towel. Second, it is hard to predict when markets will turn. You can be right but right too early, sometimes way too early. Third, you are up against big institutions who perform probably 90% of all transactions. To think that you are going to outsmart a big institution with Math PhD's, super fast computers, and superior software is just laughable. Problem is, the more you trade, the greater toll that the "Nedsaid effect" takes on your performance. The effect of incorrect sell/buy decisions really adds up over time. I suppose a fourth reason for the "Nedsaid effect" is that many small investors don't know what they are doing. Many folks read one book and think themselves experts.

One advantage that you have over institutions is that you can take a longer term approach. You aren't benchmarked to the market averages quarter by quarter as the institutions are. Also no need to do such things as window dressing each quarter. Window dressing is buying the recently hot performing stocks near the end of the quarter so that shareholders can see that you owned them. It reduces the embarrassment of underperforming the benchmarks as at least you were in the "best" stocks. It is a way of covering up what a portfolio manager really was doing. Also, institutions have done some pretty dumb things themselves.

I do agree that 25 stocks can provide an amazing amount of diversification. For an individual, if you own more than that, it gets to be difficult to follow each company. But indexes are a more efficient way to invest. For myself, I have done most things right as an investor in individual stocks but when I trail the indexes, I trail by as much as 1% a year over 15 years. Whenever I have outperformed, it has been by a fraction of 1%. So not much to write home about except that the research shows that most individuals picking stocks trail the indexes by 4% a year.

Also keep in mind that the analysis tools you are using, like Portfolio Visualizer, while quite good are still inferior to what the big Institutional investors have access to. For one thing, they all have the Bloomberg machine that provides instantaneous market information. You are also doing the analysis yourself, you don't have a Math PhD on your payroll. Also, you do this only part-time vs. teams of full-time people. Even if you had the exact same tools and information as the institutions, they have the greater expertise.

As far as Alpha from rebalancing, color me skeptical. In my own analysis, it seems that rebalancing sometimes helped performance and sometimes hurt. If you are rebalancing between stocks and bonds, I doubt you will experience Alpha on a long term basis, in fact rebalancing will likely dampen your returns as stocks over time return more than bonds. I don't believe in the rebalancing bonus, rebalancing is more about controlling risk than enhancing return. If you are rebalancing between volatile asset classes, that is sectors of the stock market, you might have something there. Alpha there is possible, but the markets are pretty darned efficient, though not perfectly so.

My guess is that if you are patient and do some sort of factor investing, you as an individual investor have a shot at Alpha. But it looks like you are doing a fair amount of trading and rebalancing and I think both things reduce your chances of outperformance. Pretty hard to outguess the market as a whole.
A fool and his money are good for business.

User avatar
mhadden1
Posts: 695
Joined: Tue Mar 25, 2014 8:14 pm
Location: North Alabama

Re: "Steelmanning" the case for owning individual stocks

Post by mhadden1 » Sat May 18, 2019 1:42 pm

I hope you have fun frittering your time away searching for alpha. Try not to lose too much. :beer
Oh I can't, can I? That's what they said to Thomas Edison, mighty inventor, Thomas Lindberg, mighty flyer,and Thomas Shefsky, mighty like a rose.

KyleAAA
Posts: 7218
Joined: Wed Jul 01, 2009 5:35 pm
Contact:

Re: "Steelmanning" the case for owning individual stocks

Post by KyleAAA » Sat May 18, 2019 1:54 pm

Owning individual stocks makes a lot of sense for very wealthy individuals. They can make sense in niche cases for those of more normal means. If you told me you wanted to hold 50 stocks based on some reasonable set of rules I would say sure, go for it. Just make sure you understand the risks.

Call_Me_Op
Posts: 7308
Joined: Mon Sep 07, 2009 2:57 pm
Location: Milky Way

Re: "Steelmanning" the case for owning individual stocks

Post by Call_Me_Op » Sun May 19, 2019 8:09 am

If you enjoy it - by all means have at it, but don't fool yourself into to thinking this is a productive use of your time and energy.
Best regards, -Op | | "In the middle of difficulty lies opportunity." Einstein

aristotelian
Posts: 5809
Joined: Wed Jan 11, 2017 8:05 pm

Re: "Steelmanning" the case for owning individual stocks

Post by aristotelian » Sun May 19, 2019 8:11 am

The best argument is tax efficiency, not beating the market.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Wed May 22, 2019 12:19 pm

Some surprising results when running the factor regression on the portfolio.

Image

1. Size is not negatively significant even though I use only large caps
2. Lukewarm exposure to Momentum :?:
3. Significant exposure to Value ? :shock:
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Wed May 22, 2019 12:23 pm

nedsaid wrote:
Sat May 18, 2019 1:18 pm
Pretty much you are saying that you have run up the white flag and admitting that you couldn't do individual security selection better than the ETFs.
I guess that's one way to say it. I notice that my screening/ranking dictates most of the difference. This portfolio doesn't look like anything you see in an ETF. I'm simply not interested in the analysis of balance sheets data. My strengths are in time series analysis and systematic implementations. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

bltn
Posts: 446
Joined: Mon Feb 20, 2017 9:32 pm

Re: "Steelmanning" the case for owning individual stocks

Post by bltn » Wed May 22, 2019 3:24 pm

Your proposed endeavor reminds me of something I tried 25 years ago. Diversification, decreased correlation with the returns of my retirement fund, and lots of control over the investment. I tried to buy and manage rental real estate. A chance for outsized returns with the leverage. Poor liquidity, but since it was going to be securely under my management and control, that probably didn't t matter.
It took more time and effort than I thought, and the returns were no better than I made later with my first index fund, which tracked the s and p 500. And for those final returns, I spent many more nights, and weekends working with, and worrying about the investment than I thought I would. With more knowledge, maybe I would have done better.
This was a great learning experience for me. Thankfully, I didn't use more than about 15% of my savings. And thankfully, I did this early in my investing career so that I knew what I should avoid in the future.
I think that the chances are great that the value of this venture will be as a learning experience for you.
Best of luck.

