← Back to Publications List

Machine Learning Models for Socioeconomic Inequality Prediction Using Census Data

Students & Supervisors

Student Authors
Badhon Roy Nibir
Bachelor of Science in Computer Science & Engineering, FST
Anima Ferdushi Anika
Bachelor of Science in Computer Science & Engineering, FST
Zarin Tasnim Rika
Bachelor of Science in Computer Science & Engineering, FST
Md. Rajob
Bachelor of Science in Computer Science & Engineering, FST
Mst. Nazmun Nahar
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Md. Mortuza Ahmmed
Associate Professor, Faculty, FST

Abstract

Socioeconomic inequality denotes to the imbalance distribution of resources, prospects and privileges among people in a society based on their social and economic status and it is dividing the society in many groups. It reflects how a certain group of people have better access to education, jobs and housing than others. Machine learning models can recognize patters of various indexes related to socioeconomic inequality and can come up with results by which we can minimize the inequality in our society. The primary purpose of this research is to identify how various kind of indexes are related to Socioeconomic inequality and understand how to identify which variable contributes the most to inequality and to examine by using machine learning models. For our research we have studied four factors of data which includes income inequality index, education level index, employment rate and housing quality index from 1994 to 2024. The analysis shows how the socioeconomic indicators demonstrate their role to create overall discrimination. Our analysis result showed huge ups and downs throughout the year. The income inequality fluctuated between 1.3% and 99.2%. On the other hand, education levels gradually improved towards the year ending, reaching a high point in 2023 (96.63). Employment rates were unstable. The percentage of housing rate 95.81 % in 1995 to 94.07% in 2025 is quite equal. Inspite of this, these inequalities remains in employment reliability and housing rate and it indicates the need for fair development. This study concludes that machine learning can efficiently analyze secondary quantitative data to predict reasons behind the socioeconomic inequality. The major findings indicate how data modelling can find patterns and help policymakers to improving education, employment, and housing conditions to decrease inequality.

Keywords

Socioeconomic Machine Learning Models Inequality Disparity Patterns Policymakers.

Publication Details

  • Type of Publication:
  • Conference Name: Gazipur Agricultural University International Conference(GAUIC) 2025
  • Date of Conference: 12/12/2025 - 12/12/2025
  • Venue: Gazipur Agricultural University, Gazipur, Bangladesh
  • Organizer: Gazipur Agricultural University
View on Publisher