Login | Register

A Comparison Between a Long Short-Term Memory Network Hybrid Model and an ARIMA Hybrid Model for Stock Return Predictability

Title:

A Comparison Between a Long Short-Term Memory Network Hybrid Model and an ARIMA Hybrid Model for Stock Return Predictability

Wang, Xinxuan (2019) A Comparison Between a Long Short-Term Memory Network Hybrid Model and an ARIMA Hybrid Model for Stock Return Predictability. Masters thesis, Concordia University.

[thumbnail of Wang_MSc_F2019.pdf]
Preview
Text (application/pdf)
Wang_MSc_F2019.pdf - Accepted Version
1MB

Abstract

This thesis explores the applicability of neural networks in stock return forecasts by designing a hybrid LSTM (long short-term memory) network and compares its forecasting ability with both a static LSTM network and an ARIMA hybrid model. The S&P100 stock set is employed as the prediction sample. The hybrid models use the neural network approach and frequentist method respectively to estimate Fama-French risk factors, then predict stock returns based on factor estimations that benefit from the prediction ability and computational power of the LSTM network and the ARIMA model as well as the Fama-French model’s explanatory power of returns. Better factor predictions are made by the LSTM network with a 31% reduction of Mean Squared Error (MSE) and broader ranges of estimation than the ARIMA model. Hybrid models demonstrate a better fit, resulting in more accurate predictions compared to the static LSTM network by an average of 4.6% (LSTM-FF) and 3.1% (ARIMA-FF). However, I find that the slight outperformance of the LSTM-FF hybrid model over the ARIMA-FF hybrid model is not statistically significant.

Divisions:Concordia University > John Molson School of Business > Finance
Item Type:Thesis (Masters)
Authors:Wang, Xinxuan
Institution:Concordia University
Degree Name:M. Sc.
Program:Administration (Finance option)
Date:22 August 2019
Thesis Supervisor(s):Newton, David
ID Code:985741
Deposited By: Xinxuan Wang
Deposited On:19 Dec 2019 14:28
Last Modified:19 Dec 2019 14:28
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top