User avatar
nedsaid
Posts: 11882
Joined: Fri Nov 23, 2012 12:33 pm

Re: "Steelmanning" the case for owning individual stocks

Post by nedsaid » Wed May 22, 2019 4:13 pm

hdas wrote:
Wed May 22, 2019 12:23 pm
nedsaid wrote:
Sat May 18, 2019 1:18 pm
Pretty much you are saying that you have run up the white flag and admitting that you couldn't do individual security selection better than the ETFs.
I guess that's one way to say it. I notice that my screening/ranking dictates most of the difference. This portfolio doesn't look like anything you see in an ETF. I'm simply not interested in the analysis of balance sheets data. My strengths are in time series analysis and systematic implementations. :greedy
What you have found is that this stuff is hard. I used to pour over the ValueLine research at the Public Library and scour financial publications for stock tips. Did a lot of research and it just didn't pay off. After the 2000-2002 bear market, I look at a few metrics and try to buy good stocks in good industries at reasonable prices. Don't do the fancy spreadsheet stuff, just eyeballing. Pretty much, I have sampled the S&P 500 Index and it shouldn't be too surprising that my results have shadowed those of the Index.

So it sounds like you have fired yourself as a fundamental analyst and hired yourself as a technical analyst. Good luck interpreting the wiggles and squiggles on graphs. Louis Rukeyser ridiculed this practice every chance he got on his famous TV show. Hint: your chances of success are better on the fundamental side. Markets are sometimes driven by emotion rather than logic and this trashes a lot of quant models.
A fool and his money are good for business.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Factor Exposure and Sector Bets

Post by hdas » Thu May 23, 2019 9:39 am

Related to my point about the challenge of implementing sector constrains in optimization a portfolio of targeted factors:

Image

From: Barrons Article

And a more granular breakdown:

Value

Image

Size

Image

Momentum

Image

Low Volatility

Image

Quality

Image

Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Fri May 31, 2019 5:55 pm

Notes from this week:

>> I transitioned from SP500 stocks to Russell 1000 stocks as universe. Cast a wider net, add midcaps. Win-Win.
>> I've been noticed an important end of the month effect. This is related to term premium component I believe. Perhaps there's a way to systematically exploit this.
>> When running the traditional factor regression, I'm not getting as much Momentum exposure as wanted. At this point I don't care because portfolio is working very well...and this might be a direct result of the peculiar way I measure momentum in my stocks.
>> Glad my portfolio only went down 0.3% in this crazy week. Look forward to the adaptations it makes in order to perform well in the swing up.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Tue Jun 04, 2019 11:19 am

Notes from the trenches:

It's been almost 3 months since experiment started, the portfolio outperforming benchmark (SP500) handly, however, it's clear that this has been possible due to the significant exposure to term risk.

Image

The way I calculate, rank and integrate Low Vol and momentum its not giving me significant exposure to those factors. It's worth pondering: if there's significant positive alpha do we even care about factor exposure?

future avenues for research:

1. Additionally incorporate sector momentum.
2. Make use of equity/credit and Low-Vol/High Beta ratios.

Image

ps. Incidentally, every month I like to update my Vanguard profile with the holdings of this portfolio. One way I have been able to confirm that the active rebalancing is working vs monthly rebalancing is comparing the account balance with the account balance that would have happened if I left the accounts from previous month untouched.

Cheers :greedy
Last edited by hdas on Thu Jun 06, 2019 7:06 pm, edited 3 times in total.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

beentherenyt
Posts: 1
Joined: Tue Jun 04, 2019 2:07 pm

Re: "Steelmanning" the case for owning individual stocks

Post by beentherenyt » Tue Jun 04, 2019 2:38 pm

The reason I choose to invest a very small portion (maybe 2%) of my assets in individual stocks is because, as someone who enjoys reading about money matters/investing/finance/etc., I think it's much more fun than investing solely in the same 6 Admiral funds so many other people on this forum are dedicated to exclusively. That's not to say it's likely to maximize my lifelong returns. But I enjoy participating in a marketplace where yesterday my meager holding was up 320% and today (the last time I looked) it was down 40% (LGCY}. That's just not going to happen in VDADX.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Thu Jun 06, 2019 7:03 pm

beentherenyt wrote:
Tue Jun 04, 2019 2:38 pm
The reason I choose to invest a very small portion (maybe 2%) of my assets in individual stocks is because, as someone who enjoys reading about money matters/investing/finance/etc., I think it's much more fun than investing solely in the same 6 Admiral funds so many other people on this forum are dedicated to exclusively. That's not to say it's likely to maximize my lifelong returns. But I enjoy participating in a marketplace where yesterday my meager holding was up 320% and today (the last time I looked) it was down 40% (LGCY}. That's just not going to happen in VDADX.
You, like many other are buying lottery tickets. This whole thread is about the opposite, ppl in this forum conflate holding individual stocks with gambling. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

3 Month Review

Post by hdas » Thu Jun 13, 2019 5:06 pm

It's been exactly 3 months since I started the live experiment, here are the results:

Image

Image

Takeaways:

>> While achieving the goal of outperforming the market, the portfolio didn't return more than the direct ETF competition.
>> Curious to see what happens when low vol starts underperforming
>> The switch to sectors constrained cost me some basis points during the 3rd week of April.
>> I'm going to give it a full year before dropping and switching to ETF's

Next Avenues for research:

>> Manipulate the window of observation --> Exponential weighting.
>> Add momentum relative to sector.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

Hector
Posts: 944
Joined: Fri Dec 24, 2010 2:21 pm
Contact:

Re: "Steelmanning" the case for owning individual stocks

Post by Hector » Thu Jun 13, 2019 5:43 pm

I do own individual stocks; https://www.bogleheads.org/wiki/Passive ... ual_stocks
hdas wrote:
Tue Jan 29, 2019 12:48 pm
1. A desirable fund with X,Y characteristics doesn't exist.
If you have reasons to believe that you will gain more than total stock market. Go for it.
I don't think I know how to beat the market and my stock allocation is world stock allocation.
hdas wrote:
Tue Jan 29, 2019 12:48 pm
3. The strategy can be implemented at reasonable cost and sensitive to tax issues.
You definitely pay less tax by owing no and low dividend stocks in non-retirement accounts.
hdas wrote:
Tue Jan 29, 2019 12:48 pm
4. The investor has the interest, quantitative skills and time to carry on with the endeavor.
I think majority of us can't beat the market.
hdas wrote:
Tue Jan 29, 2019 12:48 pm
1. The odds of outperforming the benchmark over the long term are low. But how about when adding low cost?
Apart from expense ratio, I doubt most can beat most benchmarks.
hdas wrote:
Tue Jan 29, 2019 12:48 pm
2. Tax Loss Harvesting becomes a lot easier.
I don't think its any easier.
hdas wrote:
Tue Jan 29, 2019 12:48 pm
4. Daily or event based rebalancing.
Congratulation on another job.

