{"page":"/blog/explainable-ai-bidding","modified":"2026-11-10","license":"https://creativecommons.org/licenses/by/4.0/","columns":["Request","How it is produced","What it proves","Limits"],"rows":[["1. Global feature importance","Average absolute attribution per feature over many bids","Which inputs the model relies on most","Hides interactions and rare cases"],["2. Per-bid attributions (SHAP-style)","SHAP or LIME run on logged bids","Why this bid was high or low","Needs the model and its exact inputs; costly at scale"],["3. Decision logs","The bidder writes each layer's output per bid","What the system actually did","Only as complete as the fields logged"],["4. Counterfactual tests","Replay logged requests with one input changed","Whether a feature changes bids, without model access","Shows effects, not internal reasons"],["5. Model documentation","A model card: purpose, data window, metrics, limits, update dates","That the vendor knows and states the model's limits","Self-reported; must be checked against logs"]],"sourceUrls":[[],[],[],[],[]]}