XRMDN: An Extended Recurrent Mixture Density Network for Short-Term Probabilistic Rider Demand Forecasting with High Volatility

TL;DR

This paper introduces XRMDN, a deep learning model that improves short-term probabilistic rider demand forecasts in high-volatility MoD systems by capturing demand uncertainty and volatility more effectively.

Contribution

The paper presents XRMDN, a novel recurrent mixture density network architecture that incorporates endogenous and exogenous factors to enhance demand forecasting accuracy in volatile environments.

Findings

XRMDN outperforms benchmark models in real-world datasets.

It significantly improves forecast accuracy during high-demand volatility periods.

The model effectively captures demand uncertainty and volatility.

Abstract

In the realm of Mobility-on-Demand (MoD) systems, the forecasting of rider demand is a cornerstone for operational decision-making and system optimization. Traditional forecasting methodologies primarily yield point estimates, thereby neglecting the inherent uncertainty within demand projections. Moreover, MoD demand levels are profoundly influenced by both endogenous and exogenous factors, leading to high and dynamic volatility. This volatility significantly undermines the efficacy of conventional time series forecasting methods. In response, we propose an Extended Recurrent Mixture Density Network (XRMDN), a novel deep learning framework engineered to address these challenges. XRMDN leverages a sophisticated architecture to process demand residuals and variance through correlated modules, allowing for the flexible incorporation of endogenous and exogenous data. This architecture, featuring recurrent connections within the weight, mean, and variance neural networks, adeptly captures demand trends, thus significantly enhancing forecasting precision, particularly in high-volatility scenarios. Our comprehensive experimental analysis, utilizing real-world MoD datasets, demonstrates that XRMDN surpasses the existing benchmark models across various metrics, notably excelling in high-demand volatility contexts. This advancement in probabilistic demand forecasting marks a significant contribution to the field, offering a robust tool for enhancing operational efficiency and customer satisfaction in MoD systems.