Repository Docs & Knowledge Base

id: d2a91f44-6f3a-4c2e-9b7a-91a7e3c5b812 name: Provide pricing recommendations kind: Insight cron: 0 0 /4 * * analysis_window: 60d comparison_periods: [7d, 28d]

Generate context-aware pricing recommendations based on demand patterns, time-based behavior, and item performance to maximize revenue and margin.

Known Tables & Columns

curated.pos_transaction_items

• item (integer) - menu item identifier — references itm.id
• bohname (varchar) - menu item name — for item name join itm on gnditem.item = itm.id and use itm.longname
• price (decimal) - current selling price
• revid (integer) - revenue center identifier — for revenue center name join rev on gnditem.revid = rev.id and use rev.name

curated.pos_catalog_items

• id (integer, PK) - menu item identifier
• longname (varchar) - menu item name
• cost (decimal) - estimated cost of item
• donotshow (varchar) - inactive flag (donotshow = 'Y' means hidden)

curated.pos_transactions

• check (integer, PK) - check identifier
• dob (date) - date of sale
• openhour + openmin (integer, integer) - check open time (reconstruct timestamp)
• revenue (integer) - revenue center identifier — join rev for name
• amount (decimal) - total check value

Analysis Approach

1. Aggregate menu item performance over the last {AnalysisWindow}.

For each item calculate:

• total units sold
• total revenue
• average selling price
• revenue contribution share

1. Identify top-performing and underperforming items:
2. high-demand items (top revenue / volume)
3. low-demand items (low volume or declining trends)

1. Analyze time-based demand patterns:
2. sales by hour of day (peak vs off-peak)
3. sales by day of week
4. detect recurring demand spikes and slow periods

1. Segment performance by revenue center (if applicable):

Identify items that perform differently across locations or service types.

1. Detect pricing opportunities:

• Peak pricing opportunities:

Items with consistently high demand during specific hours or days.

• Off-peak optimization:

Items with weak demand during slow periods.

• Stable high-demand items:

Items with strong volume and consistent demand → candidates for price increases.

• Weak demand items:

Items with low or inconsistent sales → candidates for discounts, promotions, or repositioning.

1. Estimate price sensitivity (proxy-based):
2. Compare demand stability vs price levels (if price variation exists)
3. Assume:
4. stable demand → low sensitivity (pricing power)
5. fluctuating demand → higher sensitivity

1. Detect contextual opportunities:
2. time-based pricing (lunch vs dinner vs late hours)
3. weekday vs weekend pricing
4. revenue center-specific pricing differences

1. Exclude items with fewer than 30 total units sold during the analysis window.

1. Generate recommendations as clear pricing actions, such as:
2. percentage price increases during peak demand
3. off-peak discounts
4. simple dynamic pricing rules
5. location-based price adjustments

Severity Guidance

• Low: Small pricing improvement opportunity (e.g., +3–5% adjustment or minor discount).
• Medium: Noticeable mismatch between demand and pricing requiring adjustment.
• High: Strong pricing inefficiency (e.g., high demand with underpriced item or consistently weak item with no optimization).