Adaptive generalized logistic lasso (AGLL)

Flexible, robust and fast algorithm for the AGLL with applications to ratings in sports.

Authors

Robert Bajons

Joint work with Kurt Hornik

Published

June 1, 2024

Hit Counter by Digits

Resources on the Project
Resource Date Link
Presentation given at the International Workshop on Statistical Modelling 2024 2024-07-16 Presentation (IWSM 24)
Contribution to proceedings of the International Workshop on Statistical Modelling 2024 2024-07-15 Short Paper (IWSM 24)

Overview

The generalized lasso is a popular model for ranking competitors, as it allows for implicit grouping of estimated abilities. In this work, we present an implementation of an adaptive variant of the generalized lasso penalty for logistic regression using conic programming principles. This approach is flexible, robust, and fast, especially in a high-dimensional setting. The methodology is applied to sports data, with the aim of ranking players in soccer and ice hockey.