RG Smart Gambling Machines: A prevention model to respond to risky play in real time
Bibliographic record
Abstract
Abstract: In collaboration with industry, public health, and regulators, Focal Research developed an effective modelling process using player data and technology to identify and assist customers at-risk of having problems with their gambling. The system was originally designed using account-based player data to accurately assess play patterns. Complex algorithms scan the player data stored in an operator’s member data system, alerting operators to play behaviours typically observed among those scoring 8 or higher on the Problem Gambling Severity Index. During a live trial, the system was found to help staff interact with at-risk customers leading to measurable improvement in outcomes for ‘Players of Interest’ identified by the algorithms. The next step is to use this technology to expand player protection to customers gambling without using player identification (i.e., anonymous, or non-account gambling transactions). With industry sponsorship and co-funding through the National Research Council of Canada, Focal Research has developed a prototype model using session data to identify at-risk gambling behaviour during play and to possibly offer valuable messaging (i.e., receiving an interaction or seeing a targeted message when the player is engaged in relevant risky play practices rather than when they reach an arbitrary threshold of time or money spent). Implications: The prototype performed well, offering the potential for detecting at-risk play in real-time so targeted personal or automated intervention can occur when it is most likely to be beneficial for the customer. Focal will report on model performance for research underway with operators in Britain, Australia, and New Zealand.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 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".