APPARATUS AND METHOD FOR PREDICTING COMMERCIAL PARTS DISCONTINUANCE USING ARTIFICIAL NEURAL NETWORK

摘要

The present invention relates to a method and apparatus for predicting component discontinuity using an artificial neural network, and the method for predicting part discontinuity using an artificial neural network according to an embodiment of the present invention identifies a target part in a commercial parts database, and uses a web crawler. a data collection step of collecting discontinuance information of parts using a data integration step of integrating information of parts collected through the data collection step; A data pre-processing step of processing and pre-processing the integrated part data to enable learning and prediction with an artificial neural network; a predictive model construction step of inputting vectorized data through the data pre-processing step into an artificial neural network and outputting predictive discontinuance information of parts; and a predictive model performance verification step of setting a performance criterion of the predictive model based on descriptive statistics, and verifying the performance of the predictive model by comparing whether the output prediction discontinuation information meets the set performance criterion.