Intermittent Demand Forecasting with Deep Renewal Processes
This addresses a common and challenging forecasting problem in domains like inventory management, but appears incremental as it builds on existing deep temporal point process paradigms.
The paper tackled the problem of intermittent demand forecasting by connecting renewal processes with existing models and developing new models using recurrent neural networks to parameterize conditional interdemand time and size distributions. It reported favorable empirical findings on discrete and continuous time data, validating the practical value of the approach.
Intermittent demand, where demand occurrences appear sporadically in time, is a common and challenging problem in forecasting. In this paper, we first make the connections between renewal processes, and a collection of current models used for intermittent demand forecasting. We then develop a set of models that benefit from recurrent neural networks to parameterize conditional interdemand time and size distributions, building on the latest paradigm in "deep" temporal point processes. We present favorable empirical findings on discrete and continuous time intermittent demand data, validating the practical value of our approach.