User avatar
arcticpineapplecorp.
Posts: 4200
Joined: Tue Mar 06, 2012 9:22 pm

Re: "Steelmanning" the case for owning individual stocks

Post by arcticpineapplecorp. » Thu Jun 13, 2019 5:49 pm

Rick Ferri has described the investor's eductional endeavors to generally follow the following path (viewtopic.php?t=250534) :
A successful index fund investor goes through four phases:
1) Darkness - takes advice from everyone;
2) Enlightenment - realizes a market return is superior to their return;
3) Complexity - overdoing everything to find optimal;
4) Simplicity - invests in a few total market funds

source: https://twitter.com/rick_ferri/status/9 ... 89?lang=en
I'd say you're in phase 3 now. What say you?
"May you live as long as you want and never want as long as you live" -- Irish Blessing | "Invest we must" -- Jack Bogle

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Thu Jun 13, 2019 6:02 pm

arcticpineapplecorp. wrote:
Thu Jun 13, 2019 5:49 pm
Rick Ferri has described the investor's eductional endeavors to generally follow the following path (viewtopic.php?t=250534) :
A successful index fund investor goes through four phases:
1) Darkness - takes advice from everyone;
2) Enlightenment - realizes a market return is superior to their return;
3) Complexity - overdoing everything to find optimal;
4) Simplicity - invests in a few total market funds

source: https://twitter.com/rick_ferri/status/9 ... 89?lang=en
I'd say you're in phase 3 now. What say you?
Sure, do you prefer 3.38% with a 7% drawdown or 6.20% with a 1.8 drawdown? :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

TropikThunder
Posts: 1556
Joined: Sun Apr 03, 2016 5:41 pm

Re: "Steelmanning" the case for owning individual stocks

Post by TropikThunder » Thu Jun 13, 2019 6:15 pm

hdas wrote:
Thu Jun 13, 2019 6:02 pm
arcticpineapplecorp. wrote:
Thu Jun 13, 2019 5:49 pm
Rick Ferri has described the investor's eductional endeavors to generally follow the following path (viewtopic.php?t=250534) :
A successful index fund investor goes through four phases:
1) Darkness - takes advice from everyone;
2) Enlightenment - realizes a market return is superior to their return;
3) Complexity - overdoing everything to find optimal;
4) Simplicity - invests in a few total market funds

source: https://twitter.com/rick_ferri/status/9 ... 89?lang=en
I'd say you're in phase 3 now. What say you?
Sure, do you prefer 3.38% with a 7% drawdown or 6.20% with a 1.8 drawdown? :greedy
I prefer to wait longer than three months before claiming victory.

User avatar
corn18
Posts: 1457
Joined: Fri May 22, 2015 6:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by corn18 » Thu Jun 13, 2019 6:35 pm

Did you buy any AQR?
Don't do something, just stand there!

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Thu Jun 13, 2019 6:39 pm

TropikThunder wrote:
Thu Jun 13, 2019 6:15 pm
hdas wrote:
Thu Jun 13, 2019 6:02 pm
arcticpineapplecorp. wrote:
Thu Jun 13, 2019 5:49 pm
Rick Ferri has described the investor's eductional endeavors to generally follow the following path (viewtopic.php?t=250534) :
A successful index fund investor goes through four phases:
1) Darkness - takes advice from everyone;
2) Enlightenment - realizes a market return is superior to their return;
3) Complexity - overdoing everything to find optimal;
4) Simplicity - invests in a few total market funds

source: https://twitter.com/rick_ferri/status/9 ... 89?lang=en
I'd say you're in phase 3 now. What say you?
Sure, do you prefer 3.38% with a 7% drawdown or 6.20% with a 1.8 drawdown? :greedy
I prefer to wait longer than three months before claiming victory.
Definitively, showing promise tho. Curious to see what happens when low vol underperforms. It needs a resurgence of animal spirits, perhaps above 3000 we get that.
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Fri Jul 05, 2019 10:14 pm

Some interesting ideas here:
Back to the absolute index. For example, let’s say I want to build a multi-factor fund based on 4 factors: Value, Momentum, Volatility, and Quality.

The typical way would be to rank each stock on those four measures, then average those four ranks together, and then select the stocks with the highest combined ranks.

In the absolute index version, we would have a rule where any stock that falls outside of a certain percentile of ANY measure, would be excluded from the portfolio. There would be no composite score, but instead, any stock included in the portfolio would rank in the top X% of EVERY metric.
Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
willthrill81
Posts: 10991
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: "Steelmanning" the case for owning individual stocks

Post by willthrill81 » Fri Jul 05, 2019 10:31 pm

If you're going to go down this path, you might want to consider implementing a volatility targeting approach with a portion of your portfolio.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Fri Jul 05, 2019 10:44 pm

willthrill81 wrote:
Fri Jul 05, 2019 10:31 pm
If you're going to go down this path, you might want to consider implementing a volatility targeting approach with a portion of your portfolio.
Yes, I’d like to use leverage at some point but I don’t have access to cheap rates. I’m using Merrill, I have private banking privileges but still rates are not low enough. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
willthrill81
Posts: 10991
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: "Steelmanning" the case for owning individual stocks

Post by willthrill81 » Fri Jul 05, 2019 10:57 pm

hdas wrote:
Fri Jul 05, 2019 10:44 pm
willthrill81 wrote:
Fri Jul 05, 2019 10:31 pm
If you're going to go down this path, you might want to consider implementing a volatility targeting approach with a portion of your portfolio.
Yes, I’d like to use leverage at some point but I don’t have access to cheap rates. I’m using Merrill, I have private banking privileges but still rates are not low enough. :greedy
No leverage is needed to implement volatility targeting.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

MoneyMarathon
Posts: 235
Joined: Sun Sep 30, 2012 3:38 am

Re: "Steelmanning" the case for owning individual stocks

Post by MoneyMarathon » Sat Jul 06, 2019 1:48 am

hdas wrote:
Sat May 18, 2019 12:37 pm
Controlling for quality is the easiest and index providers do the work for you.

