December 4, 2025Data Science for TransportationOpen Access

A Fully Neural Network-Based Travel Demand and Scheduling Model, Covering Activities, Destinations, and Modes of Transportation

View Full Paper

Ask AI

Bookmark

Authors

JFJoel Fredriksson AKAnders Karlström

Discussion

Member takes

Implication

Observational analysis demonstrates improved predictive accuracy for mode choice in travel demand, indicating neural networks enhance scheduling effectiveness.

Key Points

The neural network model shows improved predictive accuracy compared to traditional methods, addressing multiple components of travel demand.
In the Stockholm case study, the model effectively integrates activities, destinations, and modes, managing 1375 destinations.
Evaluation uses a utility-maximizing microsimulation approach, highlighting advancements in activity-based modeling.
Findings suggest potential for transferability to other urban settings, paving the way for broader applications of neural network models.

Cite This Study

Fredriksson et al. (2025) studied this question.

synapsesocial.com/papers/6930e8d7ea1aef094cca3a51 https://doi.org/10.1007/s42421-025-00141-5

View Full Paper

Ask AI

Bookmark

Implication

Observational analysis demonstrates improved predictive accuracy for mode choice in travel demand, indicating neural networks enhance scheduling effectiveness.

A Fully Neural Network-Based Travel Demand and Scheduling Model, Covering Activities, Destinations, and Modes of Transportation

Discussion

Member takes

Implication

Key Points

Cite This Study

A Fully Neural Network-Based Travel Demand and Scheduling Model, Covering Activities, Destinations, and Modes of Transportation

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider