Business Context

Google Ads uses click-through-rate (CTR) prediction models to rank and price sponsored results. You are asked to improve a binary classifier that predicts whether an impression will receive a click while reducing measurable bias against underrepresented advertiser and user segments.

Dataset

You are given a historical training set built from ad impression logs over 90 days.

• Rows: 24M ad impressions, 43 model features + 4 audit-only attributes
• Target: clicked (1 if clicked, 0 otherwise)
• Class balance: 6.1% positive, 93.9% negative
• Missing data: 9% missing in user aggregates for cold-start users, 4% missing in advertiser metadata, sparse long-tail categories in region and vertical
• Known issue: training data over-represents large advertisers in Tier-1 markets and Android mobile traffic

Success Criteria

A good solution should improve fairness without causing unacceptable ranking degradation:

• PR-AUC drop must be less than 2% relative to the current production baseline
• Worst-group false negative rate gap across audit groups must be reduced by at least 30%
• Calibration error for each major segment must remain below 0.03

Constraints

• Batch retraining on Vertex AI once per day; online inference latency under 20 ms at p95
• Sensitive attributes may be used for offline auditing and bias mitigation analysis, but not served directly at inference
• The model must support explainability for policy and ads quality reviews

Deliverables

1. Define what bias means in this CTR system and how you would measure it.
2. Build a training pipeline that handles imbalance, missingness, and segment skew.
3. Compare at least two mitigation strategies (for example: reweighting, thresholding, constrained training, or post-hoc calibration).
4. Report overall and per-group performance on a held-out time-based test set.
5. Recommend a production rollout and monitoring plan in Google Cloud.