Title: A smart prediction model for identifying homeless people using machine learning and immediate assistance system for homeless people using Android application

Authors: Md. Mehadi Hasan Shuvo; Mahfuzulhoq Chowdhury

Addresses: Computer Science and Engineering Department, Chittagong University of Engineering and Technology, Chittagong – 4349, Bangladesh ' Computer Science and Engineering Department, Chittagong University of Engineering and Technology, Chittagong – 4349, Bangladesh

Abstract: Homelessness is a state in which a person does not have access to an appropriate housing facility for living. The number of homeless people in developing countries like Bangladesh is on the rise. But due to a lack of proper prediction and assistance systems, they could not get the basic needs they deserve. This paper focuses on gaining useful insights into why people are becoming homeless in our country and which criteria can be selected for identifying homeless people effectively. Based on the data from the survey, this paper created a dataset for homeless people and applied five machine learning classifier algorithms to find out the best one for creating the prediction model for identifying homeless people. This paper also developed an Android Homeless People Aid application to provide immediate help to homeless people. The prediction model was also integrated into the application. The results highlight the usefulness of this work.

Keywords: homelessness; machine learning; prediction model; Google Maps; Homeless People Aid; mobile application.

DOI: 10.1504/IJSSS.2023.135917

International Journal of Society Systems Science, 2023 Vol.14 No.4, pp.282 - 302

Received: 12 May 2023
Accepted: 23 Jul 2023
Published online: 09 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article