Neurosymbolic AI for Travel Demand Prediction: Integrating Decision Tree Rules into Neural Networks

2025-02-02

AI Summary

Low prediction accuracy and poor interpretability hinder travel demand forecasting in transportation planning. Method: This paper proposes a neuro-symbolic AI framework that, for the first time, embeds fine-grained decision-tree symbolic rules—derived via variance-threshold pruning (0.0001)—as structured priors into a neural network, thereby unifying interpretability with strong representational capacity. The approach integrates heterogeneous multi-source data—including geographic, economic, and mobility features—and employs a symbiotic symbolic-subnetwork modeling architecture coupled with ensemble learning. Results: Experiments demonstrate consistent superiority over pure neural network and pure decision tree baselines across MAE, R², and CPC metrics: prediction error decreases by 12.7%, commute pattern matching improves by 19.3%, and generalization capability as well as alignment with real-world mobility patterns is significantly enhanced.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Travel demand prediction is crucial for optimizing transportation planning, resource allocation, and infrastructure development, ensuring efficient mobility and economic sustainability. This study introduces a Neurosymbolic Artificial Intelligence (Neurosymbolic AI) framework that integrates decision tree (DT)-based symbolic rules with neural networks (NNs) to predict travel demand, leveraging the interpretability of symbolic reasoning and the predictive power of neural learning. The framework utilizes data from diverse sources, including geospatial, economic, and mobility datasets, to build a comprehensive feature set. DTs are employed to extract interpretable if-then rules that capture key patterns, which are then incorporated as additional features into a NN to enhance its predictive capabilities. Experimental results show that the combined dataset, enriched with symbolic rules, consistently outperforms standalone datasets across multiple evaluation metrics, including Mean Absolute Error (MAE), (R^2), and Common Part of Commuters (CPC). Rules selected at finer variance thresholds (e.g., 0.0001) demonstrate superior effectiveness in capturing nuanced relationships, reducing prediction errors, and aligning with observed commuter patterns. By merging symbolic and neural learning paradigms, this Neurosymbolic approach achieves both interpretability and accuracy.

Problem

• Integrates decision tree rules into neural networks.
• Predicts travel demand using Neurosymbolic AI framework.
• Enhances accuracy and interpretability in travel predictions.

Innovation

• Integrates decision tree rules
• Enhances neural network predictions
• Combines symbolic and neural learning