Financial Returns and Efficiency As Seen By An Artificial Technical Analyst

Abstract

We introduce trading rules which are selected by an artificially intelligent agent who learns from experience - an Artificial Technical Analyst. These rules restrict the data-mining concerns associated with the use of 'simple' technical trading rules as model evaluation devices and are good at recognising subtle regularities in return processes. The relationship between the efficiency of financial markets and the efficacy of technical analysis is investigated and it is shown that the Artificial Technical Analyst can be used to provide a quantitative measure of market efficiency. We estimate this measure on the DJIA daily index from 1962 to 1986 and draw implications for the optimal behaviour of certain classes of investors. It is also shown that the structure of technical trading rules commonly used is consistent with utility maximisation for risk neutral agents and in a myopic sense even for risk-averse agents.