Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale
This work addresses forecasting challenges for e-commerce platforms dealing with intermittent demand, but it is incremental as it builds on existing state space models with a focus on scalability.
The paper tackles demand forecasting for intermittent and bursty sales in e-commerce by developing a scalable Bayesian inference method for linear state space models, achieving improved performance over competing approaches on large real-world datasets for fast and medium moving items.
We present a scalable and robust Bayesian inference method for linear state space models. The method is applied to demand forecasting in the context of a large e-commerce platform, paying special attention to intermittent and bursty target statistics. Inference is approximated by the Newton-Raphson algorithm, reduced to linear-time Kalman smoothing, which allows us to operate on several orders of magnitude larger problems than previous related work. In a study on large real-world sales datasets, our method outperforms competing approaches on fast and medium moving items.