Predicting online gambling self-exclusion: an analysis of the performance of supervised machine learning models

As gambling operators become increasingly sophisticated in their analysis of individual gambling behaviour, this study evaluates the potential for using machine learning techniques to identify individuals who used self-exclusion tools out of a sample of 845 online gamblers, based on analysing trends in their gambling behaviour. Being able to identify other gamblers whose behaviour is similar to those who decided to use self-exclusion tools could, for instance, be used to share responsible gaming messages or other information that aids self-aware gambling and reduces the risk of adverse outcomes. However, operators need to understand how accurate models can be and which techniques work well. The purpose of the article is to identify the most accurate technique out of four highly diverse techniques and to discuss how to deal analytically and practically with a rare event like self-exclusion, which was used by fewer than 1% of gamblers in our data-set. We conclude that balanced training data-sets are necessary for creating effective models and that, on our data-set, the most effective method is the random forest technique which achieves an accuracy improvement of 35 percentage points versus baseline estimates.     

Cognitive distortions as a problem gambling risk factor in Internet gambling

The purpose of this study was to examine the role of cognitive distortions in Internet gambling. The primary objectives were to determine whether cognitive distortions predict Internet gambling and investigate whether distorted gambling-related cognitions are associated with problem gambling severity among online gamblers. Three hundred and seventy four undergraduate participants (143 online gamblers, 172 males) completed an online questionnaire looking at demographics, play-related variables (duration, frequency and expenditures of play) and cognitive distortions. Variables were entered into a logistic regression model to predict online gambling. Three variables made independent contributions to predicting Internet gambling: male gender, higher frequency of play, and cognitive distortions. A hierarchical linear regression analysis with Internet gamblers revealed that cognitive distortions accounted for a proportion of the variance in problem gambling severity beyond variance accounted for by demographic variables and level of gambling involvement. Results suggest that cognitive distortions are a risk factor in online gambling.     

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

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.     

Analyses of multiple types of online gambling within one provider: an extended evaluation framework of actual online gambling behaviour

The aim of this article is to extend previous publications of actual online gambling behaviour that neglected involvement across multiple types of gambling and did not provide levels of at-risk involvement. Behavioural data from 27,653 subscribers of an online gambling provider (bwin) in February 2005 were reanalysed across eight products over seven months. Established involvement levels of offline gambling segregated possible online at-risk gamblers. Forty-seven percent of the sample exceeded at least one of the two most conservative thresholds. Each additionally used gambling product increased the risk of transgressing involvement cut-offs by 3.06 to 4.27 times, but type-specific risks decreased strongly after adjusting for involvement in multiple gambling types. Only Poker and Live-action betting remained significant risk factors after adjustment. Taken together, cross-product analyses of gambling patterns lay the groundwork for an extended understanding of individual online gambling behaviour and overcome the methodological artefacts of isolated analyses.     

Forms of gambling,gambling involvement and problem gambling: evidence from a Swedish population survey

The purpose of this study was to explore the association between problem gambling (PG) and participation in different forms of gambling in order to elucidate relationships between PG, gambling involvement and gambling intensity. Using data from the first wave of the Swedish Longitudinal Gambling Study (Swelogs) (n = 4,991), the study tested four hypotheses, namely that (1) some forms of gambling are more closely associated with PG than other forms; (2) high gambling involvement is associated with PG; (3) gambling involvement is positively associated with the intensity of gambling; and (4) the relationship between gambling involvement and PG is influenced by the specific forms of gambling in which individuals participate. All four hypotheses were supported. More specifically, the study found that while many PGs regularly participate in multiple forms of gambling, half of PGs participate regularly in only one or two forms of gambling. The study concluded that some forms of gambling are more closely associated with problem gambling than other forms, and that gambling policy and regulation, as well as the development of responsible gambling initiatives, should focus on these forms.     

