A Two-Level Plackett-Luce Model for preference modeling in smart mobility platforms

TL;DR

This paper presents a novel two-level Plackett-Luce model with Bayesian inference for personalized route choice in smart mobility platforms, demonstrated through practical use cases.

Contribution

It introduces a new two-level Plackett-Luce model combined with a multinomial logistic scheme for preference modeling in smart mobility.

Findings

Model effectively captures consumer preferences for route recommendations.

Empirical testing shows the model's applicability and potential for refinement.

Use cases demonstrate practical relevance in route selection and car pooling.

Abstract

The Plackett-Luce model is widely used to deal with probabilities in discrete choice settings. This paper introduces a novel two-level Plackett-Luce model combined with a multinomial logistic scheme that provides the basis for the route choice module in a smart mobility platform. For this, we develop Bayesian inference and prediction mechanisms to capture consumers' preferences for personalized route recommendations. The model is empirically tested, allowing for refinements and discussion of its applicability. We also illustrate its practical relevance through several use cases, including relevant route selection, coordinated car pooling, incentive design and synthetic data generation.