Using Data Analytics to predict students score

TL;DR

This paper employs machine learning on PISA data to predict student scores and analyze social, economic, and educational factors influencing performance, providing insights for educational policy development.

Contribution

It introduces a novel application of machine learning techniques to PISA data for score prediction and factor analysis in the context of Singapore's education system.

Findings

Machine learning models can accurately predict student scores.

Social and economic factors significantly influence student performance.

Insights can inform education policy and targeted interventions.

Abstract

Education is very important to Singapore, and the government has continued to invest heavily in our education system to become one of the world-class systems today. A strong foundation of Science, Technology, Engineering, and Mathematics (STEM) was what underpinned Singapore's development over the past 50 years. PISA is a triennial international survey that evaluates education systems worldwide by testing the skills and knowledge of 15-year-old students who are nearing the end of compulsory education. In this paper, the authors used the PISA data from 2012 and 2015 and developed machine learning techniques to predictive the students' scores and understand the inter-relationships among social, economic, and education factors. The insights gained would be useful to have fresh perspectives on education, useful for policy formulation.