Two new models have been added to the Models page at foquant.com.

The first is the Gordon Growth Model, which is a very simple equity valuation tool. This model features a chart that shows the difference in price dependent upon the dividend growth rate. This is important, because as the growth rate approaches the required rate of return, the value of the equity approaches infinity.

The second is a C++ calculator for a standard coupon bond. The user is asked for inputs concerning the bond, and the value is printed to the screen. Similar to the GGM, this file will also show a range of prices depending upon discount rates, providing almost a high to duration and convexity.

On the topic of the Models page - this page will soon be redesigned. It will be laid out by topic model type, making it easier to view. While this may not seem necessary now as there are only a handful of models, this will be useful as the page grows and the models increase in complexity.

I’ve completed about half of the book on Einstein, and it is very apparent that he prefers deductive reasoning over inductive reasoning. Simons, in 2000, made the opposite argument regarding his Medallion Fund:

We don’t start with models. We start with data. We don’t have any preconceived notions. We look for things that can be replicated thousands of times. A trouble with convergence trading is that you don’t have a time scale. You say that eventually things will come together. Well, when is eventually?

This identifies a divide between the methods of trading strategy creation.

First, you have those who believe that trading methods should be created through the analysis of existing characteristics. Behavioral finance and much of market microstructure theory are based upon this type of reasoning.

Second, you have those who believe that any pattern or anomaly derived from data is just as substantiated. Medallion’s historic returns are based upon this type of reasoning.

I thought this was interesting after reviewing ASTA, which seems to have capabilities of supporting both approaches. Perhaps, the solution to the question of which method is more appropriate is based upon what the trader believes they are looking for. Einstein was looking for underlying laws, and from a prior post we already know that Simons doesn’t believe in underlying laws in the financial marketplace, even if the principles that underpin his systems don’t change.

[Update] This post brings to mind a newsletter I received a number of months back from Mike at Breakout Futures. You can access the main article here. He provides simple code for TradeStation that will develop automated systems for the user, based upon the type of price pattern system the trader dictates.

While I haven’t used this type of system, I think it warrants further review with caution - it is likely similar in concept, although more rudimentary, to those systems developed at aiQUANT and Neural Market Trends.

Personally, I have used deductive reasoning to develop frameworks for money management methods, and then tested data in a similar, inductive method, to create the details.

Thomas Helstrom created a MATLAB program entitled Artificial Stock Trading Agent, or ASTA. Unfortunately, the code is no longer available as he is turning it into a commerical product. Still, it seems that what he had was a mechanism for both creating and testing automated strategies, encompassing one ability that many modern retail platforms don’t: testing a portfolio instead of a single issue.

The program, from what I’ve read, was a collection of about 300 .m files. The paper that served as the introduction was written by Helstrom and Kenneth Holmstrom, and titled Parameter Tuning in Trading Algorithms Using ASTA. While I don’t have a copy of it available, it is included in the 1999 publication Computational Finance.

Much of the content of that paper is also included in the ASTA User Guide. The paper, followed closely, shows the methodology for the creation of the ASTA system, and it is quite an interesting read.

While there are a lot of great views and insights in the paper, one of them was interesting from a NN/AI/data-mining algorithm development aspect:

The time series formulation based on the minimized RMSE measure is not always ideal for useful predictions of financial time series. Some reasons are:
1. The fixed prediction horizon h does not reflect the way in which financial predictions are being used. The ability of a model to predict should not be evaluated at one single fixed point in the future. A big increase in a stock value 14 days into the future is as good as the same increase 15 days into the future!
2. The equation treats all predictions, small and large, as equal. This is not always appropriate. Prediction points that would never be used for actual trading (i. e. price changes too small to be interesting) may cause higher residuals at the other points of more interest, to minimize the global RMSE.
3. A small predicted change in price, followed by a large real change in the same direction, is penalized by the RMSE measure. A trader is normally happy in this case, at least if, say, the small positive prediction was large enough to give a buy signal.
4. Several papers report a poor correlation between the RMSE measure and the profit made by applying a prediction algorithm, e. g. [Leitch and Tanner 1991] and [Bengio 1997]. A strategy that separates the modeling from the decision-taking rule, such as the one in 23.4, is less optimal than modeling the decision taking directly [Moody 1992]. Arguments 2 and 3 both give some explanations to these results.

It will be interesting to see if this comes out as a commercial product or not. According to his website, the site hasn’t been updated since 2006, so I don’t really know where it is. Any insight would be great - please comment if you know.