Philosophical Musings

December 23, 2008

Stock Market Prediction Services – Caveat Emptor

Filed under: investing — Elad Kehat @ 10:07 pm

Services that offer to assist investors in predicting the behavior of capital markets always make me lough. The exact nature of the method du jour is not important; be it charting (that has idiotically become mainstream) or the new new thing – tapping into the wisdom of the crowds as captured online (see for example StockMood, and most activity on prediction markets such as AskMarkets). Either way, the subscriber to such a service is unlikely to profit from it.
The reason is not some inherent flaw of the methods used for prediction, but rather a simple human reasoning. I know because I dabbled in an attempt to develop such a method myself (with a little help from my friends). The idea was to mine online investor generated content in search of correlations between some of its properties and future market movements. We were unsuccessful at the time, but I shall not expand more on the details of the attempt, as I have not given up hope entirely – and that (as shall become clear momentarily) is the whole point of this post.
I dubbed our attempt “The Money Printer Project”, since should it have been successful, we would have had a machine in our hands that is equivalent to a (legal) printer of dollar bills. After all, if you develop a method to predict how stock prices will change before they actually do, at a better than random probability, you will most likely making a lot of money using it. (Only most likely because there is also the likelyhood of you ignoring the math and using emotion, thus making stupid mistakes and losing.)
Of course, if your method became known and popular, it will cease to be useful, as others will be able to predict your actions and either preempt you or simply trade against you. You can rely on larger financial institutions, as well as investors bigger than yourself, to have greater resources, access to greater computing power, and the ability to execute trade faster and cheaper than you. There is no for you to win against them, so your game must not be known – you have to be the only player playing that game.
Assuming that anyone intelligent enough to develop such a method also realizes the points above, they would never offer their method to others. The only reason to offer this method is if it doesn’t really work. There are enough gullible investors out there that can be impressed by a sophisticated (yet false) prediction model. It is far easier to succumb to greed than to try and falsify such a model scientifically.
In other words, if someone offers you a system that can help you predict capital markets they are probably lying. If it was indeed successful, they would have used it themselves. If they sell its predictions instead, it is most likely because that is the only way to make money out of it.


August 23, 2007

Some More Shoddy Statistics

Filed under: business,investing,statistics — Elad Kehat @ 10:47 am

Founders know best, says USA Today: “Firms tend to prosper with founders at the helm“.
As a startup founder myself, I was naturally intrigued – what data supports this conclusion?

“Going back 15 years, stocks in founder/CEO companies have surged an average 970%, vs. a 222% gain for the S&P 500, according to data from S&P’s Capital IQ.”

Oh. See the problem? If not, read on…
The article goes on to try and explain (unsurprisingly, with no further hard data) why it is that founders are so successful at managing their own companies. No further consideration is given to the idea that this may just be a false correlation.
So here’s the problem: Del Jones and Matt Krantz, the USA Today reporters, compare the 15 year performance of companies with founder at the helm vs. companies in general.
What about an alternative explanation: public companies that have the same CEO at the helm for 15 years must have a damn good CEO. Otherwise they wouldn’t be successful and the board would find someone else for the job.
It’s nice that they use a system called “Capital IQ”, but a little more of it (or a passing understanding of statistics, or a minimum level of critical thought) would have prompted them to dig further and compare those founder/CEO companies to other companies that had the same CEO for the past 15 year. Would that study yield the same result? Or would that just lead to no article and an angry editor?

Or maybe it isn’t reporters fault:
“Ohio State University finance professor Rudi Fahlenbrach”. This is from a top-60 university?

