Supply Lead Time Prediction Model Using Price Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Companies face challenges in predicting lead times for parts from suppliers due to price fluctuations and varying component ratios, which affects the supply chain and production planning.
Innovation Solution
A method for generating a supply lead time prediction model that involves receiving input data for a final part, obtaining historical price and lead time data for component parts, preprocessing this data, and using it to train a model for predicting lead times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If companies use traditional methods to predict lead times without considering price fluctuations and component ratios, then the prediction process is simple, but the prediction accuracy deteriorates
Solution Approach 1:
The patent applies parameter changes by incorporating price data and component ratios as additional input parameters into the lead time prediction model. The model processes multiple parameters including historical lead times, current prices, and component compositions to dynamically adjust predictions, thereby improving accuracy while managing complexity through structured data processing
Solution Approach 2:
The patent segments the lead time prediction problem into multiple independent components: historical lead time analysis, price fluctuation analysis, and component ratio analysis. Each segment is processed separately and then integrated to form the final prediction, making the complex problem more manageable and accurate
2Measurement precision
If companies collect and process multiple types of data (price data, historical lead time data) for prediction, then the prediction accuracy improves, but the data processing complexity increases
Solution Approach 1:
The patent applies preliminary action by collecting and organizing price data and historical lead time data before the actual prediction process. The system pre-processes this data to establish relationships between price fluctuations, component ratios, and lead times, creating a ready-to-use knowledge base that simplifies the real-time prediction process
Solution Approach 2:
The patent uses an intermediary processing layer that transforms raw price and historical data into meaningful features for prediction. This intermediary process includes data cleaning, normalization, and feature extraction, which bridges the gap between raw data collection and final prediction, reducing overall system complexity
3Productivity
If companies use a prediction model that considers price fluctuations of component parts, then the supply chain optimization improves, but the computational time increases
Solution Approach 1:
The patent applies partial action by focusing the prediction model on the most influential factors affecting lead time, such as price fluctuations of critical component parts. Rather than analyzing all possible variables, the model selectively processes key parameters that have the greatest impact on supply chain optimization, reducing computational time while maintaining productivity benefits
Data Source
AI summary
Provided is a method for generating a lead time prediction model including: receiving input data for a final part from a user, wherein the final part is composed of one or more component parts; obtaining a first data for each of the one or more component parts, wherein the first data includes at least price data and historical lead time data; performing preprocessing on the first data to generate second data; and generating a model for generating a predicted lead time for at least one of the final part and the one or more component parts by performing learning using the second data as a training dataset.