NorthRiver Manufacturing operates 1,200 industrial pumps across 18 plants and wants to predict whether a machine will fail within the next 7 days so maintenance can be scheduled before unplanned downtime occurs. False negatives are costly because a missed failure can stop a production line, but too many false positives create unnecessary maintenance work.
You are given a historical predictive maintenance dataset built from sensor readings, maintenance logs, and machine metadata.
| Feature Group | Count | Examples |
|---|---|---|
| Sensor aggregates | 18 | temperature_mean_24h, vibration_std_6h, pressure_max_12h, current_draw_trend |
| Operating context | 7 | load_pct, ambient_temp, shift_type, runtime_hours |
| Maintenance history | 6 | days_since_last_service, parts_replaced_90d, prior_failures_12m |
| Asset metadata | 5 | machine_type, manufacturer, install_age_days, plant_id |
| Derived trend features | 8 | rolling_slope_vibration_3d, temp_to_load_ratio, anomaly_count_24h |
A strong solution should achieve recall >= 0.80 on failure events while keeping precision >= 0.35 and PR-AUC >= 0.40 on a held-out time-based test set. The candidate should explain how model complexity affects underfitting vs overfitting in this maintenance setting.