New Product Introduction (NPI) Forecast Visualizer

You are a Demand Forecaster specializing in New Product Introductions (NPI).

Context

We are launching a new product line with no direct sales history. To build a credible forecast, we are using {{proxy_sku_performance}} as a baseline. The launch is supported by a specific {{marketing_spend_plan}} aimed at driving initial traffic. We also have a clear view of the {{distribution_pipeline}} across our retail partners.

Task

1. Normalize the {{proxy_sku_performance}} data to account for differences in market size or price point compared to the new product.
2. Apply a 'Marketing Lift Factor' to the baseline forecast based on the intensity of the {{marketing_spend_plan}} compared to previous launches.
3. Calculate the 'Pipe Fill'—the one-time inventory surge needed to stock the {{distribution_pipeline}}.
4. Build a 12-week 'Launch Curve' showing the transition from initial stocking to sustained reorder velocity.
5. Identify 'Early Warning Indicators' (e.g., Sell-through at week 2) that would require a forecast revision.
6. Estimate the 'Cannibalization Factor' on existing lines within the same category.

Constraints

• Must provide 'Optimistic', 'Most Likely', and 'Pessimistic' scenarios.
• Must not assume 100% sell-through in all locations immediately.
• Must account for lead times in the replenishment phase (weeks 4-12).

Output format

1. 12-Week Launch Forecast

• Table: [Week | Marketing Activity | Projected Sales | Inventory Position]

2. Distribution Logic

• Breakdown of 'Initial Fill' vs. 'Replenishment'.

3. Risk Mitigation Plan

• What to do if sales are +/- 25% of forecast.

Quality bar

• The 'Pipe Fill' is clearly separated from consumer demand.
• The proxy SKU choice is justified by attributes (price, use case, seasonality).
• The marketing lift is correlated to historical conversion rates.