The present study aimed to compare the expenditure of real-world online gamblers (N = 926,086) from six countries (Great Britain, Netherlands, Germany, Spain, Canada [Ontario], and US) to identify potential impacts of specific regulatory aspects on the amount of money gambled by players. The dataset comprised 233,221 British players, 167,826 Dutch players, 89,456 German players, 55,229 Spanish players, 18,463 Canadian players, and 361,891 US players. Data were analyzed using the total amount of money bet, lost, and deposited. German players bet (median = €74) and lost (median = €15) the lowest amounts of money gambling. Moreover, the average bet per game (median = €0.17) was the lowest among German players. Canadian (mean = €11,165) and US players (mean = €6434) bet the highest amounts. The US and Canada were the two countries with the largest outliers with respect to amount bet. Analysis also showed that a small percentage of players were responsible for the majority of the revenue in each of the six jurisdictions. More specifically, in the US, the 20% highest spending players accounted for 95% of the amount of money bet. The respective percentages for Canada, Great Britain, Germany, Spain and the Netherlands were 94%, 88%, 86%, 91%, and 79%. The present study's findings suggest that less restrictive regulation is associated with higher gambling expenditure, and that very strict regulation is associated with lower gambling expenditure.

Studies suggest that algorithms can effectively be used to predict self-reported problem gambling using player tracking data. The present study analyzed a sample of real-world online gamblers (N = 1,611) who engaged in lottery playing, casino gambling, bingo playing, and sports betting. The data also comprised each player’s actual gambling activity, as well as age and gender, in the 30 days prior to answering the Problem Gambling Severity Index (PGSI). Players who engaged in at least one lottery game 30 days prior to answering the PGSI were less likely to be problem gamblers compared to players who did not play lottery games. For all other game-categories the relationship was reversed. The results also indicated that specific behavioral tracking features—such as the average number of monetary deposits per session, total amount of money bet per day, session length, and casino gambling involvement—were among the most significant predictors of self-reported problem gambling. When evaluating different machine algorithms, logistic regression and random forest emerged as the most effective in predicting self-reported problem gambling. The present study is among the few which predicts self-reported problem gambling using a sample of online lottery players, casino gamblers, bingo players and sports bettors, and provides further empirical evidence supporting the use of machine learning models to identify self-reported problem gamblers based on player tracking data. These findings can inform responsible gambling strategies by enabling operators to identify and intervene before gambling-related problems escalate.

In recent years a number of studies have used objective gambling data from online gambling operators to study gambling behavior. A few of these studies have compared gamblers' actual gambling behavior (using account-based tracking data) with their subjective gambling behavior (using responses from survey data). The present study extended previous studies by comparing self-reported money deposited with the actual amount of money deposited. The authors were given access to an anonymized secondary dataset of 1,516 online gamblers from a European online gambling operator. After removing those who had not deposited any money in the previous 30 days, the final sample size for analysis was 639 online gamblers. The results indicated that gamblers were able to estimate fairly accurately how much money they had deposited in the past 30 days. However, the higher the amount of money deposited, the more likely gamblers underestimated the actual amount of money deposited. With respect to age and gender, there were no significant differences between male and female gamblers in their estimation biases. However, a significant age difference was found between those who overestimated and underestimated their deposits, with younger gamblers tending to overestimate their deposits. Providing feedback as to whether the gamblers overestimated or underestimated their deposits did not lead to any additional significant changes in the amount of money deposited when considering the overall reduction in deposits after self-assessment. The implications of the findings are discussed.

