Identifying Behavioral Characteristics in EGM Gambling Data Using Session Clustering

The rising accessibility and popularity of gambling products has increased interest in the effects of gambling. Nonetheless, research of gambling measures is scarce. This paper presents the application of data mining techniques, on 46,514 gambling sessions, to distinguish types of gambling and identify potential instances of problem gambling in EGMs. Gambling sessions included measures of gambling involvement, out-of-pocket expense, winnings and cost of gambling. In this first exploratory study, sessions were clustered into four clusters, as a stability test determined four clusters to be the most high-quality yielding and stable solution within our clustering criteria. Based on the expressed gambling behavior within these sessions, our k-means cluster analysis results indicated sessions were classified as potential non-problem gambling sessions, potential low risk gambling sessions, potential moderate risk gambling sessions, and potential problem gambling sessions. While the complexity of EGM data prevents researchers from recognizing the incidence of problem gambling in a specific individual, our methods suggest that the lack of player identification does not prevent one from identifying the incidence of problem gambling behavior.