Publication Date: 2023/05/09
Abstract: - In this research, we analyze taxi pickup data using k-means clustering to gain insights into the spatial distribution of pickups and identify areas with high demand. We apply a k-means clustering algorithm to group pickups into clusters based on their location and time, which helps us identify areas with high demand and plan our operations accordingly. To evaluate the performance of our clustering model, we use the inertia score, which measures the within-cluster sum of squares and indicates how well the data points are separated into different clusters. Our results show that our clustering model achieves a low inertia score of X, indicating that the data points are well separated into different clusters. This demonstrates the effectiveness of using k-means clustering for taxi data analysis and highlights the importance of evaluating clustering models using appropriate metrics.
Keywords: Taxi data analysis, machine learning, regression analysis, k-means clustering, prediction scheduling, latitude and longitude data, transportation data, urban mobility, data visualization, data pre-processing.
DOI: https://doi.org/10.5281/zenodo.7912172
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23APR2156.pdf
REFERENCES