Internet gambling in relation to Internet addiction,substance use,online sexual engagement and suicidality in a Greek sample

Research has found gambling to be related to a variety of other addictive behaviours. The study objective was to evaluate the association of Internet gambling with Internet addiction, online sexual engagement, suicidality and substance use, in a sample of Greek adults. The study sample consisted of 789 military personnel. During their annual medical examination the study participants anonymously completed a series of self-reported questionnaires in relation to socio-demographic data, Internet gambling practices, online sexual engagement, Internet addiction, suicidality and psychoactive substance use. We found that Internet addiction significantly predicted engagement with online gambling, followed by substance use in general, and, in particular, the use of cocaine or heroin. Finally, two other predictive indicators were self-reported suicide attempts and engagement with online sex. Online gambling is associated with various behaviours related to impulsivity such as Internet addiction, online sexual engagement, suicidality and substance use. Future research will increase our knowledge on the contribution of new technologies and the Internet in Internet gambling dimensions, as well as on the associations with other high-risk behaviours such as substance use, pornography and suicidality.     

A taxonomy of gambling and casino games via social media and online technologies

The increased popularity of casino games on social media platforms has prompted international jurisdictions to consider the extent to which these games may be similar to Internet gambling activities and therefore subject to regulatory action. Gambling themes are popular in video and computer games, and simulated-gambling activities are commonly offered by gambling operators as a way of enticing users to gamble online with money. However, little research has evaluated the impact of the digital convergence of gambling and gaming. The lack of a clear definition of online gambling-themed activities to guide such research undertakings represents a significant hurdle to the fields of gambling and gaming. Based on a review of the extant literature, this article proposes a taxonomy to distinguish between many types of online activities with gambling-themed content. This taxonomy suggests that the principal features that differentiate online gambling games include the requirement for payment, the role of skill, the type of platform and the centrality of the gambling theme. The proposed hierarchical framework aims to promote clear and consistent discussion to guide ongoing investigation of new and emerging Internet gambling and gaming technologies.     

Predicting gambling behaviour and problems from implicit and explicit positive gambling outcome expectancies in regular gamblers

Outcome expectancies are the positive or negative effects that individuals anticipate may occur from engaging in a given behaviour. Although explicit outcome expectancies have been found to play an important role in gambling, research has yet to assess the role of implicit outcome expectancies in gambling. In two studies, we investigated whether implicit and explicit positive gambling outcome expectancies were independent predictors of gambling behaviour (i.e. amount of time spent and money risked gambling; Study 1) and problem gambling severity (Study 2). In both studies, implicit positive gambling outcome expectancies were assessed by having regular gamblers (N = 58 in Study 1; N = 96 in Study 2) complete a gambling outcome expectancy reaction time (RT) task. A self-report measure of positive gambling outcome expectancies was used to assess participants' explicit positive gambling outcome expectancies. Both the RT task and self-report measure of positive gambling outcome expectancies significantly contributed unique as well as shared variance in the prediction of self-reported gambling behaviour (Study 1) and problem gambling severity (Study 2). Findings from the current research point to the importance of using both direct and indirect assessment modes when examining the role of outcome expectancies in gambling.     

Gendered gambling domains and changes in Sweden

Pachinko is an ‘amusement arcade’ type machine that is popular throughout Japan, with an estimated 17.1 million ‘players’ providing an enormous annual revenue of 2.87 trillion yen (US$250 billion). It is simple and easy to play and has all the hallmarks and structural features of gaming machines worldwide. While academic discourses on the addictive potential of gaming machines are well developed, their application to pachinko is very limited. This is, perhaps, due to a number of factors. First, pachinko is portrayed as a game rather than as gambling in Japan, so that addiction issues are ignored or downplayed. Second, most accounts of ‘playing’ pachinko are journalistic rather than academic. Third, academics tend to focus on police corruption and organized crime rather than addiction. Here, we take the approach that pachinko represents ‘gambling by proxy’ and explore its addictive potential. We conclude that unless pachinko is recognized as a form of gambling, present changes in Japanese legislation will be of limited value in tackling addiction.     

Does gambling type moderate the links between problem gambling,emotion regulation,anxiety, depression and gambling motives

The aim of this study is to assess the link between emotion regulation, depression, anxiety and gambling motives among a population of regular gamblers, distinguishing between strategic and chance game players. We recruited 287 regular gamblers online, including both problem (PG) and non-problem gamblers (NPG). All participants completed online questionnaires to screen for problem gambling (SOGS) and to assess emotion regulation (ERQ), anxiety and depression (HADS) and gambling motives (GMQ-F). In this sample, 33.4% of participants were PG. PG scored significantly higher than NPG on the GMQ-F (except for the social subscale) and HADS, but not in ERQ. Gamblers who played both strategic and chance games displayed more frequent and severe gambling problems and had higher depression and anxiety scores than those playing only strategic games. Overall, enhancement and financial motives and depression significantly predicted PG. Finally, the study found that gambling type moderates the relationship between problem gambling and expressive suppression, depression and gambling motives. The results show the intricate relationship between gambling motives and psychiatric symptoms (in particular, depression) in PG. Mixed and strategic gamblers share common motives, but coping, financial and enhancement were stronger among PG. Finally, they emphasize the differences between different types of gamblers.     

