Post-Balstm a Bagged Lstm Forecasting Ensemble Embedded with a Postponement Framework to Target the Semiconductor Shortage in the Automotive Industry: An Electronics Manufacturing Services Case Study

•We are the first to predict forecasts and prediction intervals based on deep learning networks in the context of postponement.•The forecast model developed in this research efficiently tackles the semiconductors shortage.•Our forecast model results show that the method outperforms other standard techniques by nearly 43%.•We introduce an interval accuracy measure denominated the Spectrum Fidelity.•Our method improves forecasting accuracy. It can capture nonlinear patterns in time series data.