Sunday, May 29, 2011

Strategy actual expectancy uncertainty

Despite that any trading strategy, even with a high Expected Value and awesome looking historical equity curves, possible losses within a small sample (e.g. a few hundred trades) are expected. Of course there's also the chance that it does not really make money, and that the back test data simply got lucky. The same thing could happen with a conventional business failures where they may have started with awesome concepts, but with no empirical evidence.

So how do we deal with it? As Nassim Taleb has mentioned in Models on Models, practically profitable trading strategies often hold robust theory and have little dependence on probability estimate.

Purely statistics based trading strategies are dangerous.

 Pure number crunching does not reflect how markets evolve, and that financial distributions have consistently implied a pathological nature. This means we can NOT assume that bigger sample back test results converge to population statistics, i.e. great historical performance are really meaningless without robust principle explaining the inefficiency exploited.

Here's a simple applet from HQuotes showing possible equity curves with customized expected values, for a small number of bars(trades). We can see that unless you have a significant edge, short term performance really can not be trusted!

Monday, May 23, 2011

Stock Fair Value estimate via Discounted Cash Model

So the Fair Value Graph at Morningstar, applying a Discounted Cash Model, caught my attention. It makes economic sense, has a positive correlation to the underlying indices, naturally I looked for details. The guy at "My Coverd Call Blog" made a pretty cool post explaining the formula:

Benjamin Graham describes a simpler formula to determine intrinsic value.
Formula: V = EPS x (8.5 + 2G) * (4.4 / Y)
  • V: Intrinsic Value
  • EPS: the company’s last 12-month earnings per share
  • 8.5: the constant represents the appropriate P/E ratio for a no-growth company as proposed by Graham
  • G: the company’s future long-term (five years) earnings growth estimate
  • 4.4: the average yield of high-grade corporate bonds in 1962, when this model was introduced
  • Y: the current yield on AAA corporate bonds
I use the modified formula from Old School Value, which uses a P/E of 7 for a no-growth company and a multiplier of 1.5G rather than 2G, since these are more conservative.

Modified Formula: V = EPS x (7 + 1.5G) * (4.4 / Y)
The original formula uses the last 12-month EPS (TTM), however, like Old School Value, I normalize EPS over a 10 year period, which estimates future EPS for the next 5 years, using a linear forecast based on the previous 10 years, and then takes the median of the previous 5 years and next 5 years to arrive at a normalized EPS. For estimated future 5yr growth rate I use 3 different sources, 1) Yahoo Finance, 2) Morningstar, and 3) MSN Money. I found that each site has a different 5yr estimate, so I use an average of these estimates."

We can see that the it's mostly straight forward, just that earnings expectations remain uncertain. So that is where more research remains to be done!

Wednesday, May 18, 2011

About Kerrisdale Capital's 2011 Q1 73% Return

Kerrisdale Capital appears to be a hedge fund who specializes in finding distressed securities around fraud. Bottom line here: small niche, big edge. They're up 299% since inception in 2009.

Here's their latest Quarterly Letter, around how they make money.

Kerrisdale Quarterly Letter 3-31-11

Tuesday, May 17, 2011

Sports etting rbitrage software discount

An associate of mine is offering this sports betting arbitrage software package. The basic idea is to find bookies whose odds present (almost) risk free net profit for specific sporting events.

US residents currently do not have access to online betting due to domestic laws.

Here's the kicker. If you decide to give it a try with a purchase, let me know that you've done so and you will receive a $10USD rebate from my associate.

Betting Arbitrage Software Link

Wednesday, May 11, 2011

Kiwisaver funds performance review

This is from Leon's Musings

...twelve month performance for most NZ equity funds was in the 4~5% range with only a few breaking 7% and going out to 3 years their performance drops around another 3%.  With 6 month cash term deposits up around 4.6% it’s probably no wonder funds are languishing.

This is before all the crazy fees imposed upon the people. I feel that the problem with local New Zealanders and these retirement fund schemes is that they give too much credit to the government that they got good people managing their life savings. They obviously do not, if they've under performed against the actual rate of inflation, which is obviously higher than the local bank Term Deposits, since more interest has been created off higher rated loans (mortgages, credit cards, etc.).

Yes this naturally implies that government incentives do not always benefit the working, middle class. In this case, these Kiwisaver funds are likely to really benefit the government borrowers and the few large mutual fund outfits in New Zealand.

Sunday, May 8, 2011

Rats trained to trade

Yes, rats trained to forecast financial markets, literally. The methodology feels conceptionally similar to that of existing AI algorithms such as Support Vector Machines or Extreme Learning Machines. While this is interesting, this introduces a whole new level of risk as now we much estimate behavior norms of these living rats. At the same time, if some of these patterns are simple enough for rats to figure out, the average human mind is then naturally more than capable just as well. Are we moving in circles here?