Why is My Route Different Today? An Algorithm for Explaining Route Selection

2025-06-05

AI Summary

To address users’ demand for explainability—specifically, “Why is this route recommended?”—in navigation services, this work investigates which dynamic traffic conditions cause the traffic-aware shortest path to deviate from the static (traffic-free) baseline path. We introduce the notion of a *Simple and Valid Explanation* (SVE), formally defining the minimal set of traffic conditions sufficient to induce the observed path deviation—ensuring both explanatory conciseness and theoretical soundness. Methodologically, we integrate graph algorithms, path sensitivity analysis, pruning optimization, and counterfactual reasoning to enable efficient SVE computation. Evaluated on real-world road networks, our approach generates highly readable explanations averaging fewer than three segments, with >92% accuracy and sub-200ms response time. Our core contribution is the first theoretically grounded explainability framework for dynamic path divergence, coupled with a practical algorithm that jointly achieves computational efficiency, high fidelity, and human interpretability.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Heuristic Search
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Users of routing services like Apple Maps, Google Maps, and Waze frequently wonder why a given route is proposed. This question particularly arises when dynamic conditions like traffic and road closures cause unusual routes to be proposed. While many dynamic conditions may exist in a road network at any time, only a small fraction of those conditions are typically relevant to a given user's route. In this work, we introduce the concept of a simple valid explanation (SVE), which consists of a small set of traffic-laden road segments that answer the following question: Which traffic conditions cause a particular shortest traffic-aware route to differ from the shortest traffic-free route? We give an efficient algorithm for finding SVEs and show that they theoretically and experimentally lead to small and interpretable answers to the question.

Problem

• Explaining why routing services propose unusual routes
• Identifying relevant traffic conditions affecting route selection
• Providing small, interpretable explanations for route differences

Innovation

• Introduces simple valid explanation (SVE) concept
• Efficient algorithm for finding SVEs
• Explains route differences using traffic conditions