It's remarkable the level of diversification you can achieve with only 25 holdings.
What are your holdings? And how did you choose them?

I can't really tell from your updates whether you're holding individual stocks, or are using ETFs... and what they are.

rossington
Posts: 69
Joined: Fri Jun 07, 2019 2:00 am
Location: Florida Suncoast

Re: "Steelmanning" the case for owning individual stocks

Post by rossington » Sat Jul 06, 2019 4:50 am

Not sure where the OP is going here but: Investing in individual stocks is what was the norm prior to mutual/index funds. Investors made money the "old fashioned way" and did it with the principle of buy and hold that our beloved Jack Bogle espoused...Hence the foundation of Vanguard. All stock funds either active or index invest in individual stocks across specific criteria. It is the quality of these companies and their management that we rely on for our ROI. I learned how to invest (from my father) by doing research on individual stocks. We minimized our risk by buying the best quality stocks that fit our investment goals (Value Line as a research tool back in the day was our Bible...no computers or backtesting available). It has worked out very well ( '70's till now). You are your own fiduciary do the research...investing in ETF's or index/mutual funds can be as complicated as ind. stocks today but all will be rewarding with an asset allocation and risk tolerance that you need to achieve your goals.
"Success is going from failure to failure without loss of enthusiasm." Winston Churchill.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Jul 06, 2019 8:41 am

MoneyMarathon wrote:
Sat Jul 06, 2019 1:48 am

What are your holdings? And how did you choose them?
> I hold individual stocks.
> I prefer to keep the holding private. Besides, there’s a lot of turnover, 1-2 stocks per week.
> I rank the largest 1000 US stocks based on low volatility and momentum. Then select the top 25 after adjusting for sector diversification.
> The specific ranking methodology differs significantly from the traditional approaches.

Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Jul 06, 2019 8:43 am

rossington wrote:
Sat Jul 06, 2019 4:50 am
Not sure where the OP is going here but: Investing in individual stocks is what was the norm prior to mutual/index funds. Investors made money the "old fashioned way" and did it with the principle of buy and hold that our beloved Jack Bogle espoused...Hence the foundation of Vanguard. All stock funds either active or index invest in individual stocks across specific criteria. It is the quality of these companies and their management that we rely on for our ROI. I learned how to invest (from my father) by doing research on individual stocks. We minimized our risk by buying the best quality stocks that fit our investment goals (Value Line as a research tool back in the day was our Bible...no computers or backtesting available). It has worked out very well ( '70's till now). You are your own fiduciary do the research...investing in ETF's or index/mutual funds can be as complicated as ind. stocks today but all will be rewarding with an asset allocation and risk tolerance that you need to achieve your goals.
Value Line was better when Samuel Eisenstadt was there. Cheers. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

StandingRock
Posts: 212
Joined: Sat Feb 02, 2019 6:54 pm

Re: "Steelmanning" the case for owning individual stocks

Post by StandingRock » Sat Jul 06, 2019 8:47 am

If you have to invent words to make an argument you're probably wrong.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Jul 06, 2019 9:01 am

willthrill81 wrote:
Fri Jul 05, 2019 10:57 pm
hdas wrote:
Fri Jul 05, 2019 10:44 pm
willthrill81 wrote:
Fri Jul 05, 2019 10:31 pm
If you're going to go down this path, you might want to consider implementing a volatility targeting approach with a portion of your portfolio.
Yes, I’d like to use leverage at some point but I don’t have access to cheap rates. I’m using Merrill, I have private banking privileges but still rates are not low enough. :greedy
No leverage is needed to implement volatility targeting.
In my case it is because in this portfolio low vol is targeted from security selection and portfolio optimization. I already have extremely low volatility, the next logical step is to lever up. :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
willthrill81
Posts: 10991
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: "Steelmanning" the case for owning individual stocks

Post by willthrill81 » Sat Jul 06, 2019 9:03 am

hdas wrote:
Sat Jul 06, 2019 9:01 am
willthrill81 wrote:
Fri Jul 05, 2019 10:57 pm
hdas wrote:
Fri Jul 05, 2019 10:44 pm
willthrill81 wrote:
Fri Jul 05, 2019 10:31 pm
If you're going to go down this path, you might want to consider implementing a volatility targeting approach with a portion of your portfolio.
Yes, I’d like to use leverage at some point but I don’t have access to cheap rates. I’m using Merrill, I have private banking privileges but still rates are not low enough. :greedy
No leverage is needed to implement volatility targeting.
In my case it is because in this portfolio low vol is targeted from security selection and portfolio optimization. I already have extremely low volatility, the next logical step is to lever up. :greedy
Ah, I see.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Jul 13, 2019 11:11 am

This is week 17 of the experiment, some observations:

1. To the extent that the portfolio is doing better that SPY which was the goal (im only investing in large caps), we are doing ok. However, the portfolio is trailing the performance of a naive 50/50 MTUM, USMV benchmark by ~1.5%.

Image

2. This is the current composition of sectors:

Image

3. Here are the main avenues for improvement:

a.) Take advantage of the shifting regimes in the Low Vol - High Vol performance relationship (SPLV / SPHB ratio)

Image

b.) Shift from using low volatility as a ranking component, and use it as a criteria to get rid of high volatility stocks only. Preliminary tests in this suggests a nice increase in returns and a modest increase in portfolio volatility.

c.) Shift away from equal weighting to a more sophisticated weighting scheme, the key here is to implement the approach that has the best change to replicate out of sample and it's not complex. The candidates are:

>> Hierarchical Risk Parity

>> Covariance Matrix Shrinkage (Ledoit)

Image

>> Use Exponentially-weighted moving average instead of raw returns.

