Short term intraday trading of futures market analysis

Abstract

This study proposes a neural network model utilizing technical analysis indicators, try to find the knowledge rules from futures' intraday trading data and construct a futures' short-term time interval predicting model. In the short-term time interval, the transaction data often changes in a small range; also, this study propose two data pre-processing techniques to overcome this problem and improve neural network's learning ability. The results of experiments indicate that although the transaction data contains insufficient information and knowledge in a short-term time interval, it is possible to achieve better accuracy and profitability through data smoothing and data filtering.