Norm Staff Planning in Automotive Sector with Artificial Neural Networks

This study proposes an autocorrelated integrated moving average (ARIMA)-enhanced artificial neural network(ANN) model in order to make norm staff forecasts more effectively within the scope of human resources planningin the automotive sector. Accurate and timely determination of labour force requirements is one of the main factorsthat directly affect productivity and cost factors in the sector. Although there are many approaches to norm staffingcalculations in the literature, it is rare to use time series and artificial intelligence based models together. In thisstudy, the data of the past years were analysed with the ARIMA model, which is widely used in time series analysis,to reveal the time series components, and then the estimated workload was evaluated with ANN to predict thefuture personnel needs. The model was trained with 60 periods of historical data and forecasting was performedfor the next 12 periods. According to the results obtained, this combined model outperformed both the classicalARIMA model and the ANN model used alone in performance measures such as root mean square error (RMSE),mean absolute percentage error (MAPE) and coefficient of variance (R2).