Fostering Trust via Explainable ML Inferences
summary
Claims a practical, quantifiable game‑theory framework that turns explainable inferences into measurable trust: use feature ablation (remove fields to see confidence shifts) to produce explanations, track per‑customer metrics (crashes, bias reports with severity) as initial value V and remittance p, model perceived gain with a magnification K and feedback q, and plot trust over iterations. Simulations show trust grows when K>1 and erodes when K≤1; operational steps are metric selection, automated feedback, retraining and plotting trust curves.
AI-written summary · about
chapters (6)
- 0:00Start
- 5:17Game Theory
- 20:41Adding Value
- 23:56Causing Inefficiencies
- 24:31Rapid Erosion of Trust
- 26:49Trust Over Time
related talks
24mWhy and How to Build Explainability into your ML Workflow
16mBuilding Trust through Explainable AI
31mMeasurement of Trust in AI
35mWhy Do You Need an Explainable Ai?
26mUsing Explainable AI to garner trust and overcome adoption inhibitors
02h 01mFostering Trust in AI-Driven Finance
01h 29mNavigating ML Explainability: From Theory to Implementation
16mTrust by Design: Building Reliable AI for Sensitive Environments