Binge gambling is a relatively under-explored area and the few published studies have all used self-report data (i.e. surveys and interviews). The use of account-based tracking data has increasingly been used to identify indicators of problem gambling. However, no previous study has ever used tracking data to operationalize and explore binge gambling. Therefore, the present study investigated whether it is possible to identify behavioral patterns that could be related to binge gambling among a real-world sample of online gamblers. The authors were given access to an anonymized secondary dataset from a British online casino operator comprising 150,895 online gamblers who gambled between January and March 2023. Using 14 parameters of gambling (e.g. total number of gambling days, total number of gambling sessions, average amount of money spent per game), six distinct clusters of gamblers were identified. Two clusters - Cluster 2 (n = 22,364) and Cluster 5 (n = 12,523) - gambled on a relatively low number of days during three months, but displayed a high gambling intensity on those days compared to the other four clusters. These two profiles could potentially match the habits of binge gamblers. The majority of players retained their behavior in the following three months between April and June 2023 and were consequently assigned to the same cluster in the latter time period. A total of 17% of gamblers in Cluster 3 and 29% of gamblers in Cluster 5 stopped gambling entirely between April and June 2023. The findings suggest that binge gambling may be able to be identified by online gambling operators using account-based tracking data and that targeted interventions could be implemented with binge gamblers.

The prevalence of online gambling and the potential for related harm necessitate predictive models for early detection of problem gambling. The present study expands upon prior research by incorporating a cross-country approach to predict self-reported problem gambling using player-tracking data in an online casino setting. Utilizing a secondary dataset comprising 1743 British, Canadian, and Spanish online casino gamblers (39% female; mean age = 42.4 years; 27.4% scoring 8 + on the Problem Gambling Severity Index), the present study examined the association between demographic, behavioral, and monetary intensity variables with self-reported problem gambling, employing a hierarchical logistic regression model. The study also tested the efficacy of five different machine learning models to predict self-reported problem gambling among online casino gamblers from different countries. The findings indicated that behavioral variables, such as taking self-exclusions, frequent in-session monetary depositing, and account depletion, were paramount in predicting self-reported problem gambling over monetary intensity variables. The study also demonstrated that while machine learning models can effectively predict problem gambling across different countries without country-specific training data, incorporating such data improved the overall model performance. This suggests that specific behavioral patterns are universal, yet nuanced differences across countries exist that can improve prediction models.

Many items in current problem gambling screens focus on negative consequences of gambling and gambling-related harms. However, few problem gambling screens comprise items that are totally based on actual gambling behavior such as gambling duration, gambling frequency, or gambling late at night. The aim of the present study was to develop and validate the 12-item Online Problem Gambling Behavior Index (OPGBI). A total of 10,000 online Croatian gamblers were administered the OPGBI alongside the nine-item Problem Gambling Severity Index (PGSI), as well as questions regarding types of gambling engaged in and socio-demographic factors. The 12 OPGBI items mainly concern actual gambling behavior. The correlation between OPGBI and PGSI was highly significant (r = 0.68). Three latent factors in the OPGBI were identified (gambling behavior, limit setting, communication with operator). The three factors all significantly correlated with the PGSI score (R2- = 51.8%). The fact that pure gambling behavior related items explained over 50% of the PGSI score strengthens the idea that player tracking could be an important approach in identifying problem gambling.

In recent years, several European regulators have introduced mandatory player tracking to identify potentially problematic online gambling. The present study's aim was to investigate the possibility of predicting future high-risk gambling based on a short time window (i.e., the first seven days after the registration for an online gambling site). The authors were given access to a secondary dataset comprising 37,986 gamblers who registered at a European online gambling operator between January 1 and April 30, 2022. The study examined the association between gambling behavior during the first week after registration and high-risk gambling during the first 90 days after registration. A logistic regression model with high-risk gamblers (based on the first three months of gambling data after initial registration) as the dependent variable and age, gender, and the first week's gambling behavior as independent variables explained 40% of the variance. Age, gender, and seven player tracking features from the first week after registration were significant. Machine learning models confirmed the high correlation between the first week of gambling and a high-risk classification during the first three months after registration. The most important features reported by a Random Forest and a Gradient Boost Machine model were the total amount of money deposited, the number of deposits, the amount of money lost, and the average number of deposits per session. The study showed that high-risk gambling during the first three months of a player's lifetime can be predicted very early after registration. These findings suggest that gambling operators should initiate preventive measures (such as limit setting, mandatory play-breaks, personalized messaging) and monitor gambling behavior at a very early stage after a gambler's initial registration.