Here are some other additional links:

- Minimum Covariance Determinant (MCD): robust estimator of covariance.
- Covariance estimation :
Many statistical problems require the estimation of a population’s covariance matrix, which can be seen as an estimation of data set scatter plot shape. Most of the time, such an estimation has to be done on a sample whose properties (size, structure, homogeneity) have a large influence on the estimation’s quality. The sklearn.covariance package provides tools for accurately estimating a population’s covariance matrix under various settings.
- A Test of Covariance Matrix Forecasting Methods
Abstract
Providing a more accurate covariance matrix forecast can substantially improve the performance of optimized portfolios. Using out-of-sample tests, in this paper, we evaluate alternative covariance matrix forecasting methods by looking at (1) their forecast accuracy, (2) their ability to track the volatility of the minimum-variance portfolio, and (3) their ability to keep the volatility of the minimum-variance portfolio at a target level. We find large differences between the methods. Our results suggest that shrinkage of the sample covariance matrix improves neither the forecast accuracy nor the performance of minimum-variance portfolios. In contrast, switching from the sample covariance matrix forecast to a multivariate GARCH forecast reduces forecasting error and portfolio tracking error by at least half. Our findings also reveal that the exponentially weighted covariance matrix forecast performs only slightly worse than the multivariate GARCH forecast.
- The Impact of Covariance Misspecification in Risk-Based Portfolios
Abstract
The equal-risk-contribution, inverse-volatility weighted, maximum-diversification and minimum-variance portfolio weights are all direct functions of the estimated covariance matrix. We perform a Monte Carlo study to assess the impact of covariance matrix misspecification to these risk-based portfolios. Our results show that the equal-risk-contribution and inverse-volatility weighted portfolio weights are relatively robust to covariance misspecification, but that the minimum-variance and maximum-diversification portfolios are highly sensitive to errors in the estimated variance and correlation, respectively.
Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

Caduceus
Posts: 1934
Joined: Mon Sep 17, 2012 1:47 am

Re: "Steelmanning" the case for owning individual stocks

Post by Caduceus » Sat Jul 13, 2019 4:49 pm

The idea of basing an investment strategy on a stock's volatility is absurd. At the end of the day, a stock represents fractional ownership in a company, and it is that company's fundamental business performance and future prospects that will determine the stock's long term price. If the company gets more valuable, the stock will become more valuable, and if the company flounders, the stock will as well.

If you want to go this route, I suggest looking at people who have actually done very well over long periods of time. Warren Buffett is a billionaire, as is Seth Klarman. The Wall Street traders who do things like "low-vol stocks" might be multi-millionaires, but they have not enjoyed a tiny fraction of the success of investors who are value investors.

Why not learn some accounting, actually read financial statements, start with very simple businesses, and see if you can understand them?

I suggest the shareholder letters of Warren Buffett. Take a look at his early investments. He once bought a company that was selling for less than the price of its stock portfolio. This was a company that was in the business of making maps for insurance companies; it was a business where you make a map once and then you rarely have to update the map, and you get a stream of royalty on your intellectual property. The firm also owned many stocks, and the market was valuing the entire firm at less than the value of the stock portfolio. So you could have bought up the firm, sold the stocks, made a profit, and then got the map business for free. Of course you are going to get very, very, very rich if you can find positions like that. But they are hard to find.

Investing is not a mathematical or a statistical problem, and attempting to use math to improve returns is slightly south of idiotic. We are not talking about a world that is regulated by laws of physics so there is no reason that math beyond basic arithmetic should have any sway here. What you need are skills to evaluate the value of a business, the same way that say, a small business owner attempting to sell his firm will have to value his firm. If I have a business that has made 10 million a year the last ten years and I'm carrying no debt, the fair market value might be something like 100-200 million a year; if the stock market offers you a fractional interest at 50 million, you buy the business. Do it often enough, you make a lot of money. What's difficult is that financial statements LIE all the time. Firms include things in earnings that don't belong there; they shift earnings around; they buy back stocks, etc. This is a more productive route if you want to improve returns.

Just because you are strong in math doesn't mean it is the right tool. You might be a gifted dentist. Doesn't mean you are gonna be a good investor. A dentist probably has more relevant skills than the type of math you are trying to apply. You want to get rich? Learn accounting.

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Sat Jul 13, 2019 7:21 pm

Caduceus wrote:
Sat Jul 13, 2019 4:49 pm
The idea of basing an investment strategy on a stock's volatility is absurd.
Image
Caduceus wrote:
Sat Jul 13, 2019 4:49 pm
I suggest the shareholder letters of Warren Buffett.
20 years late...but thanks.
Caduceus wrote:
Sat Jul 13, 2019 4:49 pm
Investing is not a mathematical or a statistical problem, and attempting to use math to improve returns is slightly south of idiotic.
Hello?. Most successful funds of all time are highly quantitative.
Caduceus wrote:
Sat Jul 13, 2019 4:49 pm
You want to get rich? Learn accounting.
LOL...you take the price for joke of the day.

Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
CyclingDuo
Posts: 2358
Joined: Fri Jan 06, 2017 9:07 am

Re: "Steelmanning" the case for owning individual stocks

Post by CyclingDuo » Mon Jul 15, 2019 6:47 am

hdas wrote:
Tue Jan 29, 2019 12:48 pm
I found the wiki section very good.
Yes, it's very good portion of the Wiki to study. If you want to passively hold a DIY index fund made up of individual stocks, one can do very well. The studies and data presented are quite telling. Not many have the patience of longer term buy and hold of a broad, diverse portfolio to "allow" a DIY index fund portfolio of individual stocks to be successful.

From the Wiki link....

Ikenberry, Shockley and Womack

They found that for 35-stock portfolios, where the stocks are randomly chosen from the S&P 500 index and equally weighted, the average yearly median portfolio return lags the mean by 0.22%. This number goes down to 0.14% for 50-stock portfolios, 0.09% for 75-stock portfolios, 0.06% for 100-stock portfolios, and 0.03% for 150-stock portfolios. The skewness cost is somewhat lower for capitalization-weighted portfolios, and for equal-weighted portfolios where the probability of selecting a stock is proportional to its market capitalization.


So they say.

I can see that having no ER fees can make up any, if not all of the skew in an equally weighted, randomly chosen portfolio holding 75-150 stocks compared to the S&P 500 index. In most cases, it is probably a lot easier to just buy the index fund at that point than purchasing 100-150 individual stocks and making sure it was equally weighted. However, for those who have the patience and enough capital to spread through that many individual stocks, sectors, factors - the path to success is laid out to do it.

