Business forecasting using hybrid approach: A new forecasting method using deep learning and time series

Business forecasting generally employs machine learning methods for longer and nonlinear use cases and econometrics approaches for linear trends. Pasi Helenius and Larry Orimoloye outline a hybrid approach that combines deep learning and econometrics. This method is particularly useful in areas such as competitive event (CE) forecasting (e.g., in sports events political events).

Machine learning methods are becoming increasingly popular among mainstream forecasting practitioners, due to their ability to obtain better accuracy when the forecast horizon is much longer and nonlinear. While this is true, an econometrics approach allows more transparency and formal standard to verify forecasts with better performance for linear trends. Pasi Helenius and Larry Orimoloye outline a hybrid approach that combines deep learning and econometrics. This method is particularly useful in areas such as competitive event (CE) forecasting (e.g., in sports events political events).