About Prompt
- Prompt Type – Dynamic
- Prompt Platform – ChatGPT, Grok, Deepseek, Gemini, Copilot, Midjourney, Meta AI and more
- Niche – Demand-Driven Procurement
- Language – English
- Category – Supply Chain Forecasting
- Prompt Title – AI Prompt for Forecasting Raw Material Needs Based on Production Trends
Prompt Details
**Prompt Type:** Dynamic
**Purpose:** Supply Chain Forecasting – Raw Material Needs Prediction
**Target AI Platform:** All
**Instructions:**
This prompt aims to forecast raw material needs based on real-time production trends within a demand-driven procurement model. You will receive dynamic input data and are expected to generate a detailed forecast of required raw materials.
**Input Data Format:**
The input data will be provided in JSON format, containing the following key-value pairs:
* `”historical_demand”`: An array of historical demand data points, each representing a specific time period (e.g., daily, weekly, monthly). Each data point is a dictionary with:
* `”date”`: Date of the demand data point (ISO 8601 format, YYYY-MM-DD).
* `”quantity”`: The quantity of finished goods demanded during that period.
* `”current_demand”`: An array of recent demand data points (e.g., last week’s daily demand) with the same structure as `historical_demand`.
* `”lead_time”`: The average lead time for procuring each raw material (in days). This can be a single number or a dictionary with material names as keys and lead times as values.
* `”bill_of_materials”`: A dictionary where keys are finished product names and values are dictionaries representing their bill of materials. Each BOM dictionary has raw material names as keys and their required quantity per finished good as values.
* `”current_inventory”`: A dictionary where keys are raw material names and values are their current inventory levels.
* `”safety_stock_level”`: A dictionary specifying the desired safety stock level for each raw material. This can be expressed as a percentage of the forecasted demand or as a fixed quantity.
* `”forecast_horizon”`: The time period for which the forecast is required (e.g., “3 months”, “5 weeks”, “90 days”).
* `”seasonality_factors”`: (Optional) An array of seasonality multipliers. For example, if demand typically increases by 20% in December, the December multiplier would be 1.2. If no seasonality is applicable, omit this field or provide an array of 1.0 values.
* `”external_factors”`: (Optional) A dictionary of external factors that might influence demand. This could include things like planned promotions, economic indicators, or competitor activity. Describe each factor briefly and quantify its potential impact if possible (e.g., `{“promotion”: “Expected 15% increase in demand during promotional period from YYYY-MM-DD to YYYY-MM-DD”}`).
**Output Data Format:**
The output should be a JSON object containing:
* `”forecasted_demand”`: An array of forecasted demand for finished goods for each period within the `forecast_horizon`, using the same structure as the input demand data.
* `”raw_material_needs”`: A dictionary where keys are raw material names and values are arrays of their forecasted needs for each period within the `forecast_horizon`. Each element in the array should be a dictionary with:
* `”date”`: The date for which the need is forecasted (ISO 8601 format).
* `”quantity”`: The forecasted quantity of the raw material needed.
* `”reorder_points”`: A dictionary where keys are raw material names and values are the calculated reorder points based on lead time, forecasted demand, and safety stock.
* `”potential_stockouts”`: An array of potential stockouts identified based on current inventory, forecasted needs, and lead times. Each element should be a dictionary with:
* `”material”`: The name of the material potentially facing a stockout.
* `”date”`: The date the stockout is predicted to occur.
* `”confidence_level”`: An optional field expressing the confidence level of the forecast (e.g., “high”, “medium”, “low”, or a numerical probability between 0 and 1).
**Prompt Example:**
“`json
{
// … (Input data in JSON format as described above)
}
“`
**Detailed Instructions:**
1. Analyze historical and current demand data to identify trends and patterns.
2. Consider lead times, bill of materials, current inventory, safety stock levels, seasonality factors (if provided), and external factors (if provided) to forecast raw material needs accurately.
3. Calculate reorder points for each raw material to ensure timely procurement.
4. Identify potential stockouts and alert the user.
5. Provide a confidence level for the forecast if possible.
**Note:**
This prompt is designed to be dynamic, allowing for various input data structures and forecast horizons. Adapt your forecasting methodology based on the provided data. Prioritize accuracy and clarity in your response. Aim to provide actionable insights for demand-driven procurement decisions. If certain data is missing or unclear, explain the assumptions made and their potential impact on the forecast.