Obviously, the location of the individual stocks is also important for tax strategies (REITs in tax advantaged and or Roth accounts, etc....). When on auto-pilot (DRIPs) and being passive with the DIY index portfolio, it's a rather low maintenance proposition in terms of not taking up any time throughout your year once you get it all allocated and set up. Again - not many have the patience of longer term buy and hold to "allow" a DIY portfolio to be successful. In this case, successful would be matching the return of the an index fund on the equity side of the portfolio. There is a lot of room for behavioral finance mistakes to upsot the apple cart when dealing with a portfolio made up of individual stocks covering 75-150 companies. Patience and the ability to watch paint dry for years at a time is required... 8-)
"Everywhere is within walking distance if you have the time." ~ Steven Wright

Alex GR
Posts: 78
Joined: Mon Jul 31, 2017 9:17 am

Re: "Steelmanning" the case for owning individual stocks

Post by Alex GR » Mon Jul 15, 2019 9:22 am

Caduceus wrote:
Sat Jul 13, 2019 4:49 pm
The idea of basing an investment strategy on a stock's volatility is absurd. At the end of the day, a stock represents fractional ownership in a company, and it is that company's fundamental business performance and future prospects that will determine the stock's long term price. If the company gets more valuable, the stock will become more valuable, and if the company flounders, the stock will as well.

If you want to go this route, I suggest looking at people who have actually done very well over long periods of time. Warren Buffett is a billionaire, as is Seth Klarman. The Wall Street traders who do things like "low-vol stocks" might be multi-millionaires, but they have not enjoyed a tiny fraction of the success of investors who are value investors.

Why not learn some accounting, actually read financial statements, start with very simple businesses, and see if you can understand them?

I suggest the shareholder letters of Warren Buffett. Take a look at his early investments. He once bought a company that was selling for less than the price of its stock portfolio. This was a company that was in the business of making maps for insurance companies; it was a business where you make a map once and then you rarely have to update the map, and you get a stream of royalty on your intellectual property. The firm also owned many stocks, and the market was valuing the entire firm at less than the value of the stock portfolio. So you could have bought up the firm, sold the stocks, made a profit, and then got the map business for free. Of course you are going to get very, very, very rich if you can find positions like that. But they are hard to find.

Investing is not a mathematical or a statistical problem, and attempting to use math to improve returns is slightly south of idiotic. We are not talking about a world that is regulated by laws of physics so there is no reason that math beyond basic arithmetic should have any sway here. What you need are skills to evaluate the value of a business, the same way that say, a small business owner attempting to sell his firm will have to value his firm. If I have a business that has made 10 million a year the last ten years and I'm carrying no debt, the fair market value might be something like 100-200 million a year; if the stock market offers you a fractional interest at 50 million, you buy the business. Do it often enough, you make a lot of money. What's difficult is that financial statements LIE all the time. Firms include things in earnings that don't belong there; they shift earnings around; they buy back stocks, etc. This is a more productive route if you want to improve returns.

Just because you are strong in math doesn't mean it is the right tool. You might be a gifted dentist. Doesn't mean you are gonna be a good investor. A dentist probably has more relevant skills than the type of math you are trying to apply. You want to get rich? Learn accounting.
Hi Caduceus,
I fully agree with you in that value investing is the way to go. Seems like buying and selling stocks based on volatility and various mathematical statistics works... until it doesn't.

However since most people are not qualified to pick stocks themselves, what about this approach:
(a combination of holding long-term value stocks and having your own "system")

1. Find a source (or several) that has consistently been successful at factor investing. Example: MTUM.
Question: When they make a change to their holdings is this info available immediately? I really don't know. Do we know the date the buy/sell and the purchase price?
Visa Inc. Class A 5.15%
Mastercard Incorporated Class A 5.14%
Microsoft Corporation 5.06%
Procter & Gamble Company 4.98%
Walt Disney Company 4.31%
Cisco Systems, Inc. 3.83%
Comcast Corporation Class A 2.91%
Merck & Co., Inc. 2.63%
PayPal Holdings Inc 2.62%

etc.

2. Come up with a short list of stocks that match your criteria. Perhaps factor in P/E ratios and dividends into the formula and narrow the list down further. To do this successfully one would need to learn fundamental analysis as you're suggesting.

3. Put in orders to buy the stocks that made it to the final list at 5%-10%(or varying percentages based on some criteria) less than the price your "trusted" fund(s) paid for them.
Of course in most cases it won't happen but 1-2 will go through which means you bought stock you want to own anyway at a discount. You can get creative and make a rule that you sell 1/2 if it goes back to the "target" price that your "trusted fund" paid for it, etc.

Seems this would work for someone who is relatively inexperienced and doesn't know how to do the advanced analysis OP is describing but wants to get a piece of the action and follow a simple system. :greedy

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Re: "Steelmanning" the case for owning individual stocks

Post by hdas » Mon Jul 15, 2019 9:49 am

Alex GR wrote:
Mon Jul 15, 2019 9:22 am

Question: When they make a change to their holdings is this info available immediately? I really don't know. Do we know the date the buy/sell and the purchase price?



Next business day, no price info tho.

Alex GR wrote:
Mon Jul 15, 2019 9:22 am

3. Put in orders to buy the stocks that made it to the final list at 5%-10%(or varying percentages based on some criteria) less than the price your "trusted" fund(s) paid for them.
Of course in most cases it won't happen but 1-2 will go through which means you bought stock you want to own anyway at a discount. You can get creative and make a rule that you sell 1/2 if it goes back to the "target" price that your "trusted fund" paid for it, etc.

