Neural Multi-Quantile Forecasting for Optimal Inventory Management

TL;DR

This paper introduces a neural multi-quantile forecasting model using dilated recurrent neural networks with temporal scaling, demonstrating improved inventory management predictions over traditional statistical models on a large sales dataset.

Contribution

The paper presents a novel neural network architecture combining quantile regression and temporal scaling for multi-horizon forecasting in inventory management.

Findings

Up to 3.2% better performance than statistical benchmarks

6% improvement over non-scaled neural models

Validated on 10,000 sales time series over 53 weeks

Abstract

In this work we propose the use of quantile regression and dilated recurrent neural networks with temporal scaling (MQ-DRNN-s) and apply it to the inventory management task. This model showed a better performance of up to 3.2\% over a statistical benchmark (the quantile autoregressive model with exogenous variables, QAR-X), being better than the MQ-DRNN without temporal scaling by 6\%. The above on a set of 10,000 time series of sales of El Globo over a 53-week horizon using rolling windows of 7-day ahead each week.