Data-Driven Stochastic VRP: Integration of Forecast Duration into Optimization for Utility Workforce Management

TL;DR

This paper presents a novel approach that integrates machine learning forecasts of intervention durations into a stochastic vehicle routing problem, improving operational efficiency in utility workforce management.

Contribution

It introduces a method combining gradient boosting predictions with risk-aware multi-objective optimization for stochastic routing problems.

Findings

20-25% improvement in operator utilization and completion rates

Validation of sub-Gaussian residuals supports the risk model

Framework effectively manages uncertainty in real-world routing

Abstract

This paper investigates the integration of machine learning forecasts of intervention durations into a stochastic variant of the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW). In particular, we exploit tree-based gradient boosting (XGBoost) trained on eight years of gas meter maintenance data to produce point predictions and uncertainty estimates, which then drive a multi-objective evolutionary optimization routine. The methodology addresses uncertainty through sub-Gaussian concentration bounds for route-level risk buffers and explicitly accounts for competing operational KPIs through a multi-objective formulation. Empirical analysis of prediction residuals validates the sub-Gaussian assumption underlying the risk model. From an empirical point of view, our results report improvements around 20-25\% in operator utilization and completion rates compared with plans computed using default durations. The integration of uncertainty quantification and risk-aware optimization provides a practical framework for handling stochastic service durations in real-world routing applications.