Automobile spare part demand prediction system based on multi-model optimization selection

Abstract

The embodiment of the invention discloses an automobile spare part demand prediction system based on multi-model optimization selection, and relates to the technical field of data prediction. The system comprises a model training module; the threshold value determination module is used for finally averaging to obtain an average error evaluation index value of all the automobile spare parts under each candidate threshold value; determining a final threshold value according to the change condition of the average error evaluation index value; the model optimization module is used for determining the prediction model corresponding to the minimum error evaluation index value to carry out demand quantity prediction if the difference value corresponding to the same automobile spare parts is greater than or equal to a final threshold value, and obtaining a prediction value; and if the difference value corresponding to the same kind of automobile spare parts is smaller than a final threshold value, at least two prediction models for predicting the demand quantity of the same kind of automobile spare parts are determined for demand quantity prediction, and an average prediction value is obtained. According to the embodiment of the invention, the optimal model or combination is scientifically and reasonably selected from the plurality of prediction models, so that an accurate prediction result is obtained.

Description

technical field [0001] Embodiments of the present invention relate to electrical digital processing technology, and in particular to a demand forecasting system for auto spare parts based on multi-model optimization. Background technique [0002] Automobile spare parts demand forecast, that is, an estimate of the future demand for automobile spare parts. By predicting customers' demand for spare parts in a certain period of time in the future, car companies can purchase raw materials in advance, arrange production activities, and set reasonable inventory levels. Automobile spare parts are upgraded frequently, and there are tens of thousands of spare parts units at every turn. The supply chain is facing severe cost and inventory challenges. The accuracy of spare part demand forecasting directly affects the supply chain cost and customer satisfaction of auto companies. [0003] Automobile spare parts demand forecasting is generally based on past historical data, using various...

AI Technical Summary

Problems solved by technology

Existing methods generally choose a mature model for prediction, which makes the prediction result heavily dependent on the accuracy of the model, thus affecting the accuracy of the prediction

Images