![[2602.16573] MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.16573] MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models
Summary
The paper presents MoDE-Boost, a novel approach using gradient boosting models to forecast urban mobility demand, enhancing efficiency in shared mobility services.
Why It Matters
As urbanization accelerates, effective demand forecasting for shared mobility is crucial for optimizing transportation systems. This research contributes to sustainable urban development by improving routing and dispatching through advanced predictive models, addressing the challenges posed by increasing urban mobility needs.
Key Takeaways
- MoDE-Boost employs two gradient boosting model variations for demand forecasting.
- The models can predict demand at various time horizons, enhancing operational efficiency.
- Real-world data from e-scooter and e-bike networks validate the model's effectiveness.
- The approach integrates temporal and contextual features for accurate predictions.
- This research supports sustainable urban mobility management amidst rapid urbanization.
Computer Science > Machine Learning arXiv:2602.16573 (cs) [Submitted on 18 Feb 2026] Title:MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models Authors:Antonios Tziorvas, George S. Theodoropoulos, Yannis Theodoridis View a PDF of the paper titled MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models, by Antonios Tziorvas and 1 other authors View PDF HTML (experimental) Abstract:Urban demand forecasting plays a critical role in optimizing routing, dispatching, and congestion management within Intelligent Transportation Systems. By leveraging data fusion and analytics techniques, traffic demand forecasting serves as a key intermediate measure for identifying emerging spatial and temporal demand patterns. In this paper, we tackle this challenge by proposing two gradient boosting model variations, one for classiffication and one for regression, both capable of generating demand forecasts at various temporal horizons, from 5 minutes up to one hour. Our overall approach effectively integrates temporal and contextual features, enabling accurate predictions that are essential for improving the efficiency of shared (micro-) mobility services. To evaluate its effectiveness, we utilize open shared mobility data derived from e-scooter and e-bike networks in five metropolitan areas. These real-world datasets allow us to compare our approach with state-of-the-art methods as well as a Generative AI-based model, demonstrating its effectiven...