Detection of possible problem gambling behaviour
AssigneeMindway Ai Aps
InventorKim Mouridsen
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a system and a method for identifying possible problematic behaviour in gambling, in particular online gambling involving monetary transactions. One embodiment relates to a computer implemented method for detection of possible problem gaming behaviour of a subject engaged in one or more 5 games involving monetary transactions, the method comprising the steps of obtaining a dataset comprising the subjects gaining transactions over a time period, analysing the gaining behaviour of said subject by modelling against a trained model employing artificial intelligence, and predicting and/or detecting Possible Problem Gambling Behavior (PPGB) of said subject based on the analysis wherein the trained model is 10 trained based on one or more behavioral targets at outcome.
Claims22
A computer implemented method for detection of possible problem gaming behaviour of a subject engaged in one or more games involving monetary transactions, the method comprising the steps of:
- obtaining a reference dataset that includes objective markers of gameplay by a plurality of reference subjects over a first time period;
- dividing the reference dataset into a first subset and a second subset, the first subset corresponding to an early portion of the first time period and the second subset corresponding to a later portion of the first time period;
- labeling the second subset with results of an expert behaviour assessment of the second subset to generate labels for the second subset;
- training a classification model using the first subset and the labels for the second subset;
- obtaining a subject dataset comprising the subject's gaming transactions over a second time period,
- applying the subject dataset against the classification model;
- and
- detecting Possible Problem Gambling Behaviour (PPGB) of said subject based on an analysis of gaming behaviour output by the classification model.
A system for detection of possible problem gaming behaviour of a subject engaged in one or more games, comprising a computer-readable storage device for storing instructions that, when executed by a processor, cause the system to:
- obtain a reference dataset that includes objective markers of gameplay by a plurality of reference subjects over a first time period;
- divide the reference dataset into a first subset and a second subset, the first subset corresponding to an early portion of the first time period and the second subset corresponding to a later portion of the first time period;
- label the second subset with results of an expert behaviour assessment of the second subset to generate labels for the second subset;
- train a classification model using the first subset and the labels for the second subset;
- obtain a subject dataset comprising the subject's gaming transactions over a second time period,
- apply the subject dataset against the classification model;
- and
- detect Possible Problem Gambling Behaviour (PPGB) of said subject based on an analysis of gaming behaviour output by the classification model.
Dependencies are inferred from the claim text.