Model Metric Dashboard
Internal ML governance dashboard tracking train/test MAPE, MAE, RMSE, and classification metrics across all deployed platform models.
Akash Sharma
Primary Owner
20+
Models Monitored
Overview
Built an internal dashboard tracking MAPE, wMAPE, MAE, RMSE, F1, PR-AUC, and classification metrics per model per scoring run. Provides longitudinal view of model health across the full platform.
The problem
With 20+ models in production, there was no systematic way to detect model degradation, validate retraining, or monitor performance drift over time.
Results
Enabled early detection of model degradation and provided evidence for retraining decisions across 20+ production ML models.
Related Platform & Infrastructure Projects
ML Regression Framework
Reusable ML regression framework standardizing feature engineering, training, validation, and scoring, adopted as the baseline for all subsequent platform models.