抄録
Recently, the number of trader by internet securities companies has increased rapidly. There have been reported lots of studies on forecast of stock prices based on the closing price. However, there are few researches which utilize real time information such as bid and ask price. In this paper, the authors proposed a novel method of evolving day-trade strategies by means of the genetic programming which utilized only order book information. The performance of the proposed method is shown by means of Day Trade Agent Framework (DTAF).