The classification accuracy of four problem gambling assessment instruments in population research

Improved methodology was used to re-examine the weak correspondence between problem and pathological gamblers identified in population surveys and subsequent classification of these individuals in clinical interviews. The SOGS-R, the CPGI, the NODS and the Problem and Pathological Gambling Measure (PPGM), as well as questions about gambling participation and expenditures, were administered to a total of 7272 adults. Two clinicians then assessed each person's status, based on comprehensive written profiles derived from these questionnaire responses. Instrument classification was then compared to clinical classification. All four instruments correctly classified most non-problem gamblers (i.e. had good to excellent sensitivity, specificity and negative predictive power). However, the PPGM was the only instrument with good classification of problem gamblers (i.e. excellent sensitivity and positive predictive power). The CPGI and SOGS-R had weak positive predictive power and the NODS had only adequate sensitivity and positive predictive power. Improvement in the classification accuracy of the CPGI occurred when a 5+ cut-off was used and when a 4+ cut-off was used with the SOGS. In general, the classification accuracy of the NODS, SOGS and CPGI is better than prior research suggested but overall accuracy is still modest. With adjusted cut-offs, all three instruments are reasonably congruent with clinical ratings.     

Thoughts and acts of self-harm,and suicidal ideation,in online gamblers

Gambling problems have been linked to suicidal ideation and enhanced risk of suicide attempts. However, we know very little about the factors associated with either thoughts or acts of self-harm amongst people who gamble. A web-based study of 4125 online gamblers (79% males; mean age 35.5 years), analysed using hierarchical multiple regression, revealed that self-reported non-gambling-related self-harm was negatively related to age and marital status, and positively related to problematic alcohol use. Self-reported acts of self-harm both related and unrelated to gambling were associated with drug misuse. Thoughts and acts of gambling-related self-harm were associated with problem gambling, gambling involvement and parental problem gambling. All types of self-harm were associated with mood disorder symptoms, unemployment and certain gambling motivations. When tailoring assessment and interventions for individuals at risk for gambling-related deliberate self-harm, it is important to recognize that contributory factors may include some that differ from those for deliberate self-harm in general, and that there is potential value in evaluating gambling involvement and motivations, and history of parental gambling.     

Assessing the effectiveness of a responsible gambling behavioural feedback tool for reducing the gambling expenditure of at-risk players

The current study assessed the utility of a responsible gambling (RG) tool that provides players with behavioural feedback about their gambling. Data was obtained from 779 people (n = 694 male; n = 85 female) who gambled online with Svenska Spel (the Swedish gambling operator) and who opted to receive behavioural feedback via an RG tool (Playscan). Importantly, data was also obtained from a matched sample of 779 players who did not opt to receive behavioural feedback. Feedback took the form of a colour-coded risk rating (Green = no issues, Yellow = at-risk, Red = problematic), which was determined by a proprietary algorithm. Additionally, gambling expenditure data (amounts deposited and wagered) was gathered for the week in which players enrolled to use the RG tool, the subsequent week and 24 weeks later (this data was also gathered for the matched sample). Results showed that Yellow (i.e. at-risk) players who used the tool significantly reduced the amounts of money deposited and wagered compared to players who did not use the tool – an effect observed the week following enrolment as well as 24 weeks later. Thus, informing at-risk players who have opted to receive feedback about their gambling appears to have a positive impact on subsequent expenditures.     

Explaining the performance of online sports bettors

This article reports the results of an online survey conducted among a sample of 161 online sports bettors in which their return-on-investment (ROI) performance as computed on the basis of their last 20 bets was used as the main dependent variable. A regression analysis showed that the online gamblers’ ROI performance is positively associated with their experience in sports betting, the degree of information search and analysis performed prior to betting, and their propensity to consider that events that happen in their life are the results of chance forces. These research results are discussed in the context of a general theoretical model where gambling performance is seen as depending on four types of determinants: the gambler's experience, personality, motivation and cognitive abilities.     

