INGARCH-based fuzzy clustering of count time series with a football application

被引：9

作者：

Cerqueti, Roy ^{[1
,2
,3
]}

D'Urso, Pierpaolo ^{[1
]}

De Giovanni, Livia ^{[4
]}

Mattera, Raffaele ^{[1
]}

Vitale, Vincenzina ^{[1
]}

机构：

[1] Sapienza Univ Rome, Dept Social & Econ Sci, Rome, Italy

[2] London South Bank Univ, Sch Business, London, England

[3] Univ Angers, GRANEM, Angers, France

[4] LUISS Guido Carli, Dept Polit Sci, Rome, Italy

来源：

MACHINE LEARNING WITH APPLICATIONS | 2022年 / 10卷

关键词：

Fuzzy C-medoids; INGARCH; Poisson distribution; Sport analytics; BIVARIATE POISSON MODEL;

D O I：

10.1016/j.mlwa.2022.100417

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Although there are many contributions in the time series clustering literature, few studies still deal with count time series data. This paper aims to develop a fuzzy clustering procedure for count time series data. We propose an Integer GARCH-based Fuzzy C -medoids (INGARCH-FCMd) method for clustering count time series based on a Mahalanobis distance between the parameters estimated by an INGARCH model. We show how the proposed clustering method works by clustering football teams according to the number of scored goals.

引用

页数：11

共 55 条

[1] A Poisson Autoregressive Model to Understand COVID-19 Contagion Dynamics [J].