Sports match prediction model for training and exercise using attention-based LSTM network

Qiyun Zhang; Xuyun Zhang; Hongsheng Hu; Caizhong Li; Yinping Lin; Rui Ma

doi:10.1016/j.dcan.2021.08.008

Sports match prediction model for training and exercise using attention-based LSTM network

Qiyun Zhang, Xuyun Zhang, Hongsheng Hu, Caizhong Li, Yinping Lin, Rui Ma^*

^*Corresponding author for this work

School of Computing

Research output: Contribution to journal › Article › peer-review

39 Citations (Scopus)

565 Downloads (Pure)

Abstract

Sports matches are very popular all over the world. The prediction of a sports match is helpful to grasp the team's state in time and adjust the strategy in the process of the match. It's a challenging effort to predict a sports match. Therefore, a method is proposed to predict the result of the next match by using teams' historical match data. We combined the Long Short-Term Memory (LSTM) model with the attention mechanism and put forward an AS-LSTM model for predicting match results. Furthermore, to ensure the timeliness of the prediction, we add the time sliding window to make the prediction have better timeliness. Taking the football match as an example, we carried out a case study and proposed the feasibility of this method.

Original language	English
Pages (from-to)	508-515
Number of pages	8
Journal	Digital Communications and Networks
Volume	8
Issue number	4
Early online date	30 Aug 2021
DOIs	https://doi.org/10.1016/j.dcan.2021.08.008
Publication status	Published - Aug 2022

Bibliographical note

Copyright the Publisher 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Sports
Prediction
Long short-term memory
Attention
Sliding window

Access to Document

10.1016/j.dcan.2021.08.008Licence: CC BY-NC-ND

Publisher version (open access)Final published version, 1.14 MBLicence: CC BY-NC-ND

Cite this

@article{26b3b60f57dc4124b333e8045496cdfe,

title = "Sports match prediction model for training and exercise using attention-based LSTM network",

abstract = "Sports matches are very popular all over the world. The prediction of a sports match is helpful to grasp the team's state in time and adjust the strategy in the process of the match. It's a challenging effort to predict a sports match. Therefore, a method is proposed to predict the result of the next match by using teams' historical match data. We combined the Long Short-Term Memory (LSTM) model with the attention mechanism and put forward an AS-LSTM model for predicting match results. Furthermore, to ensure the timeliness of the prediction, we add the time sliding window to make the prediction have better timeliness. Taking the football match as an example, we carried out a case study and proposed the feasibility of this method.",

keywords = "Sports, Prediction, Long short-term memory, Attention, Sliding window",

author = "Qiyun Zhang and Xuyun Zhang and Hongsheng Hu and Caizhong Li and Yinping Lin and Rui Ma",

note = "Copyright the Publisher 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2022",

month = aug,

doi = "10.1016/j.dcan.2021.08.008",

language = "English",

volume = "8",

pages = "508--515",

journal = "Digital Communications and Networks",

issn = "2352-8648",

publisher = "Chongqing University of Posts and Telecommunications",

number = "4",

}

TY - JOUR

T1 - Sports match prediction model for training and exercise using attention-based LSTM network

AU - Zhang, Qiyun

AU - Zhang, Xuyun

AU - Hu, Hongsheng

AU - Li, Caizhong

AU - Lin, Yinping

AU - Ma, Rui

N1 - Copyright the Publisher 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2022/8

Y1 - 2022/8

N2 - Sports matches are very popular all over the world. The prediction of a sports match is helpful to grasp the team's state in time and adjust the strategy in the process of the match. It's a challenging effort to predict a sports match. Therefore, a method is proposed to predict the result of the next match by using teams' historical match data. We combined the Long Short-Term Memory (LSTM) model with the attention mechanism and put forward an AS-LSTM model for predicting match results. Furthermore, to ensure the timeliness of the prediction, we add the time sliding window to make the prediction have better timeliness. Taking the football match as an example, we carried out a case study and proposed the feasibility of this method.

AB - Sports matches are very popular all over the world. The prediction of a sports match is helpful to grasp the team's state in time and adjust the strategy in the process of the match. It's a challenging effort to predict a sports match. Therefore, a method is proposed to predict the result of the next match by using teams' historical match data. We combined the Long Short-Term Memory (LSTM) model with the attention mechanism and put forward an AS-LSTM model for predicting match results. Furthermore, to ensure the timeliness of the prediction, we add the time sliding window to make the prediction have better timeliness. Taking the football match as an example, we carried out a case study and proposed the feasibility of this method.

KW - Sports

KW - Prediction

KW - Long short-term memory

KW - Attention

KW - Sliding window

UR - http://www.scopus.com/inward/record.url?scp=85118178064&partnerID=8YFLogxK

U2 - 10.1016/j.dcan.2021.08.008

DO - 10.1016/j.dcan.2021.08.008

M3 - Article

AN - SCOPUS:85118178064

SN - 2352-8648

VL - 8

SP - 508

EP - 515

JO - Digital Communications and Networks

JF - Digital Communications and Networks

IS - 4

ER -

Sports match prediction model for training and exercise using attention-based LSTM network

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this