Markers of unsustainable gambling for early detection of at-risk online gamblers

Abstract

In this work we propose novel markers for identifying at-risk gamblers based on the concept of sustainability. The first hypothesis here verified is that problematic gamblers oscillate between intervals of increasing wager size followed by rapid drops, probably because they exceed their economic sustainability limits. Due to the non-periodic nature of these fluctuations, the proposed marker detects a certain occurring feature, such as a rapid drop in wager size, over a wide range of fluctuation periods, drop sizes and shapes. The second marker, counting the number of games the gambler is involved in, aims at predicting possible consequences of an exceeding amount of time dedicated to gambling, that ultimately causes social and relational breakdowns. In the experimental phase we demonstrate how the adoption of these markers allows for identifying larger segments of high- and medium-risk gamblers with respect to previous research on actual betting behaviours

Telecommunications Network Measurements of Online Gambling Behavior in Switzerland: A Feasibility Study

“…Overall, the results of these studies do not support earlier findings that Internet gambling is more addictive than land-based gambling [15,16,17,18,19,20,21,22,23,24,25,26]. Meanwhile, a growing body of research has focused on analyzing data sets of gambling accounts provided by various gambling operators [12,13,27,28]. …”

Chasing losses in online poker and casino games: Characteristics and game play of Internet gamblers at risk of disordered gambling

“…Over the past few years efforts have been made to design intelligent detection systems to identify markers of risky and disordered gambling using algorithms that analyse player behaviours and interactions (Dragicevic et al, 2011;Gainsbury, 2011;Auer and Griffiths, 2012;Braverman and Shaffer, 2012;Adami et al, 2013). These systems can be used to trigger warning signs for players or notify operators to check in with players in an attempt to minimise harms and prevent gamblers developing serious problems (Gainsbury, 2011;Haefeli et al, 2011).…”

Identifying high-risk online gamblers: a comparison of data mining procedures

“…More information on the data set is available in Braverman and Shaffer (2012), Dragicevic 56 K.S. Philander Adami et al (2013). In order to provide a metric that is meaningful for actual implementation of these algorithms, the SLAs are compared based on their classification parameters: sensitivity, specificity, precision, accuracy, odds ratio and area under curve (AUC) (Sing, Sander, Beerenwinkel, & Lengauer, 2005).…”

“…Adami et al (2013) expand on Braverman and Shaffer (2012), and found two new markers for identifying at risk gamblers -the 'sawtooth' oscillation between increasing wager size and rapids drops, and number of games played (gambling involvement). Adami et al (2013) also note that the unsupervised k-means clustering process may be suboptimal.…”

“…Adami et al, 2013;Braverman & Shaffer, 2012;Dragicevic, Tsogas, & Kudic, 2011). While this information is important to understanding classes of player types, supervised learning algorithm (SLAs) may provide useful improvements in identification tasks, once behavioural markers of problem gamblers have been identified.…”