In this paper, we propose a two-stage approach for predicting a trips destination by clustering geocoordinates and leveraging incremental learning and contextual rule-based methods for the prediction of end destinations. The proposed approach dynamically adapts to users change in behavior and is resilient against concept drift. Using this solution, 76.39% of the predictions were within 100 meters of the actual end destination and 75% of the predictions at most 79.88 meters from the actual end destination.

Last modified

• 04/05/2021

Creator

• Rohin Mahesh
• Subramanian Subramanian

DOI

• https://doi.org/10.21985/n2-tv7y-vp97

Keyword

• data science
• machine learning

Date created

• 2021-04-05

Rights statement

• No Known Copyright