Forecasting of Non-Stationary Sales Time Series Using Deep Learning
This addresses forecasting challenges for sales data with time trends, but appears incremental as it adds a specific correction to existing neural network methods.
The paper tackled forecasting non-stationary sales time series by incorporating a time trend correction block into a deep learning model, resulting in essentially improved forecasting accuracy.
The paper describes the deep learning approach for forecasting non-stationary time series with using time trend correction in a neural network model. Along with the layers for predicting sales values, the neural network model includes a subnetwork block for the prediction weight for a time trend term which is added to a predicted sales value. The time trend term is considered as a product of the predicted weight value and normalized time value. The results show that the forecasting accuracy can be essentially improved for non-stationary sales with time trends using the trend correction block in the deep learning model.