What is it about?

Metaheuristics has great potential to find good quick solution to optimizing the vehicle assignments in Ride Hailing Services. However, they include lots of parameters that needs to be optimized. In this paper we suggest using Neural Network for picking right values for these parameters.

Featured Image

Why is it important?

In the dynamic vehicle assignments in Ride Hailing services, the nature of problem keeps changing throughout the day. Therefore, using a scheme that would pick right metaheuristic parameters for the current time and problem instance is of utmost importance for finding good vehicle assignments.


I expect that this article would open door for dealing with the problem of how to tune metaheuristic or any algorithm's parameters for dynamic problems. We suggested a simple feed forward network for the purpose. However, other more advance network architecture can provide much better results.

Arslan Ali Syed
Mobility Technologies, BMW

Read the Original

This page is a summary of: Neural Network-Based Metaheuristic Parameterization with Application to the Vehicle Matching Problem in Ride-Hailing Services, Transportation Research Record Journal of the Transportation Research Board, May 2019, SAGE Publications,
DOI: 10.1177/0361198119846099.
You can read the full text:



The following have contributed to this page