Repository Docs & Knowledge Base

id: 019cb9fd-149e-7d94-bab1-caa9edbcb1d2 name: Large Order Wave Monitor kind: Anomaly cron: 0 0 * * * * analysis_window: 1h comparison_periods: [1d, 7d]

Detect periods when orders consistently contain an unusually high number of items, indicating large tables or group orders that strain kitchen capacity.

Known Tables & Columns

curated.kitchen_orders

• guid (varchar, PK) - order identifier
• store_guid (varchar) - which store/restaurant
• items_count (int) - number of items in the order
• order_type (varchar) - DINE_IN, TO_GO, DELIVERY
• guest_table (varchar) - table identifier (e.g., T1-T24)
• server_name (varchar) - server who took the order
• done (tinyint) - whether the order is complete
• is_deleted (tinyint) - soft delete flag
• create_time (int, unix timestamp) - when the order was created
• preparation_time (int, seconds, nullable) - total order preparation time

Analysis Approach

1. Query all orders created in the last {AnalysisWindow} from curated.kitchen_orders (is_deleted=0).
2. Verify that each 15-minute window contains at least 15 orders. Ignore windows with fewer data points.
3. Group by 15-minute windows and compute the average items_count per window.
4. Compare against the historical baseline (same time windows {ComparisonPeriods}). Normal orders typically have 1-4 items depending on time of day; lunch/dinner peaks average 3-4 items.
5. Flag windows where the average items_count is significantly elevated -- specifically, look for sustained periods (3+ consecutive windows) where most orders have 6-10 items.
6. Also compute the percentage of large orders (items_count >= 6) in each window. Under normal conditions this should be rare (<10%); during an anomaly it will be the majority.
7. Check the downstream impact: do these large orders correlate with increased overall prep times or a growing backlog?

Baseline Reference

Normal item counts by time of day:

• Off-peak (late night, early morning): 1-2 items average
• Moderate (mid-morning, afternoon): 2-3 items average
• Peak (lunch 12-14, dinner 18-20): 3-4 items average

Anomalous: sustained 6-10 items per order across multiple consecutive windows.

Severity Guidance

• Low: Average items_count 2.5x above baseline sustained for 3+ consecutive windows
• Medium: Average items_count 3x above baseline sustained for 3+ windows, with visible kitchen impact
• High: Average items_count 3x+ above baseline sustained over 15+ minutes, kitchen clearly overwhelmed