Predicting self-exclusion status in online gambling data via machine learning algorithms
Session Title
Session 3-4-A: Problem Gambling Behaviors and Prevention
Presentation Type
Event
Location
Caesars Palace, Las Vegas, Nevada
Start Date
30-5-2019 3:30 PM
End Date
30-5-2019 4:55 PM
Disciplines
Applied Behavior Analysis
Abstract
Abstract: The identification of problematic gambling in online gamblers from behavioural data (‘player tracking’) may enable interventions to be targeted to those users experiencing harms. This study tested the predictive performance of machine learning models in classifying online gamblers based on voluntary self-exclusion (VSE) status as a binary indicator of problem gambling. We used 1 year of de-identified data from the eCasino section of the PlayNow.com platform in British Columbia, Canada, comprising 31,115 users placing over half a billion individual bets. Input variables were based on daily-aggregate and session-aggregate measures capturing gambling frequency, intensity, and variability. To mitigate concerns about the ‘black box’ nature of machine learning, we report ‘feature importance’ values to show the variables that are most predictive.
The primary model compared 1323 self-excluders against an under-sampled (n = 3000) control group. Across 6 variants of our machine learning model, we obtained classification performance (AUROC) from 75 to 79%. Variability in a monetary measure of gambling intensity (Variance in Money Bet per Session) showed the highest feature importance value. Model predictions were used to classify control participants in three risk levels based on resemblance to self-excluders; these risk subgroups differed significantly on each of the 9 input variables.
Implications: Machine learning can classify online gamblers based on self-exclusion status with 75-79% performance, using relatively coarse input variables that do not require baseline data or analysis of trajectories. Next steps are to establish convergence across different gambling forms, and using alternative markers of problem gambling.
Keywords
Data Science, Self-Exclusion, Problem Gambling, Machine Learning, Player Tracking
Funding Sources
LC is the Director of the Centre for Gambling Research at UBC, which is supported by funding from the British Columbia Lottery Corporation and the Province of BC government. This project was funded by a Research Grant from the BC Ministry of Finance (Gaming Policy & Enforcement Branch) awarded to Luke Clark and Tilman Lesch. The dataset was provided to the researchers by the British Columbia Lottery Corporation. These entities had no further involvement in the research design, methodology, conduct, analysis or write-up of the study, and impose no constraints on publishing.
Competing Interests
LC is the Director of the Centre for Gambling Research at UBC, which is supported by the Province of British Columbia government and the British Columbia Lottery Corporation (BCLC). The BCLC is a Canadian Crown Corporation. LC has received a speaker honorarium from Svenska Spel (Sweden) and accepted travel/accommodation for speaking engagements from the National Center for Responsible Gaming (US) and National Association of Gambling Studies (Australia). He has not received any further direct or indirect payments from the gambling industry or groups substantially funded by gambling. He has received royalties from Cambridge Cognition Ltd. relating to the licensing of a neurocognitive test. KM and TL disclose no competing interests.
Predicting self-exclusion status in online gambling data via machine learning algorithms
Caesars Palace, Las Vegas, Nevada
Abstract: The identification of problematic gambling in online gamblers from behavioural data (‘player tracking’) may enable interventions to be targeted to those users experiencing harms. This study tested the predictive performance of machine learning models in classifying online gamblers based on voluntary self-exclusion (VSE) status as a binary indicator of problem gambling. We used 1 year of de-identified data from the eCasino section of the PlayNow.com platform in British Columbia, Canada, comprising 31,115 users placing over half a billion individual bets. Input variables were based on daily-aggregate and session-aggregate measures capturing gambling frequency, intensity, and variability. To mitigate concerns about the ‘black box’ nature of machine learning, we report ‘feature importance’ values to show the variables that are most predictive.
The primary model compared 1323 self-excluders against an under-sampled (n = 3000) control group. Across 6 variants of our machine learning model, we obtained classification performance (AUROC) from 75 to 79%. Variability in a monetary measure of gambling intensity (Variance in Money Bet per Session) showed the highest feature importance value. Model predictions were used to classify control participants in three risk levels based on resemblance to self-excluders; these risk subgroups differed significantly on each of the 9 input variables.
Implications: Machine learning can classify online gamblers based on self-exclusion status with 75-79% performance, using relatively coarse input variables that do not require baseline data or analysis of trajectories. Next steps are to establish convergence across different gambling forms, and using alternative markers of problem gambling.