Adaptive Use of Technical Indicators for Predicting the Intra-Day Price Movements

  • Authors:

  • Mieko Tanaka-Yamawaki;Seiji Tokuoka

  • Affiliations:

  • Department of Information and Knowledge Engineering, Tottori University, 4-101 Koyamacho-Minami, Tottori, 680-8550, Japan;RICOH Software, Inc., I-Forefront Tower, 1-12-3 Kachidoki, Chuo-ku, Tokyo, 104-0054, Japan

  • Venue:
  • KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a system to select the best combination of technical indicators and their parameter values adaptively by learning the patterns from the tick-wise financial data. In this paper, we show that this system gives good predictions on the directions of motion with the hitting rate at 10 ticks ahead of the decision point as high as 70% for foreign exchange rates (FX) in five years from 1996 to 2000 and 8 different stock prices in NYSE market in 1993. Based on this fact, we conclude that the tick-wise price time series carry a long memory of the order of at least a few minutes, which is equivalent to 10 ticks.