순환신경망(RNN) 기반 자동차 A/S 서비스 센터 수리 부품 수요 예측 모델 연구

Abstract

The purpose of this study is to identify the demand pattern categorization of repair parts of Automotive after-sales service(A/S) and proposes a demand prediction model for Auto repair parts using Recurrent neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the SimpleRNN, LSTM, GRU and ARIMA model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV2) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. Lumpy demand pattern’s repair parts in the last five years is predicted by applying them to the SimpleRNN, LSTM GRU and ARIMA for daily, weekly, and monthly time-series data. the model prediction performance evaluation index, MAPE(%), RMSE, and RMSLE that can measure the error between the actual and the prediction value. As the result of this study, Daily time-series data with LSTM, GRU were excellently predicted and the indicators is the lowest MAPE(%), RMSE, and RMSLE followed by Weekly and Monthly time-series data. This is due to the volume of training data for Weekly and Monthly. even if the demand period is extended to get the more training data, the prediction performance is still low due to the discontinuation of current parts and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.