NorthRiver Manufacturing operates 1,200 industrial pumps across 18 plants. Unplanned pump failures cause expensive production downtime, so the maintenance team wants a model that predicts whether a machine will fail within the next 7 days using recent telemetry and maintenance history.
You are given one row per machine-day, built from rolling aggregates over raw sensor streams.
| Feature Group | Count | Examples |
|---|---|---|
| Sensor aggregates | 18 | vibration_mean_24h, temp_max_24h, pressure_std_7d, rpm_mean_24h |
| Trend features | 10 | vibration_slope_3d, temp_delta_7d, pressure_change_rate |
| Maintenance history | 6 | days_since_last_service, service_count_90d, replaced_part_flag |
| Machine metadata | 5 | model_type, plant_id, machine_age_days, manufacturer |
| Operating context | 7 | load_pct_mean_24h, ambient_temp, shift_type, runtime_hours_7d |
A good solution should identify at least 75% of upcoming failures while keeping precision above 35%, and provide ranked risk scores that maintenance planners can use for daily scheduling.