A profitable trading and risk management strategy despite transaction costs

Abstract

We present a new profitable trading and risk management strategy with transaction cost for an adaptive equally weighted portfolio. Moreover, we implement a rule-based expert system for the daily financial decision-making process using the power of spectral analysis. We use several key components such as principal component analysis, partitioning, memory in stock markets, percentile for relative standing, the first four normalized central moments, learning algorithm, and switching among several investment positions consisting of short stock market, long stock market and money market with real risk-free rates. We find that it is possible to beat the proxy for the equity market without short selling for 168 S&P 500-listed stocks during the 1998–2008 period and 213 Russell 2000-listed stocks during the 1995–2007 period. Our Monte Carlo simulation for both the various set of stocks and the interval of time confirms our findings.

Keywords:

• Behavioral finance
• Anomalies in prices
• Market efficiency
• Market prediction
• Overreaction
• Computational finance
• Financial markets
• Financial modelling

Acknowledgements

The authors are grateful for the helpful comments and suggestions of the Editors of the journal and three anonymous referees. The authors thank Mattias Jonsson, Joseph Conlon, Curtis Huntington, Kristen Moore, Virginia Young, Erhan Bayraktar, Michael Ludkovski, the other participants of the Winter 2008 Financial/Actuarial Mathematics Seminar at the University of Michigan, Ann Arbor, and the participants of the 2008 SIAM Conference on Financial Mathematics and Engineering for their feedback. The authors may have long or short positions in mutual funds that hold securities discussed in the paper.

Notes

†The list of stocks will be provided upon request. For the S&P 500, we focused on 168 stocks because they are traded over the same dates and time range between April 29, 1998 and April 4, 2008 without being delisted/removed and became accessible via finance.yahoo.com. In order to test the performance of the algorithm on smaller capitalization stocks, we use the Russell 2000 index as a guide. Among the stocks that comprised the index in July 2009, we consider those stocks that were publicly traded between 1995 and 2007. This choice results in a data set of 213 small-cap stocks from 1995 to 2007. These are the only selection criteria.