Reusable New Product Planning Model for Demand Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing product planning methods for new product introductions are manual, disparate, and lack a reusable method for predicting demand and allocating resources effectively, leading to inaccurate forecasting and supply chain challenges.
Innovation Solution
A reusable new product planning model that gathers historical demand data, calculates transition percentages, and groups them into averaged ranges to predict the impact of new products on existing products, allowing for accurate production planning and demand allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual spreadsheet tools are used for forecasting, then ease of operation is improved, but measurement precision and reliability deteriorate
Solution Approach 1:
The patent replaces manual spreadsheet-based forecasting processes with an automated machine learning system. The system automatically processes historical demand data, identifies product relationships, and generates forecasts using trained models, eliminating the need for manual calculations while significantly improving forecast accuracy and reliability.
Solution Approach 2:
The system performs self-service by automatically learning from historical data and generating its own forecasts without requiring manual intervention. The machine learning models continuously improve their predictions by processing historical patterns, allowing the system to maintain high measurement precision while remaining easy to operate through automated operations.
2Ease of operation
If trial and error methods are used for new product planning, then ease of operation is improved, but reliability and measurement precision deteriorate
Solution Approach 1:
The system performs preliminary action by pre-processing and analyzing historical demand data to identify product relationships and market patterns before generating forecasts. This preliminary analysis of historical data enables the machine learning models to make reliable predictions about new product introductions and their impact on existing products, eliminating the need for trial and error approaches.
3Ease of operation
If personal prognostications are used for forecasting, then ease of operation is improved, but measurement precision and reliability deteriorate
Solution Approach 1:
The patent replaces personal prognostications with an automated machine learning system that objectively analyzes historical demand data. The system processes quantitative data to identify patterns and relationships, generating precise forecasts without the subjectivity and variability inherent in manual prognostications, thereby significantly improving measurement precision while maintaining ease of operation through automation.
Data Source
AI summary
A method, system, and computer program product for implementing a reusable new product planning model is provided. The method includes gathering historical demand data for products in a product set and determining a launch period for the products, the historical demand data broken down by time periods. For each of the time periods, the method includes determining a transition percentage for each of the products, grouping the transition percentages by respective launch-based time periods, and averaging the transition percentages, resulting in an averaged transition range. The method further includes calculating fast and slow transition ranges for each of the launch-based time periods. The method further includes developing a production plan for a new product by applying one of the transition ranges to the new product before product launch, and allocating a remaining demand percentage to existing products in the product set using the selected transition range and for a corresponding launch-based time period.