Online gambling is a socially acceptable means of entertainment, but it can also have a negative impact on many areas of life and lead to problem gambling for a minority of individuals. In recent years, gambling operators have increasingly implemented responsible gambling tools to help at-risk gamblers control and limit their gambling. One such tool is voluntary self-exclusion (VSE), where gamblers can exclude themselves from the gambling platform for a self-selected period of time. Despite the widespread use of VSE, there are few published studies on the efficacy of VSE among online gamblers and none on whether (and what type of) gamblers return to gambling after self-exclusion and how VSE affects their wagering if they return. Using a secondary dataset, the present study empirically analyzed a real-world sample of 3,203 British online casino players who opted for a VSE between January 2021 and August 2022. Analysis showed that most players who took a short-term VSE (up to 38 days) started gambling again on the platform after their self-exclusion ended, while players who opted for long-term self-exclusion (more than 90 days) did not start gambling again on the platform. A return to the gambling platform after VSE was positively associated with (i) a shorter duration of the self-exclusion, (ii) being female, (iii) gambling on more days, (iv) placing more bets, (v) playing fewer type of games, and (vi) having a lower average number of deposits per day. Players who returned from VSE did not change their wagering compared to a matched control group. These results suggest that short-term VSE may not be as effective as long-term VSE in reducing gambling. Overall, the present findings suggest that gamblers returning from VSE should be closely monitored, especially if the reason for self-exclusion is related to problem gambling.

Structural characteristics of games have been regarded as important aspects in the possible development of problematic gambling. The most important factors along with individual susceptibility and risk factors of the individual gambler are the structural characteristics such as the speed and frequency of the game (and more specifically event frequency, bet frequency, event duration, and payout interval). To date, the association between structural characteristics and behavior has not been studied in an online gambling environment. The present study investigated the association between structural characteristics and online gambling behavior in an ecologically valid setting using data from actual gamblers. The authors were given access to data from a large European online gambling operator with players from Germany, Austria, UK, Poland, and Slovenia. The sample comprised 763,490 sessions between November 27, 2020 and April 15, 2021 utilizing data from 43,731 players. A machine learning tree-based algorithm with structural characteristics and session metrics explained 26% of the variance of the number of games played in a session. The results also showed that only 7.7% of the variance in the number of bets placed in a session was explained by the game's structural characteristics alone. The most important structural characteristic with respect to the number of games played in a session was the event frequency of the game followed by the maximum amount won on a single bet in a session.

The prevention of problematic online gambling behavior is a topic of major interest for regulators, the gambling industry, and researchers. Many gambling operators approach this issue by using responsible gambling tools. Among such tools, mandatory play breaks are used to interrupt long online gambling sessions, providing “cooling off” periods for players to take a reflective “time out”. The present study investigated the effects of mandatory play breaks in a large-scale experiment with 23,234 online gamblers engaging in more than 870,000,000 gambling transactions on Norsk Tipping’s gambling platform over a 1-month period. The gamblers were randomly assigned to several intervention groups with varying duration of mandatory play breaks and one control group with Norsk Tipping’s standard play break duration. More specifically, the study analyzed the relationship between the mandatory break received and the gambler’s acceptance of this tool, the interaction patterns with the tool, and how quickly they started to gamble again, as well as post-intervention effects on gambling behavior. Results showed that gamblers who were treated with longer mandatory breaks (i) tended to take longer voluntary breaks, and (ii) interacted more frequently with the tool (for instance, by clicking the “logout” button). Furthermore, gamblers appeared to accept longer mandatory play breaks. However, only a fraction of post-intervention effects remained, and mainly only for gamblers who received a substantial number of long mandatory play breaks. Overall, the present study provides actionable insights for both researchers and the gambling industry to improve the effectiveness of mandatory play breaks as a responsible gambling tool.

