ABSTRACT
The identification of disordered gambling in the online environment may enable interventions to be targeted to those users experiencing harms. We tested the performance of machine learning in classifying online gamblers with and without a record of voluntary self-exclusion (VSE). We analyzed a one year dataset from PlayNow.com, the provincially owned online gambling platform in British Columbia, Canada. The primary model compared 2,157 gamblers with a record of VSE enrollment (6 months to 3 years) against 17,526 non-VSE controls, using 20 input variables of gambling behavior. Machine learning (random forest classifier) achieved an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.75 (SD = 0.01). The input variable with the greatest predictive signal (based on feature importance values) was Variance in Money Bet per Session. Further analyses tested a logistic regression model as a benchmark, and tested the impact of key modeling decisions (including use of a balanced dataset, and data inclusion threshold). Across all models, machine learning algorithms were able to predict VSE status with performance between 0.65 and 0.76, using our behavioral inputs. These results provide proof-of-principle data for the applied use of behavioral tracking to identify disordered gambling, and highlight the importance of behavioral inputs reflecting betting variability.
Disclosure statement
Funding sources
This project was funded by a Research Grant from the Province of BC Ministry of Finance (Gaming Policy & Enforcement Branch) awarded to Luke Clark and Tilman Lesch, and by the core funding of the Centre for Gambling Research at UBC. The dataset for this study was provided to the research team by the British Columbia Lottery Corporation.
Constraints on publishing
The Centre for Gambling Research at UBC is supported by funding from the Province of British Columbia and the British Columbia Lottery Corporation (BCLC). The dataset for this study was provided to the research team by the British Columbia Lottery Corporation. The Province of BC government and the BCLC had no further role in the design, analysis, or interpretation 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 funding from the Province of British Columbia and the British Columbia Lottery Corporation (BCLC), a Canadian Crown Corporation. The research receives separate funding from the Province of BC Ministry of Finance (Gaming Policy & Enforcement Branch)to LC and TL. The dataset for this study was provided to the research team by the British Columbia Lottery Corporation under a Non-Disclosure Agreement that prohibits further data sharing. The Province of BC government and the BCLC had no further role in the design, analysis, or interpretation of the study, and impose no constraints on publishing. LC also receives funding from the Natural Sciences and Engineering Research Council (Canada). LC has received a speaker/travel honorarium from the National Association for Gambling Studies (Australia) and the National Center for Responsible Gaming (US), and has received fees for academic services from the National Center for Responsible Gaming (US) and Gambling Research Exchange Ontario (Canada). He has not received any further direct or indirect payments from the gambling industry or groups substantially funded by gambling. He has provided paid consultancy to, and received royalties from, Cambridge Cognition Ltd. relating to neurocognitive testing. TL is now employed by Deloitte Consulting GmbH. KM is now employed by Visier Inc.. SF, KM, XD, TL have no further disclosures to be declared.
LC is a Regional Assistant Editor for International Gambling Studies but was blinded to the review and editorial process for this manuscript.
Acknowledgements
We would like to thank the Social Responsibility and Data Analytics teams at BCLC for their assistance in providing the data.
Data availability statement
The dataset was provided in a de-identified format by the British Columbia Lottery Corporation, Data Analytics team in October 2015. Data were given to the Centre (LC and TL) under a Non-Disclosure Agreement that does not allow sharing of the dataset, or reporting of data from individual users. In the manuscript, we provide links to our code, and the exact model values, at http://github.com/CGR-UBC/PlayNow_VSEprediction_2020
Supplementary material
Supplemental data for this article can be accessed here.
Notes
1. For the purpose of classification, we use an optimized cutoff value to account for the skew in our base rates in the unbalanced case. The optimized cutoff value is found by maximizing the difference between True Positive Rate and False Positive Rate, the two axes on the ROC curve on the training dataset.
Additional information
Funding
Notes on contributors
Stephanie Finkenwirth
Stephanie Finkenwirth is a Senior Data Scientist as Visier Inc. She had worked on this project in her role as a data scientist at the Centre for Gambling Research at UBC. She has an MSc in Econometrics from Humboldt University of Berlin.
Kent MacDonald worked on this project in his role as a research assistant at the Centre for Gambling Research at UBC, and is software developer in Vancouver. He has a BA in Computer Science and Psychology from the University of Victoria.
Xiaolei Deng is a PhD student in Clinical Psychology in the Department of Psychology at the University of British Columbia. He holds a BA and MA in Psychology from UBC. His graduate research examines the use of behavioral tracking in predicting high-risk online gambling.
Tilman Lesch is a senior data scientist and manager at Deloitte Consulting GmbH in Germany. He has a PhD in Psychiatry from the University of Cambridge, and initiated this project as part of a post-doctoral placement at the Centre for Gambling Research at UBC.
Luke Clark is a Professor at the University of British Columbia, and Director of the Centre for Gambling Research at UBC. He is an experimental psychologist by training. His research focusses on the psychological and neural basis of decision-making in gambling and its relevance to the development of gambling harms.