Predicting the stock price based on BP neural network and big transaction

摘要

This paper uses the BP neural network and the intraday big transaction data from January 4, 2005 to June 30, 2008 of China Unicom(600050) to predict its daily stock price of the next 5 days. Our model contains 12 statistical variables describing the intraday big transaction features and the result of curve fittings are notable in statistics.