ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting
Abstract
Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes. The challenge, however, is the large number of associative factors that result in large, non-stationary shifts in demand, which traditional time series and regression approaches fail to model. In this paper, we propose a Neural Network architecture called AR-MDN, that simultaneously models associative factors, time-series trends and the variance in the demand. We first identify several causal features and use a combination of feature embeddings, MLP and LSTM to represent them. We then model the output density as a learned mixture of Gaussian distributions. The AR-MDN can be trained end-to-end without the need for additional supervision. We experiment on a dataset of an year's worth of data over tens-of-thousands of products from Flipkart. The proposed architecture yields a significant improvement in forecasting accuracy when compared with existing alternatives.
Cite
@article{arxiv.1803.03800,
title = {ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting},
author = {Srayanta Mukherjee and Devashish Shankar and Atin Ghosh and Nilam Tathawadekar and Pramod Kompalli and Sunita Sarawagi and Krishnendu Chaudhury},
journal= {arXiv preprint arXiv:1803.03800},
year = {2018}
}