Forex Automaton

Our primary goal is to create a public information service providing financial markets forecasts, based on our proprietary forecasting tools: an automated trading system -- a Forex Automaton™. Our secondary goal is to quantify and monitor the very existence of sustainable opportunities for arbitrage profit-making. Or simply put, to monitor the degree to which these markets are more predictable than a "fair game" -- to a trader without access to insider information.

Forex Automaton was launched in April 2008 with the ambitious mission of leveraging the specific algorithmic know-how to create a trading signal service geared toward retail forex traders. From the very beginning a two-prong strategy was adopted: first, development of the trading system product whose usefulness relies on secrecy of the relevant know-how. Second, white-paper research focusing on statistical properties of the market time series, especially those aspects which are potentially interesting from the point of view of algorithmic trading, however counter-intuitive, technical and remote from the mainstream picture of forex trading they may be. As of now, it is mostly the second prong that's visible to the website visitor. This document summarizes the main findings to emerge so far from a year of studies, including some glimpses into the progress made on the black-box algorithmic trading system front.

While it is true that past performance does not indicate the future, the only reliable information we have is about the past. A few important things make a difference between unbiased trading-system testing and self-delusion. Here I summarize my current understanding.

As any computer program, a forex trading system has input and output. This post is about the output -- what should be in it? What are the guiding principles of this communication? Here are the basic principles as we see them now:

• Regularity.
• Communicate actions, not prophecies.
• Communicate actions as they happen.
• Program the computer, not the user.
• Be accountable for the past performance.
• No misrepresentation.
• Access control.

This article begins a series of analysis reports investigating a degree of predictability in the LIBOR rates, a popular capital cost indicator. The analysis is based on historical LIBOR interest rate data released by the British Bankers Association. I continue with the same technique proved useful in the predictability analysis of forex exchange rates, as our interest in the interest rates in general is in part provoked by the results of the latter analysis, namely:

• sometimes, one forex exchage rate can "show the way" to a number of others, or in other words, foretell (in a probabilistic or statistical sense) their movement.
• when that happens, it is usually the exchange rate with a large interest rate differential showing the way to the ones with lower interest rate differentials.

Obviously, when exploring these "loopholes" or market inefficiencies for wealth generation, an algorithmic trader or a forex trading system (an automated decision making algorithm such as the one being built here on Forex Automaton™ site) must be mindful of the picture of LIBOR rates and its evolution, albeit in a somewhat different context than a long-term money manager. Being able to predict events, even in a weak statistical sense, is even better than merely following. Besides being useful via their implications for forex forecasting, LIBORs form an underlying indicator for derivatives of their own. LIBOR futures contracts and options on such contracts are traded on the CME. How does the predictability of LIBORs compare with that of currencies? Which one, LIBOR or forex, is more attractive to trade? Answering these questions, or providing a technical analysis framework to approach the answers, while leaving the fundamentals and event-driven trends aside, this series of articles about correlation features in LIBORs will serve as a useful compliment to our set of forex correlation analysis notes. I start this new series of articles with the all-important US Dollar LIBOR.

I am continuing another round of optimizations, revisiting the six popular currency pairs one after the other, extending the range of the trade-entry parameter further into the "conservative" area. In the case of USD/JPY however, the "old" optimum seems good enough so that no improvement is brought about: even though the "new" returns are higher, I am not convinced that the "new" risks are justified. The "landscape" of the optimization problem here looks very clean and understandable.

With the trade-entry parameter range extended into the more conservative area, the GBP/USD optimization results begin to look more like those of other currency pairs, with arguably a better optimum.

This study covers an extended range of the trade-entry threshold parameter, the one that controls the "patience" of a trading system or the amount of "excitement" about a trade idea needed to enter the trade. With the trade-entry parameter extended into the more conservative area, the USD/CHF optimization results begin to look more like those of other currency pairs.

