• AYESHA QAMER
• D.RAJASHEKAR REDDY

This study leverages machine learning clustering techniques to uncover patterns in travel behavior from large-scale mobility data. By applying unsupervised algorithms like K-means, DBSCAN, and hierarchical clustering, we identify distinct travel segments based on factors such as trip frequency, preferred transportation modes, and time-of-day patterns. Different models were generated using different clustering Techniques and the analysis reveals key insights into commuter behavior, including the identification of frequent commuters, seasonal travel trends, and spatial-temporal travel preferences. These findings provide a deeper understanding of traveler segments, such as regular public transit users, occasional car drivers, and cyclists, which can inform transportation policy and urban planning decisions. Additionally, the study highlights the insights in the travel behavior of central zone of Hyderabad, India. Overall, the application of machine learning clustering offers valuable insights for optimizing transportation systems, reducing congestion, and developing more personalized mobility solutions in urban environments.

Clustering Techniques, K-means Clustering, Hierarchical Clustering, Mean Shift.

"ENHANCING TRANSPORTATION PLANNING THROUGH TRAVEL BEHAVIOUR CLUSTERING IN MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.e8-e19, December-2024, Available :http://www.jetir.org/papers/JETIR2412402.pdf

"ENHANCING TRANSPORTATION PLANNING THROUGH TRAVEL BEHAVIOUR CLUSTERING IN MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppe8-e19, December-2024, Available at : http://www.jetir.org/papers/JETIR2412402.pdf