A number of scholars have argued that online gambling can be more problematic than land-based gambling. Motivating gamblers to withdraw money from their online gambling account could lower losses because there would be less money available to lose. Therefore, the present study investigated whether personalized messages are an effective way of ‘nudging’ gamblers to withdraw money from their online gambling account. The authors were given access to a secondary dataset by Nederlandse Loterij (the national Dutch Lottery operator) comprising 4049 online gamblers. Two types of messages were used to ‘nudge’ gamblers to withdraw money from their gambling account (i.e., a ‘winning streak’ message and a ‘withdrawal’ message). The findings indicated that (i) 38% of gamblers reading the ‘winning streak’ messages withdrew money from their gambling account on the same day, and (ii) 18% of gamblers reading the ‘withdrawal’ messages withdrew money from their gambling account on the same day. Gamblers who read personalized messages also withdrew larger amounts of money from their gambling accounts compared to gamblers who did not read personalized messages. The findings suggest that the personalized messages can have an impact on both the likelihood to withdraw money as well as the amount of money which was withdrawn and could help reduce gambling-related harm.

In recent years, various novel responsible gambling (RG) tools have been implemented to aid harm-minimization. One such RG tool has been the implementation of enforced mandatory play breaks. Despite many responsible gambling operators using mandatory play breaks, only three previous studies have examined their efficacy and the findings were mixed. Therefore, the present investigation was a large-scale real-world study which was designed to see whether a 60-minute mandatory play break influenced subsequent depositing and wagering. The authors were given access to 27 days of player data prior to the introduction of a mandatory play break and 27 days of player data after the mandatory play break was introduced. The study comprised British online gamblers from Skillonnet (a European online gambling operator). Between July 23 and September 15 (2021), 2,021 players deposited at least ten times or more on a calendar day, at least once. The 2,201 players generated 2,994 corresponding events (i.e., the depositing of money at least 10 times in one day). The percentage of players who stopped depositing money as a consequence of the mandatory play break rose from 27% to 68% on the day of a play break. Moreover, the percentage of players who stopped wagering as a consequence of the mandatory play break rose from 0.1% to 45% on the day of a play break. The findings of the present study demonstrated that a 60-minute mandatory play break impacts players’ depositing and wagering immediately after the play break. This means that a mandatory hour-long play break in an online casino setting appears to prevent overspending during a short period of time. The effects of a 60-minute mandatory break on the next day’s behavior were inconclusive.

The novel coronavirus-2019 (COVID-19) pandemic has had major impacts on most societies worldwide including the cancelation and postponement of sports events. This has had a major impact on the sports betting industry. The present study is first to investigate the behavior of a sample of online sports bettors before and after COVID-19 measures were put in place by European governments. The authors were given access to the player data by a large European online gambling operator comprising players from Sweden, Germany, Finland, and Norway. The behavioral change of the sports bettors before March 7 and after March 7 (2020) was computed. All sports bettors who placed at least one wager in at least 5 calendar weeks out of the 10 possible calendar weeks between January 1 and March 7 ( n = 5396) were included in the analysis. Results showed statistically significant reductions among sports bettors wagering in online casinos. This indicates that there was no conversion of money spent from sports betting to online casino games, at least for this particular online gambling operator. The findings suggest that there was a significant decrease in the amount of money wagered by sports bettors during the COVID-19 pandemic (compared with before it) and that sports bettors did not switch to playing more online casino games and that there was also a significant reduction in playing online casino games among sports bettors.

