Forecasting stock market return with nonlinearity: a genetic programming approach

The issue whether return in the stock market is predictable remains ambiguous. This paper attempts to establish new return forecasting models in order to contribute on addressing this issue. In contrast to existing literatures, we first reveal that the model forecasting accuracy can be improved thro...

Full description

Bibliographic Details
Main Authors: Ding, Shusheng, Cui, Tianxiang, Xiong, Xihan, Bai, Ruibin
Format: Article
Language:English
Published: Springer 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/60489/
_version_ 1848799769718161408
author Ding, Shusheng
Cui, Tianxiang
Xiong, Xihan
Bai, Ruibin
author_facet Ding, Shusheng
Cui, Tianxiang
Xiong, Xihan
Bai, Ruibin
author_sort Ding, Shusheng
building Nottingham Research Data Repository
collection Online Access
description The issue whether return in the stock market is predictable remains ambiguous. This paper attempts to establish new return forecasting models in order to contribute on addressing this issue. In contrast to existing literatures, we first reveal that the model forecasting accuracy can be improved through better model specification without adding any new variables. Instead of having a unified return forecasting model, we argue that stock markets in different countries shall have different forecasting models. Furthermore, we adopt an evolutionary procedure called Genetic programming (GP), to develop our new models with nonlinearity. Our newly-developed forecasting models are testified to be more accurate than traditional AR-family models. More importantly, the trading strategy we propose based on our forecasting models has been verified to be highly profitable in different types of stock markets in terms of stock index futures trading.
first_indexed 2025-11-14T20:40:56Z
format Article
id nottingham-60489
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:40:56Z
publishDate 2020
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling nottingham-604892020-04-28T02:09:35Z https://eprints.nottingham.ac.uk/60489/ Forecasting stock market return with nonlinearity: a genetic programming approach Ding, Shusheng Cui, Tianxiang Xiong, Xihan Bai, Ruibin The issue whether return in the stock market is predictable remains ambiguous. This paper attempts to establish new return forecasting models in order to contribute on addressing this issue. In contrast to existing literatures, we first reveal that the model forecasting accuracy can be improved through better model specification without adding any new variables. Instead of having a unified return forecasting model, we argue that stock markets in different countries shall have different forecasting models. Furthermore, we adopt an evolutionary procedure called Genetic programming (GP), to develop our new models with nonlinearity. Our newly-developed forecasting models are testified to be more accurate than traditional AR-family models. More importantly, the trading strategy we propose based on our forecasting models has been verified to be highly profitable in different types of stock markets in terms of stock index futures trading. Springer 2020-02-10 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/60489/1/Forecasting%20stock%20market%20return%20with%20nonlinearity%20a%20genetic%20programming%20approach.pdf Ding, Shusheng, Cui, Tianxiang, Xiong, Xihan and Bai, Ruibin (2020) Forecasting stock market return with nonlinearity: a genetic programming approach. Journal of Ambient Intelligence and Humanized Computing . ISSN 1868-5137 Return forecasting; Nonlinear models; Genetic programming http://dx.doi.org/10.1007/s12652-020-01762-0 doi:10.1007/s12652-020-01762-0 doi:10.1007/s12652-020-01762-0
spellingShingle Return forecasting; Nonlinear models; Genetic programming
Ding, Shusheng
Cui, Tianxiang
Xiong, Xihan
Bai, Ruibin
Forecasting stock market return with nonlinearity: a genetic programming approach
title Forecasting stock market return with nonlinearity: a genetic programming approach
title_full Forecasting stock market return with nonlinearity: a genetic programming approach
title_fullStr Forecasting stock market return with nonlinearity: a genetic programming approach
title_full_unstemmed Forecasting stock market return with nonlinearity: a genetic programming approach
title_short Forecasting stock market return with nonlinearity: a genetic programming approach
title_sort forecasting stock market return with nonlinearity: a genetic programming approach
topic Return forecasting; Nonlinear models; Genetic programming
url https://eprints.nottingham.ac.uk/60489/
https://eprints.nottingham.ac.uk/60489/
https://eprints.nottingham.ac.uk/60489/