And the “experts” seem to fall for it with no trouble at all:
“I should’ve attached more attention to it over the years,” says Rob Sellar, a money manager of Aberdeen Asset Management.
Really, Mr. Sellar? How about “attaching” more attention to what’s missing from the data? After all, there no telling in this “research” whether all companies headed by their founders succeed, just that public companies that had a leader successful enough to stay at the helm for the past 15 years are successful…

April 27, 2007

The Problem with Munger’s Worldly Wisdom

Filed under: investing — Elad Kehat @ 7:43 am

I recently came across the transcript speech made by Charlie Munger, of Berkshire Hathaway fame, to the U of South California Business School in 1994. The speech, titled “A Lesson on Elementary, Worldly Wisdom As It Relates To Investment Management & Business”, is both insightful and entertaining, which makes it a great read.
Nevertheless, I believe that there’s a big problem with the system that Munger recommends we use in managing our financial investments.
Essentially, what Munger suggests is that we limit ourselves to a very small number of investments (say 20 in a lifetime) and be very diligent about picking those few. Whenever we do find one that passes our extreme scrutiny, we should load on it, and stick with it for the long term.
Munger has a lot to show for his method – Berkshire Hathaway has been built on this system with a small number of exteremely successful investments that have multiplied tens of times in value over a few decades. These include Coca Cola, American Express, Walmart and The Washington Post, to name a few well known examples.
But is this system really a good choice for the average Joe? Say you’re like me, in your thirties, making a nice income in your day job, and trying to invest your savings well enough so that you can retire comfortably 30 or 40 years from now. What would be a wiser choice for you to follow, Munger’s system, or building a diversified portfolio from a bunch of market index ETFs that would guarantee you more or less average market performance?
Obviously, if you want above average returns, you can’t go with the market index funds option, and Munger offers good reasons why letting money managers play with your money isn’t very likely to give you that desired edge either (you’re more likely to get sub-par returns). However, let’s analyze the Munger system, and see whether you’re likely to be better off using it.
The Munger system – picking only a handful of stocks over your lifetime, sticking with them, and sticking for the long haul, requires you to be a very good stock picker. After all, if you only pick a handful, there’s not much room for error. It makes perfect sense – if you pick only winners, you’ll win big, but are you going to pick the winners?
That’s why Munger suggests that you pick just a few – you can’t know everything about everybody, so you better focus more narrowly. That assumption suffers on two fronts: (a) you don’t have the time, experience and access that Buffett and Munger have in order to focus as well as they do and (b) you’re simply not as good at recognizing the good from the bad as they are. There’s a reason that there’s only one Buffett. As Munger himself says, only one fifth can be at the top 20%, and this guy is at the top 0.00001%… To the genius it seems as if he’s just applying simple worldly wisdom, to the rest of us, he’s applying magic.
So what’s your outcome likely to be if you apply Munger’s system? Let’s use Munger’s worldly wisdom – the bell curve. The majority of stock pickers will make average picks, and overall get average returns, a minority will make above average return, and a small minority’s returns will be truly spectacular. The flip side is of course that there’s an equal minority who’ll make below average returns, and a small minority who’s returns will be just horrible.
Making just a few picks in your lifetime does not guarantee the quality of your picks. Moreover, the less attempts you make at stock picking, the more likely you are to be affected by chance than to let your skill shine through.
What it all comes down to is that on average, users of the Munger system will make average returns. The average in a bell curve (assuming that stock picking aptitude is distributed normally) also includes the majority, so that’s most likely where you’ll end up. No better than if you just invested in some index funds.
There’s still the minority that makes better returns, and there’s a fair chance that you’ll end up there. That’s great, but you have to remember that it’ll be your reward for taking a risk. The risk is that you have an equal chance to fall in the bottom of the bell curve, and then woe to you. For you have to keep in mind that it’s life savings that we’re gambling with here. If you have the bad luck of being one of the bad stock pickers who just thought he could strike it rich by taking additional risk, then say goodbye to your cozy retirement.
In short, while Munger is witty, insightful and funny, and while it’s terribly tempting to believe that you too can become a billionaire (or merely very well off) by following his simple strategy, you better be damned sure that you’re a way-above-average stock picker to follow that strategy in your spare time and expect to win.
As for me, I’m definitely not against risk taking – my friends think of some of my decisions as terribly risky, but I try to take risks only with the things I know, from experience and conviction, that I’m good at. My experience with stocks has taught me that stock picking isn’t one of those things, and so my savings are better off in an index fund making average returns.

Blog at