The research was carried out by comparing Future Anthem’s Safer Player machine learning platform against 36 million gaming sessions carried out with Gamesys. Markers of player harm- intensity, frequency, variability and trajectory -were compared to aspects of gameplay outcomes- volatility, hit rate and return to player (RTP).
The research tracked the behaviours and performances of 800,000 players.
Overall, the results found no correlation between these features and the determinants of harmful play.
Volatility was calculated for each game in the study, and then placed into four categories- low, medium, medium/high and high.
Games that featured the highest amount of potential harm were classified as medium-high in volatility. Future Anthem said that this was not high enough to suggest a direct correlation between harm and volatility.
For hit rates and RTP, a similar exercise was carried out. Hit rate was sorted into categories of 35%-65%, 20%-35% and 6%-20%.
RTP for games was classified into bands of 96.1%-97.75%, 95.6%-96.09%, 95.0%-95.59% and 88.1%-94.99%.
Like volatility, neither of these gameplay outcomes were found to correlate with irresponsible gambling behaviour.
However, the report did suggest that gambling between the hours of 12am and 6am was 36% riskier than at other times of the day.
In terms of game popularity, the report found that players were just as likely to display markers of gambling harm when playing their favourite game than when playing other games.
“Identifying potential markets of harm within player game sessions is a core area of focus for Future Anthem,” said Chris Conroy, chief data officer at Future Anthem.
“We are delighted to have undertaken this research with Gamesys to begin to explore the potential for linkages with the games themselves.”
“We look forward to undertaking future research on games and game design to help build a body of data led evidence in this key area.”