Seems this would work for someone who is relatively inexperienced and doesn't know how to do the advanced analysis OP is describing but wants to get a piece of the action and follow a simple system. :greedy


This could be problematic, you might want to become acquainted with the issue of adverse selection and asymmetric information. Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

Alex GR
Posts: 78
Joined: Mon Jul 31, 2017 9:17 am

Re: "Steelmanning" the case for owning individual stocks

Post by Alex GR » Mon Jul 15, 2019 10:05 am

hdas, thanks for your reply
Watching your work very closely, please keep us posted.
I don't understand some of it but in general I really like the idea of following some type of "system" and active trading for ~5% of my portfolio.
Sounds like you're a programmer with very strong experience in data analysis.
No idea what you said in your last sentence but all I was trying to do is come up with a simple system that someone who doesn't have your skills can follow.
In layman's terms, can you explain what's wrong with the idea I posted? Seems like it would allow you to buy stocks you want to own anyway but with a further discount, improving your bottom line.
The idea is to only do this with stocks you want to hold long-term anyway (like the ones in my example) so you can't lose (or you can but you keep telling yourself that you can't 'cause otherwise you would have bought it 5% higher :mrgreen:)

User avatar
Taylor Larimore
Advisory Board
Posts: 28400
Joined: Tue Feb 27, 2007 8:09 pm
Location: Miami FL

Re: "Steelmanning" the case for owning individual stocks

Post by Taylor Larimore » Mon Jul 15, 2019 11:45 am

I'm looking forward to hear the best arguments against embarking in this effort, specifically about the desirability of the strategy features and the tax situation.
hdis:

This is what experts say:
Alpha Architect: "Between 1983 and 2006, around 73% of firms had a drawdown larger than 50% (the S&P 500’s maximum drawdown during this period was around 44%). Holding one individual stock can be very risky!"

Barber and Odean Study: "Of 66,465 households with accounts at a large discount broker during 1991 to 1996, those that trade most earned an annual return of 11.4 percent, while the market returned 17.9 percent."

Michael Batnick, CFA: "Ordinary investors would be well served if they thought for a second about who they were transacting with. Over 90% of today’s volume is done by institutions, so chances are that your counter-party has done their homework."

Brett Arends, Wall Street Journal columnist: "Buy individual stocks only as a gamble."

Benjamin Graham: "I have little confidence, even in the ability of analysts, let alone untrained investors, to select common stocks what will give better than average results."

Bill Bernstein, author of The Four Pillars of Investing: "Picking individual stocks is like volleying with the Williams sisters."

Jack Bogle: "Attempting to build an investment program around a handful of individual securities is, for all but the most exceptional investors, a fool's errand."

Adam Bold, author, adviser: "Mutual funds don't have the pizzazz of the hot stocks of the moment. If you're looking for entertainment, go gambling in Las Vegas. But if you want to accumulate real money for your retirement and other goals, mutual funds are the safer bet."

James Dahle, MD, financial advisor, and author of The White-Coat Investor: “Think you know how to pick stocks? Then guess again. Every time you buy or sell the person on the other side of the trade likely has an IQ of 160, spends 70 hours per week analyzing his industry, and has access to computing power and databases you can only dream of.”

Dalbar Research Report (July 15, 2003): "The average equity investor earned a paltry 2.57% annually; compared to inflation of 3.14% and the 12.22% the S & P 500 index earned annually for the last 19 years."

Charles Ellis author of Winning the Loser's Game: "If you, like Walter Mitty, still fantasize that you can and will beat the pros, you'll need both luck and prayer."

Kenneth French: Former President of the American Finance Association: "The market is smarter than we are and no matter how smart we get, the market will always be smarter than we are."

Sy Harding, Forbes contributor: "My advice – avoid individual stocks! Even experienced full-time professional money managers, with staffs of trained people performing research, with access to data, software, and corporate contacts that most part-time investors could not come close to duplicating, struggle to match the market’s performance by buying, holding, or selling individual stocks."

Danial Kahneman, Nobel Laureate: "There is general agreement among researchers that nearly all stock pickers, whether they know it or not-and few of them do-are playing a game of chance."

Kiplinger Personal Finance “Eight Stocks to Buy Now” in the January, 2015 forecast issue under-performed its “Five Stocks to Sell” twelve months later.

Michael Lewis, former bond broker and financial journalist: "A vast industry of stockbrokers, financial planners, and investment advisers skims a fortune for themselves off the top in exchange for passing their clients' money on to people who, as a whole, cannot possibly outperform the market."

Mathwizard: The vast majority of trades you would make are between you and a professional investor. Both of you are assigning a value to the stock, and one of you thnks the price is high and another thinks it is low. Who do you suppose is more likely to be right.

Charlie Munger, Warren Buffett's partner: "Teaching young people to actively trade stocks is like starting them on heroin."

Standard & Poor's: When the S&P 500 index was officially formed in 1957 to its 50th anniversary in 2007, only 86 of the original 500 companies still remained.

Larry Swedroe, author of many financial books: "Owning individual stocks and sector funds is more akin to speculating, not investing."

David Swensen, Chief Investment Officer of Yale University: "There's no way that spending a few hours a week looking at individual securities is going to equip an investor to compete with the incredibly talented, highly qualified, extremely educated individuals who spend their entire professional careers trying to pick stocks."

Eric Tyson, author of Mutual Funds for Dummies: The notion that most average people and non-investment professionals can, with minimal effort, beat the best full-time, experienced money managers is, how should I say, ludicrous and absurd."
Best wishes.
Taylor
Jack Bogle's Words of Wisdom: "A broker has to sell you something or he doesn't eat at the end of the day."
"Simplicity is the master key to financial success." -- Jack Bogle

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Portfolio Optimization

Post by hdas » Tue Jul 16, 2019 1:29 pm

This is a really good read. Some excerpts:
Specifically, we evaluate the performance of naive versus optimized portfolios on the following data sets, which are all available at daily scale:

10 U.S. market-cap weighted industry portfolios from the Ken French data library
25 U.S. market-cap weighted equity factor portfolios sorted on size and book-to-market (i.e. value) from the Ken French data library
38 U.S. market-cap weighted sub-industry portfolios from the Ken French data library
49 U.S. market-cap weighted sub-industry portfolios from the Ken French data library
12 global asset classes from multiple sources2
We form portfolios at the end of each quarter, with a one day delay between calculating optimal portfolio weights and trading.
Portfolio Optimization Methods:

- Minimum Variance
- Maximum Diversification
- Maximum Decorrelation
- Risk Parity
- Inverse Volatility and Inverse Variance
- Equal Risk Contribution
- Hierarchical Minimum Variance
One way to determine the amount of idiosyncratic risk in a universe of assets is to use Principal Component Analysis (PCA). PCA is a tool to identify the underlying independent (i.e. uncorrelated) sources of risk, or principal components, of the investments.

