---
type: method
slug: demand-forecasting
title: "Forecast product demand"
category: "Operations, Supply Chain & Manufacturing"
subcategory: "Supply chain & procurement"
level: intermediate
source: https://deepstoryresearch.com/method/demand-forecasting
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Planning inventory or production.

## Prompt

# Forecast product demand
Method by Deepstory Research: deepstoryresearch.com/method/demand-forecasting

You are a demand planner. Follow the method below step by step. Goal: A demand forecast with method choice, seasonality, accuracy measure and a planning range.

## My inputs
- Sales history: [SALES_HISTORY]  (example: attach monthly by SKU)
- Known events: [KNOWN_EVENTS]  (example: promotions, price changes)
- Horizon: [HORIZON]  (example: next 6 months)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Profile the history: trend, seasonality, outliers.
2. Choose a method (naive, moving average, exponential smoothing, regression) and justify.
3. Backtest and report error (MAPE or WAPE).
4. Produce the forecast with a range.
5. List assumptions and events to overlay.

## Deliver the output in this structure
- Data profile
- Method
- Accuracy
- Forecast table with range
- Assumptions

## Quality rules
- Always show a range, not a single number.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

## Evidence you can attach
- Global Food Prices: https://deepstoryresearch.com/data/food-price-index (AI context file: https://deepstoryresearch.com/context/food-price-index.md)
- E-Commerce Share of US Retail: https://deepstoryresearch.com/data/us-ecommerce-share (AI context file: https://deepstoryresearch.com/context/us-ecommerce-share.md)
- Shipping Chokepoints: https://deepstoryresearch.com/data/shipping-chokepoints (AI context file: https://deepstoryresearch.com/context/shipping-chokepoints.md)
- Battery Pack Prices: https://deepstoryresearch.com/data/battery-pack-prices (AI context file: https://deepstoryresearch.com/context/battery-pack-prices.md)

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.