The recent changes to the trading system optimization technique do show an effect on the AUD/USD optimization, shifting the preferred value of the forecasting quality parameter. This study covers an extended range of the trade-entry threshold parameter, the one that controls the "patience" of a trading system or the amount of "excitement" about a trade idea needed to enter the trade. The new optimum takes advantage of that as well.

I am revisiting the case of USD/CAD on the day scale after a few important changes to the trading system optimization technique have been introduced. The entry threshold parameter, the one that controls the "patience" of a trading system or the amount of "excitement" about a trade idea needed to enter the trade, takes much higher values in this study, and the optimal "patience" is being seen.

After important changes to the trading system optimization methodology, I am revisiting the case of GBP/USD on the day scale. In this study, the extended range of the entry threshold parameter, same as in the previous EUR/USD and USD/JPY studies, is used. The extended, more conservative threshold values are seen to increase the returns while reducing the risk. Unlike other cases, not one but two attractive ranges of the forecasting control parameter are seen.

The USD/CHF optimization note originally posted on May 29 has been updated to correct for a mistake in the data selection. Originally, 1 out of 6 runs used for the analysis (17% of the traders considered) contained USD/CAD while others contained USD/CHF data. As a result, some of the optimization results are different.

After important changes to the trading system optimization technique, I am revisiting the case of USD/JPY on the day scale. In this study, the extended range of the entry threshold parameter, same as in the previous EUR/USD study, is used. The extended, more conservative threshold values are seen to increase the returns while reducing the risk.

After important changes to the trading system optimization methodology, I am revisiting EUR/USD on the day scale. The USD/CAD and USD/CHF reports indicated that our range of trade entry parameter might not include the optimum, consequently the range is extended. As a result, much better performance figures are seen. But caution is needed when comparing even the "minimum-bias" results with those of earlier reports, since the parameter ranges are now different.

After some important changes to the trading system optimization methodology, I continue with USD/CHF on the day scale -- this currency pair has not been analyzed in this context before.

After some important changes to the trading system optimization methodology, I continue with USD/CAD on the day scale -- this currency pair has not been analyzed in this context before.

Our forex trading system optimization procedure is currently undergoing a change. This change is brought about by the recognition of the fact that a simple arithmetic average of monthly returns, a statistic used so far, is biased upwards and thus provides a falsely optimistic estimator of return. The popular Sharpe ratio statistic, if it incorporates such an estimator, is to be avoided or redefined. Here are some outlines of the upgraded approach.

When evaluating the performance of a trading system, I calculate the first moment (an arithmetic mean of the series of returns) as well as the second one (a variance of the series). Originally my "Sharpe-like" ratio, used to adjust the return for the risk, was a ratio of the first moment to the square root of the second. The series of returns would be composed of annualized returns calculated every month.

This is the fifth report in the series of the buy-side forex trading system optimization reports for the individual currency pairs, traded on the day scale, which began with AUD/JPY. In the algorithm, the forecast signal whose nature will not be disclosed is fed into the money management framework driven by three adjustable parameters. The set of 13398 parameter combinations represents the totality of possible trading styles under study. The goal is to optimize the trading style by finding, on the basis of the simulated trading performance, such values of parameters as to maximize the return while minimizing risk. The insights obtained in the process may be of general interest, since the problem is common to all traders, robots and humans alike.

This is the fourth report in the series of forex trading system optimization reports for the individual currency pairs, traded on the day scale, which began with AUD/JPY. In the algorithm, the forecast signal whose nature will not be disclosed is fed into the money management framework driven by three adjustable parameters. The parameters form a multi-dimensional space populated by figures of merit, as obtained by Monte Carlo simulation of independent trading histories. The set of 13398 parameter combinations represents the totality of possible trading styles under study. The goal is to optimize the trading style by finding the best values of parameters on the basis of the simulated trading performance. The insights obtained in the process may be of general interest, since the problem of money management is common to all traders, robots and humans alike.