Both personality factors (e.g. impulsivity) and structural game characteristics impact decision-making on games of chance. We examined the relationship between impulsivity and decision-making on a slot machine task programmed with different near-miss frequencies. Fifty-eight college students entered a simulated casino environment and played a slot machine pre-loaded with 30 credits. Unbeknownst to participants, the slot machine was programmed so that several larger wins occurred early in the sequence, followed by a pattern of diminishing returns that reduced credits to zero on a predetermined trial. Participants were randomly assigned to two conditions, the first with up to 19% of trials set as near misses and the second with only 2% as near misses. After controlling for gender, race, and lifetime gambling frequency, the near-miss condition was found to moderate the relationship between impulsivity and the number of trials played. When there were fewer near misses, impulsivity did not appear to impact decision-making. However, when near misses were frequent, individuals with higher impulsivity persisted longer, even when other characteristics of gameplay remained constant (e.g. bet size, prizes). These findings suggest that certain features of slot machines may capitalize on impulsive gamblers’ vulnerabilities and should be regulated.

Gambling activities are rapidly migrating online. Algorithms that effectively detect at-risk users could improve the prevention of online gambling-related harms. We sought to identify machine learning algorithms capable of detecting self-reported gambling problems using demographic and behavioral data. Online gamblers were recruited from all licensed online gambling platforms in France by the French Online Gambling Regulatory Authority (ARJEL). Participants completed the Problem Gambling Severity Index (PGSI), and these data were merged and synchronized with past-year online gambling behaviors recorded on the operators’ websites. Among all participants (N = 9,306), some users reported betting exclusively on sports (N = 1,183), horseracing (N = 1,711), or poker (N = 2,442) activities. In terms of Area Under the Receiver Operating Characteristic Curve (AUC), our algorithms showed excellent performance in classifying individuals at a moderate-to-high (PGSI 5+; AUC = 83.20%), or high (PGSI 8+; AUC = 87.70%) risk for experiencing gambling-related harms. Further, these models identified novel behavioral markers of harmful online gambling for future research. We conclude that machine learning can be used to detect online gamblers at-risk for experiencing gambling problems. Using algorithms like these, operators and regulators can develop targeted harm prevention and referral-to-treatment initiatives for at-risk users.

Euro-Canadians and Chinese typically hold different theories about change; Euro-Canadians often engage in linear thinking whereas Chinese often engage in non-linear thinking. The present research investigated the effects of culture-specific theories of change in two related gambling fallacies: the gambler’s fallacy (GF; the belief that one is due for a win after a run of losses) and the hot-hand fallacy (HHF; the belief that one’s winning streak is likely to continue). In Study 1, participants predicted the outcome of a coin toss following a sequence of tosses. Study 2 involved predicting and betting on the outcome of a basketball player’s shot following a sequence of shots. In Study 1, Asians (mainly Chinese) were significantly more likely than Euro-Canadians to believe that they would win (correctly predict the coin toss) after a series of losses (a non-linear thinking pattern), suggesting greater susceptibility to the gambler’s fallacy. In Study 2, Euro-Canadians were more likely than Chinese to predict outcomes consistent with a basketball player’s streaks (a linear thinking pattern), suggesting greater susceptibility to the hot hand fallacy. By illustrating the role of cultural differences in cognition, these findings contribute to our understanding of why certain cultural groups, such as Chinese, are more susceptible to gambling.