Using Machine-Learning Algorithms to Predict Self-Reported Problem Gambling Among a Sample of Online Gamblers
Bibliographic Data
| ID | 15441981 |
|---|---|
| Authors | Michael Auer (0000-0002-6303-596X, corresponding author), Mark D Griffiths (0000-0001-8880-6524, Nottingham Trent University) |
| Year | 2026 |
| Publication date | 2026-01-16 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | International Journal of Mental Health and Addiction (JOURNAL) |
| Journal identifiers | ISSN: 1557-1874 • E-ISSN: 1557-1882 |
| Publisher | Springer Science+Business Media (PUBLISHER • DE) |
| DOI | 10.1007/s11469-025-01602-2 |
| OpenAlex | W7124425380 |
| Language | EN |
| References cited | 52 |
Studies suggest that algorithms can effectively be used to predict self-reported problem gambling using player tracking data. The present study analyzed a sample of real-world online gamblers ( N = 1,611) who engaged in lottery playing, casino gambling, bingo playing, and sports betting. The data also comprised each player’s actual gambling activity, as well as age and gender, in the 30 days prior to answering the Problem Gambling Severity Index (PGSI). Players who engaged in at least one lottery game 30 days prior to answering the PGSI were less likely to be problem gamblers compared to players who did not play lottery games. For all other game-categories the relationship was reversed. The results also indicated that specific behavioral tracking features—such as the average number of monetary deposits per session, total amount of money bet per day, session length, and casino gambling involvement—were among the most significant predictors of self-reported problem gambling. When evaluating different machine algorithms, logistic regression and random forest emerged as the most effective in predicting self-reported problem gambling. The present study is among the few which predicts self-reported problem gambling using a sample of online lottery players, casino gamblers, bingo players and sports bettors, and provides further empirical evidence supporting the use of machine learning models to identify self-reported problem gamblers based on player tracking data. These findings can inform responsible gambling strategies by enabling operators to identify and intervene before gambling-related problems escalate
Health psychology · Logistic regression · Lottery · Sample (material · Session (web analytics · Tracking (education · Artificial Intelligence in Games · Gambling Behavior and Treatments · Sports Analytics and Performance
Diagnostic and Statistical Manual of Mental Disorders
An Introduction to Logistic Regression Analysis and Reporting
Support-Vector Networks
Statistics Notes
The use of the area under the ROC curve in the evaluation of machine learning algorithms
A meta‐analysis of problem gambling risk factors in the general adult population
Understanding gambling related harm
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Greedy function approximation
Random Forests
The Effects of Voluntary Deposit Limit-Setting on Long-Term Online Gambling Expenditure
Development and validation of a prediction model for online gambling problems based on players' account data
The use of personalized messages on wagering behavior of Swedish online gamblers
Gambling prevalence and gambling problems amongst land-based-only, online-only and mixed-mode gamblers in Australia
Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models
Changes in Gambling Behavior during the Covid-19 Pandemic—A Web Survey Study in Sweden
Understanding Online Voluntary Self-Exclusion in Gambling
Cognitive Dissonance, Personalized Feedback, and Online Gambling Behavior
Global Limit Setting as a Responsible Gambling Tool
An Empirical Study of the Effect of Voluntary Limit-Setting on Gamblers’ Loyalty Using Behavioural Tracking Data
Internet Self-Exclusion
An examination of internet and land-based gambling among adolescents in three Canadian provinces
Gambling formats, involvement, and problem gambling
The cards they're dealt
| Highly cited | No |
|---|