On-Time Last Mile Delivery : Order Assignment with Travel Time Predictors

We study how delivery data can be applied to improve the on-time performance of last mile delivery services. Motivated by the delivery operations and data of a food delivery service provider, we discuss a framework that integrates the travel time predictors with the order assignment optimization. Such integration enables us to capture the driver's routing behavior in practice, where the driver's decision-making process is often unobservable or intricate to model. Focusing on the order assignment problem as an example, we discuss the classes of tractable predictors and prediction models that are highly compatible with the existing stochastic and robust optimization tools. We further provide reformulations of the integrated models, which can be efficiently solved with the proposed branch-and-price algorithm. Moreover, we propose two simple heuristics for the multiperiod order assignment problem, which are built upon the single-period solutions. Using the delivery data, our numerical experiments on a real-world application not only demonstrate the superior performance of our proposed order assignment models with travel time predictors, but also highlight the importance of learning the behavioral aspects from the operational data. We find that large sample size does not necessarily compensate for the misspecification of the driver's routing behavior