Forecasting
AuraScore 81/100

Perishable Inventory Depletion and Spoilage Risk Matrix

Model depletion velocity and spoilage risk for perishable retail consumer goods.

Use this template to balance short-shelf-life retail replenishment against weather patterns and foot-traffic volatility. It delivers a structured inventory matrix highlighting high-risk expiration cohorts and store-level reorder quantities.

Template

Role: Principal Supply Chain Data Scientist specializing in grocery and perishable fast-moving consumer goods.

Context

  • Store network footprint: {{store_network}}
  • Perishable category lines: {{perishable_categories}}
  • Product shelf-life duration: {{shelf_life_window}}
  • Maximum shrink tolerance: {{shrink_rate_target}}
  • Expected weather variations: {{weather_volatility}}
  • Replenishment cycle frequency: {{replenishment_frequency}}

Task

Develop an operational perishable depletion and spoilage forecast matrix that establishes store-level daily consumption rates, flags expiration vulnerability, and prescribes adjusted reorder batches to maintain freshness within target shrink boundaries.

Method

  1. Segment {{perishable_categories}} into discrete shelf-life buckets using parameters in {{shelf_life_window}}.
  2. Correlate local foot traffic shifts across {{store_network}} with anticipated micro-climate disruptions in {{weather_volatility}}.
  3. Calculate baseline daily consumption curves for each product line under normalized demand conditions.
  4. Apply volatility multipliers to calculate worst-case and expected-case expiration volumes prior to sale.
  5. Benchmark calculated waste projections against the target threshold defined in {{shrink_rate_target}}.
  6. Determine optimal replenishment batch sizes aligned with delivery intervals specified in {{replenishment_frequency}}.
  7. Define targeted markdown intervention points where aged stock must be discounted to avoid total write-off.

Constraints

  • MUST present daily sales trajectories across a 7-day rolling window.
  • MUST flag any category exceeding the shrink threshold specified in {{shrink_rate_target}}.
  • MUST NOT recommend order frequencies that conflict with {{replenishment_frequency}}.
  • Avoid speculative supply chain alterations outside the provided {{store_network}}.

Output format

Structure the deliverable as follows:

  1. Network Freshness Overview (1 paragraph, max 120 words).
  2. Spoilage and Depletion Matrix (markdown table with columns: Category, Store Tier, Daily Depletion Rate, Spoilage Risk Index [Low/Med/High], Target Reorder Qty, Markdown Day Trigger, Expected Shrink %).
  3. Tactical Fulfillment Directives (numbered list, exactly 5 actionable steps).

Self-review

  • Confirm that every perishable line in {{perishable_categories}} is evaluated.
  • Ensure markdown day triggers fall within the boundaries of {{shelf_life_window}}.
  • Verify all recommended safety stock limits preserve the {{shrink_rate_target}} ceiling.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-forecasting
retail-consumer-goods
perishables
fmcg
spoilage-risk