Two Stock-Trading Agents: Market Making and Technical Analysis
暂无分享,去创建一个
Evolving information technologies have brought computational power and real-time facilities into the stock market. Automated stock trading draws much interest from both the fields of computer science and of business, since it promises to provide superior ability in a trading market to any individual trader. Trading strategies have been proposed and practiced from the perspectives of Artificial Intelligence, market making, external information feedback, and technical analysis among others. This paper examines two automated stock-trading agents in the context of the Penn-Lehman Automated Trading (PLAT) simulator [1], which is a real-time, real-data market simulator. The first agent devises a market-making strategy exploiting market volatility without predicting the exact direction of the stock price movement. The second agent uses technical analysis. It might seem natural to buy when the market is on the rise and sell when it’s on the decline, but the second agent does exactly the opposite. As a result, we call it the reverse strategy. The strategies used by both agents are adapted for automated trading. Both agents performed well in a PLAT live competition. In this paper, we analyze the performance of these two automated trading strategies. Comparisons between them are also provided.
[1] Luis E. Ortiz,et al. The Penn-Lehman Automated Trading Project , 2003, IEEE Intell. Syst..
[2] Jason Kingdon. Intelligent systems and financial forecasting , 1997, Perspectives in neural computing.
[3] Mark J. Kamstra,et al. Forecast combining with neural networks , 1996 .
[4] Michael D. Sheimo. Stock market rules : the facts and the fiction : 50 of the most widely held investment axioms explained, examined and exposed , 1994 .