Logistic regression for predicting the location of vegetable vendors in the city of Raipur, Chhattisgarh, India

Sushmita Chakraborty, Abir Bandyopadhyay, Swasti Sthapak


Urban planning plays a pivotal role in guaranteeing the functionality, accessibility, and adaptability of cities to meet the needs of their diverse population and various official and informal economic activities. The primary objective of this work is to investigate the application of machine learning techniques in the identification of optimal places for vegetable vendors within the urban context of Raipur City, India. While logistic regression has been used in previous studies to address issues such as soil erosion, land susceptibility mapping, and identifying potential sites for health facilities and mining exploration, this model has yet to be applied to determining suitable locations for vegetable vendors. This gap in research could be beneficial if addressed, particularly in India, where many city residents rely heavily on vegetable vendors for their dietary needs. The paper’s main focus is on evaluating the reliability of the model and encouraging its implementation in similar scenarios, highlighting its efficiency and adaptability, which are also evaluated in this study. A stratified random sampling technique was implemented to collect data from four different regions of Raipur City. Subsequently, the gathered data was subjected to analysis employing the logistic regression machine learning technique, with the objective of making predictions. The results obtained from the analysis were highly impressive, as the model successfully predicted 44 out of the total 50 locations with an accuracy rate of 88%.


Sushmita Chakraborty
schakraborty.phd2018.arch@nitrr.ac.in (Primary Contact)
Abir Bandyopadhyay
Swasti Sthapak
Chakraborty, S. ., Bandyopadhyay, A. ., & Sthapak, S. . (2023). Logistic regression for predicting the location of vegetable vendors in the city of Raipur, Chhattisgarh, India. International Journal of Innovative Research and Scientific Studies, 6(4), 970–979. https://doi.org/10.53894/ijirss.v6i4.2123

Article Details

No Related Submission Found