Gambling attitudes and beliefs associated with problem gambling: the cohort effect of Baby Boomers

Recreational and problem gamblers alike hold beliefs about gambling that are dysfunctional. These dysfunctional beliefs have been theorized to play a role in problem gambling behaviour. The current study sought to examine the effects of gambling attitudes and beliefs on problem gambling behaviour across three cohorts. A sample of 308 participants consisted of 101 individuals from Generation X, 139 from the Baby Boom cohort and 68 from the Silent Generation. Hierarchical multiple regressions showed that for Baby Boomers, higher scores on scales measuring beliefs about luck and illusions of control were associated with higher scores on measures of problem gambling than for the Silent Generation. Generation X’s higher scores on luck scales were associated with higher scores in problem gambling than the Baby Boom cohort. Attitudes associated with problem gambling did not differ among cohorts. These results suggest that while cohorts may not differ in types or levels of distorted beliefs, they differ in how such distortions relate to problem gambling. Future research should focus on determining whether such cohort effects are indicative of differences within the development and maintenance of problem gambling itself.     

Problem gambling,familial violence and alcohol misuse: exploring the triad for treatment-seekers

Research into the co-occurrence of problem gambling, familial violence, and alcohol misuse is limited. While these issues have been considered in combination (i.e. violence and alcohol misuse, problem gambling and alcohol misuse, problem gambling and violence), within Australia, in particular, there has been an absence of exploration of this triad. The current research attempts to fill the gap in the literature, to establish whether there is any difference between problem gamblers with co-occurring violence and problem gamblers who had not experienced violence in terms of their alcohol misuse and gambling behaviours. Interviews were conducted with 81 treatment-seeking problem gamblers to explore how a history of victimization only, perpetration only, victimization and perpetration, or no history of family violence impacted on gambling behaviours (including baseline Victorian Gambling Screen), as well as alcohol misuse. Results indicated that in this treatment-seeking sample there were no significant differences for gambling behaviours or alcohol misuse between problem gamblers with issues of violence and those without. Males demonstrated (on average) a greater tendency toward hazardous drinking or disordered alcohol use. It would be prudent for treatment services to routinely examine problem gamblers' history of violence and alcohol misuse until research verifies the nature of this triad.     

Defining a threshold of harm from gambling for population health surveillance research

The measurement of harm in the context of non-problem gambling has received little attention from researchers in the field. Using the combined data from six provincial gambling surveys conducted in Canada between 2001 and 2005 (N = 12,285), we compared how different thresholds of defining gambling-related harm impacts prevalence, the relationship with indicators of gambling intensity and the characteristics of non-pathological gamblers who report experiencing below threshold symptoms of problem gambling. Survey items defining harm were drawn from the Problem Gambling Severity Index (PGSI) of the Canadian Problem Gambling Index. Three definitions of harm – reporting one or more problem gambling symptoms, reporting two or more problem gambling symptoms and having a PGSI score ≥ 3 – demonstrated a strong relationship with indicators of gambling intensity, and reliably differentiated low-threshold and zero symptom problem gamblers in terms of gambling characteristics and other risk factors.     

National survey on lifestyles and gambling in Serbia: gambling participation and problem gambling in adult population

The aim was to examine the association of socio-demographic and lifestyle characteristics with gambling severity level. The study was a part of the National Survey on Lifestyles in Serbia: Substance Abuse and Gambling, in 2014. The sample consisted of 5385 individuals. Based on the Problem Gambling Severity Index (PGSI) score participants were divided into non-problem gambling, low-/moderate-risk gambling and problem gambling. Prevalence of problem gambling was 0.5%, which was associated with having poor self-perceived financial status, having moderate or high risk for psychological distress, playing sports betting, casino games and slot machines. Low/moderate gambling was associated with having poor self-perceived financial status, number of drinking days per year, using any illicit drugs in the last 30 days, playing sports betting, slot machines, and online betting. Programmes of early detection of problem gambling should be developed, and regulation of availability of slot machines and sports betting.