An Embarrassingly Simple Rule-based Visiting Circulation Approach to Trip Destination Prediction

2026-07-28

AI Summary

This work proposes a Rule-based Visit Cycle (RVC) approach to predict trip destinations in a target city where no destination label data are available, leveraging only users’ origin characteristics and historical travel behavior. By explicitly modeling origin–destination association rules and revisitation patterns, RVC avoids reliance on complex models or cross-city transfer learning, enabling efficient inference in a zero-label setting. Evaluated in the IEEE Big Data Cup 2022 competition, the method significantly outperformed existing supervised learning and heuristic baselines, securing second place on the leaderboard and demonstrating its effectiveness and novelty for destination prediction under extreme data scarcity.

Abstract

In this paper, we propose the Rule-based Visiting Circulation (RVC) model in tackling the challenge in the IEEE Big Data Cup 2022: Trip Destination Prediction. Given trips containing travel information, personal attributes, origin zones, and their features in the training metropolitan areas, the task is to predict the destination of every trip in a targeted metropolitan area whose destinations are not given at all at the training stage. We highlight the challenges in this destination prediction task -- having no knowledge of the destinations in the targeted metropolitan area. We provide insights from the datasets, in which revisiting behaviors and the relationships between origins and destinations play a crucial role in individuals' trips. Hence, we design a simple but comprehensive method, rule-based visiting circulation, which directly utilizes the origin information and individuals' trip behaviors to determine the destinations in the targeted metropolitan area, i.e., requiring no learning from the four training areas. Experimental results on both offline evaluation and leaderboard submission consistently exhibit the proposed RVC can significantly outperform supervised learning methods and other heuristics. The RVC method eventually brings us to second place in the competition leaderboard.

Problem

• Trip Destination Prediction
• Visiting Circulation
• Revisiting Behavior
• Origin-Destination Relationship
• Zero-shot Prediction

Innovation

• Rule-based Visiting Circulation
• Trip Destination Prediction
• Revisiting Behavior
• Zero-shot Transfer
• Origin-Destination Relationship