An error correction neural network for stock market prediction

Date
2019-04
Journal Title
Journal ISSN
Volume Title
Publisher
Stellenbosch : Stellenbosch University
Abstract
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 study begins with a review of the theoretical background of neural networks. Subsequently an Error Correction Neural Network (ECNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) are defined and implemented for an empirical study. This research offers evidence on the predictive accuracy and profitability performance of returns of the proposed forecasting models on futures contracts of Hong Kong’s Hang Seng futures, Japan’s NIKKEI 225 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 the ECNN model outperforms other proposed models in both predictive accuracy and profitability performance. These results indicate that ECNN shows promise as a reliable deep learning method to predict stock price.
AFRIKAANSE OPSOMMING : Die voorspelling van die aandele mark was al lank ´n interge onderwerp in verskillende navorsingsvelde. Verskeie tegnieke was al so ver toegepas om aandelemark beweging te voorspel. Hierdie studie begin met ´n oorsig van die teoretiese agtergrond van neutrale netwerke. Daarna is ´n Fout Neurale Netwerk (FNN), Herhalende Neurale Netwerk (HNN); en Lank- en - Kort Termyn Gehee (LKTG) word gedefinieer en geïmplenteer vir ´n empiriese studie. Hierdie navorsing bied bewyse oor die voorspellende akkuraatheid en winsgewendheid van die opbrengste van die voorgestelde vooruitskatting modelle op termynkontrakte van; Hongkong se Hang Seng-toekoms, Japan se NIKKEI 225 termyne, en die Verenigde State van Amerika S&P 500 en DJIA termynkontrakte vanaf 2010 tot en met 2016. Resultate toon dat die FNNmodel beter presteer as ander voorgestelde modelle in beide voorspellings akkuraatheid en winsgewendheid prestasie. Hierdie resultate dui daarop dat FNN belofte toon as ´n betroubaar masjienleermetode om die aandeelprys te voorspel.
Description
Thesis (MSc)--Stellenbosch University, 2019.
Keywords
UCTD, Stock price forecasting -- Mathematical models, Stock exchanges -- Computer networks, Neural network, Economic forecasting -- Mathematical models
Citation