Comparative Analysis of Different Machine Learning Techniques for Travel Mode Prediction

Abstract

The growth rate of cities is increasing due to urbanization, necessitating the management of resources such as public transport, private transport, roads, etc. Understanding the behavior of travel is also a crucial topic in managing and planning the resources in smart cities. Hence, in this research work an attempt is made to analyze the travel mode preference of an individual under different circumstances. The public database provided by Microsoft for tracking the travel mode of individuals is used for experimentation. The comparative analysis of different machine learning algorithms is performed for the prediction of travel mode. Experimentally, it has been observed that the Extra-Trees classifier outperforms the rest of the classifiers. The Extra-Trees classifier gained an overall accuracy of 97 % in predicting the travel mode of individuals. In this way, the proposed research work can be used in real-time applications to understand travel behavior and suggest the mode of travel for individuals under given constraints with great accuracy.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 3 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.