An error correction neural network for stock marketprediction

[摘要] ENGLISH ABSTRACT : Predicting stock market has long been an intriguing topic for research in different fields.Numerous techniques have been conducted to forecast stock market movement. This studybegins with a review of the theoretical background of neural networks. Subsequently an ErrorCorrection Neural Network (ECNN), Recurrent Neural Network (RNN) and Long Short-TermMemory (LSTM) are defined and implemented for an empirical study. This research offersevidence on the predictive accuracy and profitability performance of returns of the proposedforecasting models on futures contracts of Hong Kong's Hang Seng futures, Japan's NIKKEI225 futures, and the United State of America S&P 500 and DJIA futures from 2010 to 2016.Technical as well as fundamental data are used as input to the network. Results show that theECNN model outperforms other proposed models in both predictive accuracy and profitability performance. These results indicate that ECNN shows promise as a reliable deep learningmethod to predict stock price.

[发布机构] Stellenbosch University