Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
This addresses forecasting for cumulative data in industrial decision-making, but it is incremental as it builds on neural ODEs to handle specific data characteristics.
The authors tackled time-series forecasting for cumulative data by proposing Monotonic neural Ordinary Differential Equation (MODE), which outperformed state-of-the-art methods in experiments on a bonus allocation scenario.
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.