Spencer Murch
@spencermurch.bsky.social
Cognitive psychologist focused on addictive digital products.
Postdoc @ UCalgary
Sessional @ UBC-O
Formerly @ Concordia + UBC-V
SpencerMurch.com
Postdoc @ UCalgary
Sessional @ UBC-O
Formerly @ Concordia + UBC-V
SpencerMurch.com
In turn, these subgroups within the moderate-risk range varied on the specific items endorsed and several sociodemographic dimensions.
This kind of within-groups variability is exactly why a ML classifier might fail to perform optimally.
This kind of within-groups variability is exactly why a ML classifier might fail to perform optimally.
May 8, 2025 at 3:36 PM
In turn, these subgroups within the moderate-risk range varied on the specific items endorsed and several sociodemographic dimensions.
This kind of within-groups variability is exactly why a ML classifier might fail to perform optimally.
This kind of within-groups variability is exactly why a ML classifier might fail to perform optimally.
We found that possibly episodic cases (62% of sample) reported several different problems mainly occurring just sometimes, while specific problem cases (9%) reported significantly fewer problems that occurred more frequently.
May 8, 2025 at 3:36 PM
We found that possibly episodic cases (62% of sample) reported several different problems mainly occurring just sometimes, while specific problem cases (9%) reported significantly fewer problems that occurred more frequently.
We interpreted these groups as exhibiting "possibly episodic" gambling, "intermediate cases" of responding, and "specific problems", respectively.
May 8, 2025 at 3:36 PM
We interpreted these groups as exhibiting "possibly episodic" gambling, "intermediate cases" of responding, and "specific problems", respectively.
🎉🧵 New Paper Thread 🎉🧵
Machine Learning models that aim to detect at-risk online gamblers seem to hit a performance ceiling, and exhibit serious imprecision when making positive-class predictions.
WHY?
Maybe it's the outcome variable, the Problem Gambling Severity Index.
Machine Learning models that aim to detect at-risk online gamblers seem to hit a performance ceiling, and exhibit serious imprecision when making positive-class predictions.
WHY?
Maybe it's the outcome variable, the Problem Gambling Severity Index.
May 8, 2025 at 3:36 PM
🎉🧵 New Paper Thread 🎉🧵
Machine Learning models that aim to detect at-risk online gamblers seem to hit a performance ceiling, and exhibit serious imprecision when making positive-class predictions.
WHY?
Maybe it's the outcome variable, the Problem Gambling Severity Index.
Machine Learning models that aim to detect at-risk online gamblers seem to hit a performance ceiling, and exhibit serious imprecision when making positive-class predictions.
WHY?
Maybe it's the outcome variable, the Problem Gambling Severity Index.