The results of PCA are eigenvalues, λ, which describe the amount of total variance explained by each principal component, and the eigenvectors A, which describe the sensitivities or “betas” of each asset to each principal component. There are always the same number of eigenvalues and eigenvectors as investments, so a universe of ten investments will be decomposed into ten eigenvectors with associated eigenvalues.
Image
Number of independent “bets”

To understand just how little opportunity for diversification there is in (DeMiguel, Garlappi, and Uppal 2007)’s choices of investment universes, we found it useful to quantify the number of uncorrelated sources of return (i.e. independent bets) that are available in each group of investments. Recall that (Choueifaty and Coignard 2008) showed that the Diversification Ratio of a portfolio is the ratio of the weighted sum of asset volatilities to the portfolio volatility after accounting for diversification.

This is intuitive because, if all of the assets in the portfolio are correlated, the weighted sum of their volatilities would equal the portfolio volatility, and the Diversification Ratio would be 1. As the assets become less correlated, the portfolio volatility will decline due to diversification, while the weighted sum of constituent volatilities will remain the same, causing the ratio to rise. At the point where all assets are uncorrelated (zero pairwise correlations), every asset in the portfolio represents an independent bet.

Consider a universe of ten assets with homogeneous pairwise correlations. Figure 2 plots how the number of independent bets available declines as pairwise correlations rise from 0 to 1. Note when correlations are 0, there are 10 bets, as each asset is responding to its own source of risk. When correlations are 1, there is just 1 bet, since all assets are explained by the same source of risk.

(Choueifaty, Froidure, and Reynier 2012) demonstrate that the number of independent risk factors in a universe of assets is equal to the square of the Diversification Ratio of the Most Diversified Portfolio.

Taking this a step further, we can find the number of independent (i.e. uncorrelated) risk factors that are ultimately available within a universe of assets by first solving for the weights that satisfy the Most Diversified Portfolio. Then we take the square of the Diversification Ratio of this portfolio to produce the number of unique directions of risk if we maximize the diversification opportunity.
Image
One of the most important qualities investors should investigate is the amount of diversification available relative to the number of assets. If the quantity of available diversification is small relative to the number of assets, the noise in the covariance matrix is likely to dominate the signal.

We’ll call the ratio of the number of independent bets to the number of assets in an investment universe the “Quality Ratio”. The “Quality Ratio” is a good proxy for the amount of diversification “signal to noise” in the investment universe. When the Quality Ratio is high we would expect optimization methods to dominate naive methods. When it is low, investors should expect only a very small boost in risk-adjusted performance from using more sophisticated techniques.
Image
Simulation results

We run simulations on each of our target investment universes to compare the simulated performance of portfolios formed using naive and optimization based methods. Where volatility or covariance estimates are required for optimization, we use the past 252 days to form our estimates. We perform no shrinkage other than to constrain portfolios to be long-only with weights that sum to 100%. Portfolios are rebalanced quarterly.

For illustrative purposes, Figure 5 describes the growth of $1 for simulations on our universe of 25 portfolios sorted on price and book-to-market. Consistent with the ready availability of leverage, and for easy comparison, we have scaled each portfolio to the same ex-post volatility as the market-capitalization weighted portfolio7. We assume annual leverage costs equal to the 3-month T-bill rate plus one percent. Scaled to equal volatility, portfolios formed using Minimum Variance have produced the best performance over the period 1927 – 2017.
Image
Discussion of simulation results

Stocks

The first things to notice is that all methods outperformed the market cap weighted portfolio with a few notable exceptions: the Maximum Diversification portfolio underperformed the market cap weighted portfolio on the factor sort universe.

Asset Classes

Our belief that diversified asset classes should have equal long-term Sharpe ratios led us to hypothesize that the Maximum Diversification portfolio should dominate in the asset class universe. We expected the equal weight and Minimum Variance strategies to underperform. These predictions played out in simulation. The Equal Risk Contribution and Inverse Volatility weighted approaches were also competitive, which suggests the assumption of constant correlations may not be far from the mark.

Tests of significance

While the Minimum Variance strategy produced the highest sample Sharpe ratio for all of the equity oriented universes, Risk Parity based methods like Equal Risk Contribution and Inverse Volatility were even more dominant from a statistical standpoint. The Hierarchical Minimum Variance approach also demonstrated a high degree of statistical robustness.

For the asset class universe, all but the Hierarchical Minimum Variance portfolio outperformed the equal weight portfolio on a statistically significant basis. And the Hierarchical Minimum Variance portfolio outperformed the equal weight portfolio 93% of the time. This further validates the importance of optimization when the universe of assets has diverse volatility and correlation features.

Risk Parity methods are more likely to dominate equal weight portfolios because they exhibit a smaller amount of active risk relative to the equal weight portfolio. However, while the Risk Parity portfolios might outperform the equal weight portfolios slightly more frequently on a relative basis, they are likely to more frequently underperform Minimum Variance and Maximum Diversification, for equity and asset class universes respectively, on an absolute basis.
Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

User avatar
Topic Author
hdas
Posts: 969
Joined: Thu Jun 11, 2015 8:24 am

Factor Exposure Checkup

Post by hdas » Thu Jul 18, 2019 3:39 pm

Let's look at the factor exposure snapshot using portfolio visualizer:

Period: Since 2016 (~3 years)
Factor Data: AQR

1. Market (Rm-Rf), Size (SMB), Momentum (MOM)

Image

2. Market (Rm-Rf), Size (SMB), Momentum (MOM), Quality (QMJ)

Image

3. Market (Rm-Rf), Size (SMB), Momentum (MOM), Quality (QMJ)

Image

4. Market (Rm-Rf), Size (SMB), Momentum (MOM), Quality (QMJ), Term Risk (TRM), Credit Risk(CDT)

Image

Some takeaways:

1. There's residual significant alpha after adding all the factors.
2. Every sequential add of a factor in the regression improves the R^2
3. Not going to get caught up on factor exposure as long as we keep outperforming the benchmark.
4. The goal is to outperform the naive 50/50 MTUM, USMV

Cheers :greedy
"whenever there is a randomized way of doing something, then there is a nonrandomized way that delivers better performance but requires more thought" ET Jaynes

Post Reply