Player protection has become an important area for the gambling industry over the past decade. A number of gambling regulators now require gambling operators to interact with customers if they suspect they are gambling in a problematic way. The present study provided insight on the impact of personalized feedback interventions (PFIs) on subsequent gambling behavior among a Dutch sample of real-world gamblers. Nederlandse Loterij (the national Dutch Lottery operator) provided access to a secondary dataset comprising tracking data from online casino and sports betting gamblers (N = 2,576) who were contacted either by e-mail or telephone between November 2021 and March 2022 if they showed signs of problematic gambling as identified using behavioral tracking software. Compared to matched controls (n = 369,961 gamblers), Dutch gamblers who received a PFI (via e-mail [n = 1876] or a telephone call [n = 700]) from the gambling operator had a significant reduction in amount of money deposited, amount of money wagered, number of monetary deposits, and time spent gambling in the 30 days after being contacted. Gambling frequency as measured by the number of gambling days did not change significantly after a PFI. Telephone calls did not lead to a significant larger reduction with respect to the aforementioned behavioral metrics. High-intensity players reduced their gambling behavior as frequently as low-intensity players, which means that the intervention's success was independent of gambling intensity. The impact on subsequent gambling was the same across age groups and gender. The results of the present study are of use to many different stakeholder groups including researchers in the gambling studies field and the gambling industry as well as regulators and policymakers who can recommend or enforce that gambling operators utilize responsible gambling tools such as using PFIs to those who may be displaying problematic gambling behaviors as a way of minimizing harm and protecting gamblers.

In recent years researchers have emphasized the importance of artificial intelligence (AI) algorithms as a tool to detect problem gambling online. AI algorithms require a training dataset to learn the patterns of a prespecified group. Problem gambling screens are one method for the collection of the necessary input data to train AI algorithms. The present study’s main aim was to identify the most significant behavioral patterns which predict self-reported problem gambling. In order to fulfil the aim, the study analyzed data from a sample of real-world online casino players and matched their self-report (subjective) responses concerning problem gambling with the participants’ actual (objective) gambling behavior. More specifically, the authors were given access to the raw data of 1,287 players from a European online gambling casino who answered questions on the Problem Gambling Severity Index (PGSI) between September 2021 and February 2022. Random forest and gradient boost machine algorithms were trained to predict self-reported problem gambling based on the independent variables (e.g., wagering, depositing, gambling frequency). The random forest model predicted self-reported problem gambling better than gradient boost. Moreover, problem gamblers showed a distinct pattern with respect to their gambling based on the player tracking data. More specifically, problem gamblers lost more money per gambling day, lost more money per gambling session, and deposited money more frequently per gambling session. Problem gamblers also tended to deplete their gambling accounts more frequently compared to non-problem gamblers. A subgroup of problem gamblers identified as being at greater harm (based on their response to PGSI items) showed even higher values with respect to the aforementioned gambling behaviors. The study showed that self-reported problem gambling can be predicted by AI algorithms with high accuracy based on player tracking data.

Social responsibility and duty of care have become major cornerstones for gambling operators. This has led to the introduction of many different responsible gambling tools such as limit-setting, mandatory play breaks, and personalized messaging. In the present study, the authors were given access to two secondary datasets provided by a German online slots game operator. The first dataset was from an online survey carried out by the gambling operator among 1000 of its players concerning their attitude towards deposit limits as well as self-reported problem gambling. In addition to the survey responses, the authors were given access to a second dataset of account-based data concerning each customer's wagers, wins, monetary deposits, and monetary withdrawals. These datasets were then combined. The majority of players had a positive attitude towards the maximum deposit monthly deposit limit which was introduced by the German State Treaty on Gambling in 2021. Players who disagreed with the maximum monthly deposit limit, deposited significantly more money in the 30 days prior to answering the survey questions compared to players who agreed with the monthly deposit limit. The tracking data found only 7.6% of players had deposited the maximum amount of money allowed in one month. However, 60.5% of players in the survey data said that they did so. Players who said that they continued to gamble after reaching the deposit limit wagered and deposited significantly more money in the 30 days prior to the survey compared to players who said they stopped gambling after reaching the deposit limit. Two-fifths of players said they continued to gamble after reaching the monthly deposit limit (42%). The majority of the players said they chose a personal deposit limit because it helped them to better control their gambling expenditure. A quarter of the players reported gambling problems using the Brief Biosocial Gambling Screen (27%). Self-reported problem gambling was not correlated with depositing, wagering or any other player tracking metric.