Tracking online poker problem gamblers with player account-based gambling data only

Area of Science:

• Behavioral addiction research
• Computational social science
• Digital health

Background:

• Problem gambling is a significant public health concern.
• Online gambling platforms generate vast amounts of player account-based gambling data (PABGD).
• Identifying problem gamblers in real-time is crucial for timely intervention.

Purpose of the Study:

• To develop and validate an instrument for tracking online problem poker gamblers.
• To utilize PABGD for creating a predictive model of problem gambling.
• To assess the feasibility of using PABGD for problem gambler identification.

Main Methods:

• A predictive model was built using stepwise logistic regression on PABGD.
• The Problem Gambling Severity Index (PGSI) served as the gold standard for validation.
• 14,261 active online poker gamblers from Winamax participated.

Main Results:

• 18% of participants were identified as online poker problem gamblers (PGSI ≥ 5).
• Key risk factors identified include male gender, younger age (<28), compulsive behavior, and specific deposit, loss, stake, and session frequency thresholds.
• The developed tracking instrument demonstrated 80% sensitivity and 50% specificity.

Conclusions:

• It is feasible to develop and validate instruments for tracking online problem gamblers using only PABGD.
• The predictive model offers a promising method for early identification and intervention.
• Further research can refine this approach for broader application in online gambling settings.