Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data

TL;DR

This paper introduces MODE, a neural ODE-based method designed to improve time-series forecasting of cumulative data by explicitly modeling its monotonicity and irregularity, leading to better practical performance.

Contribution

The paper presents a novel neural ODE approach called MODE that effectively captures monotonicity and irregularity in cumulative time-series data, addressing limitations of existing methods.

Findings

MODE outperforms state-of-the-art methods in experiments

Effectively models monotonicity and irregularity in cumulative data

Demonstrates superior forecasting accuracy in industrial scenarios

Abstract

Time-Series Forecasting based on Cumulative Data (TSFCD) is a crucial problem in decision-making across various industrial scenarios. However, existing time-series forecasting methods often overlook two important characteristics of cumulative data, namely monotonicity and irregularity, which limit their practical applicability. To address this limitation, we propose a principled approach called Monotonic neural Ordinary Differential Equation (MODE) within the framework of neural ordinary differential equations. By leveraging MODE, we are able to effectively capture and represent the monotonicity and irregularity in practical cumulative data. Through extensive experiments conducted in a bonus allocation scenario, we demonstrate that MODE outperforms state-of-the-art methods, showcasing its ability to handle both monotonicity and irregularity in cumulative data and delivering superior forecasting performance.