Modelling product risk and gambling harms in online gambling
Bibliographic record
Abstract
The internet has increased the accessibility of gambling, with a corresponding increase in the risk of gambling problems. To date, little research has examined the risk profile of different forms of online gambling, or considered financial data to predict gambling risk. This dissertation describes a series of secondary analyses looking at the ‘concentration’ of online gambling activity, i.e. to what extent a small set of highly-engaged gamblers accounts for the majority of gambling activity. This is explored via the Pareto (20:80) rule and Gini coefficients. To link these effects to likely gambling problems, enrolment in Voluntary Self-Exclusion (VSE) is used; VSE programs enable a gambler to bar themselves from online and physical casinos. The dataset is from a Canadian provincial online casino for British Columbia from 2014-2015, consisting of 30,902 gamblers making over half a billion bets. Study 1 quantified the overall concentration effects for the eCasino, based on the number of bets and the net loss. Study 1 also examined Pareto values over time, finding that concentration values accumulated at longer timeframes. In the full year dataset, the 20% most active gamblers accounted for roughly 90% of gambling activity, and this elevated concentration (compared to the traditional 20:80 Pareto rule) was associated with elevated VSE rates among most active gamblers. Study 2 extended these findings by examining concentration metrics among four categories of gambling products. Video poker had the highest concentration values, and online slot machines had the lowest values. Study 2 proposes a novel measure of personal risk, combining product engagement with the concentration estimates. These personal risk scores were found to be higher among VSE gamblers. Study 3 found that gamblers with a VSE record showed higher levels of payment behaviours, including deposits and withdrawals and via more payment channels, compared to non-VSE gamblers. Random Forest models were able to classify VSE status at AUROC = 0.8 using only payment variables, and performance further improved to AUROC = 0.87 when personal risk scores were included. These results support utility of concentration effects as an indicator of product risk, and the utility of payment variables in risk modelling.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.011 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".