Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures

With the advancement of deep learning, its application in financial market forecasting has become a research hotspot. This paper proposes an innovative Multi-Scale TsMixer model for predicting stock index futures in the A-share market, covering SSE50, CSI300, and CSI500. By integrating Multi-Scale t...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyuan Pei, Jianqi Yan, Jin Yan, Bailing Yang, Xin Liu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1415
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030534158188544
author Zhiyuan Pei
Jianqi Yan
Jin Yan
Bailing Yang
Xin Liu
author_facet Zhiyuan Pei
Jianqi Yan
Jin Yan
Bailing Yang
Xin Liu
author_sort Zhiyuan Pei
collection DOAJ
description With the advancement of deep learning, its application in financial market forecasting has become a research hotspot. This paper proposes an innovative Multi-Scale TsMixer model for predicting stock index futures in the A-share market, covering SSE50, CSI300, and CSI500. By integrating Multi-Scale time-series features across the short, medium, and long term, the model effectively captures market fluctuations and trends. Moreover, since stock index futures reflect the collective movement of their constituent stocks, we introduce a novel approach: predicting individual constituent stocks and merging their forecasts using three fusion strategies (average fusion, weighted fusion, and weighted decay fusion). Experimental results demonstrate that the weighted decay fusion method significantly improves the prediction accuracy and stability, validating the effectiveness of Multi-Scale TsMixer.
format Article
id doaj-art-c8b378eed71f4e86b1fd9db8399c2c49
institution DOAJ
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-c8b378eed71f4e86b1fd9db8399c2c492025-08-20T02:59:11ZengMDPI AGMathematics2227-73902025-04-01139141510.3390/math13091415Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index FuturesZhiyuan Pei0Jianqi Yan1Jin Yan2Bailing Yang3Xin Liu4School of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaSchool of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaSchool of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaSchool of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaMacau Institute of Systems Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, ChinaWith the advancement of deep learning, its application in financial market forecasting has become a research hotspot. This paper proposes an innovative Multi-Scale TsMixer model for predicting stock index futures in the A-share market, covering SSE50, CSI300, and CSI500. By integrating Multi-Scale time-series features across the short, medium, and long term, the model effectively captures market fluctuations and trends. Moreover, since stock index futures reflect the collective movement of their constituent stocks, we introduce a novel approach: predicting individual constituent stocks and merging their forecasts using three fusion strategies (average fusion, weighted fusion, and weighted decay fusion). Experimental results demonstrate that the weighted decay fusion method significantly improves the prediction accuracy and stability, validating the effectiveness of Multi-Scale TsMixer.https://www.mdpi.com/2227-7390/13/9/1415deep learningA-shares marketstock index futuresMulti-Scale TsMixercomponent stock weightingtime-series prediction
spellingShingle Zhiyuan Pei
Jianqi Yan
Jin Yan
Bailing Yang
Xin Liu
Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
Mathematics
deep learning
A-shares market
stock index futures
Multi-Scale TsMixer
component stock weighting
time-series prediction
title Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
title_full Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
title_fullStr Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
title_full_unstemmed Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
title_short Multi-Scale TsMixer: A Novel Time-Series Architecture for Predicting A-Share Stock Index Futures
title_sort multi scale tsmixer a novel time series architecture for predicting a share stock index futures
topic deep learning
A-shares market
stock index futures
Multi-Scale TsMixer
component stock weighting
time-series prediction
url https://www.mdpi.com/2227-7390/13/9/1415
work_keys_str_mv AT zhiyuanpei multiscaletsmixeranoveltimeseriesarchitectureforpredictingasharestockindexfutures
AT jianqiyan multiscaletsmixeranoveltimeseriesarchitectureforpredictingasharestockindexfutures
AT jinyan multiscaletsmixeranoveltimeseriesarchitectureforpredictingasharestockindexfutures
AT bailingyang multiscaletsmixeranoveltimeseriesarchitectureforpredictingasharestockindexfutures
AT xinliu multiscaletsmixeranoveltimeseriesarchitectureforpredictingasharestockindexfutures