Team Name

LNTP

Team Members

Project Description

Team Members and Team Captain

• Team Member: Thang Phung
• Team Captain: Xuan Cuong Nguyen

Project Description

This project aims to uncover patterns of educational inequity among schools by analyzing socio-economic and demographic data. Using key indicators such as ICSEA (socio-educational advantage), FOEI (socio-economic disadvantage), LBOTE (language background other than English), and Indigenous representation, the project groups schools into clusters to reveal disparities in resource allocation and educational outcomes. The results provide insights into which schools are most disadvantaged and where targeted interventions may be needed to improve educational equity.

Introduction:

Education is a powerful driver of social mobility, yet not all students have equal access to high-quality educational resources. Using a dataset that includes socio-economic indicators such as ICSEA (socio-educational advantage), FOEI (socio-economic disadvantage), LBOTE (language background other than English), and Indigenous representation, this project aims to uncover patterns of inequity among schools. By applying K-Means clustering, we segmented schools into distinct groups based on their socio-economic profiles, allowing for a deeper understanding of educational disparities and where interventions are most needed.

The Findings:

Our analysis revealed several important insights:

• Clear Disparities: Schools with lower ICSEA values (less socio-educational advantage) also had higher FOEI values (more socio-economic disadvantage). These schools were predominantly in clusters with higher percentages of Indigenous and LBOTE students, highlighting a pattern of educational inequality.

• Inverse Trends: We found a strong inverse relationship between ICSEA and FOEI values—schools with more socio-educational advantage faced less socio-economic disadvantage.

• Targeted Interventions Needed: Schools in the most disadvantaged clusters, with high FOEI values and low ICSEA values, would benefit the most from targeted interventions, such as additional funding, language support, and culturally tailored programs for Indigenous students.

Conclusion:

This project tells a compelling data story about educational inequities. By clustering schools based on their socio-economic and demographic profiles, we have provided a clear, data-driven case for addressing educational disparities and guiding policy interventions that can make a meaningful impact.

Data Story

Data Story: Identifying Educational Inequities Through Socio-Economic Clustering

The Journey of the Data:

The project started with school-level data, capturing key socio-economic and demographic indicators. We replaced missing values and standardized the data to ensure consistency across all schools. Our key metrics—ICSEA, FOEI, LBOTE_pct, and Indigenous_pct—were chosen because they strongly correlate with student outcomes and educational equity. We used a data sampling methods and other preprocessing techniques to ensure the data is fit for machine learning purposes.

We then applied K-Means clustering to group schools into clusters based on their socio-economic and demographic profiles. This allowed us to create distinct groups that showed how certain schools, often serving vulnerable communities, are socio-economically disadvantaged.

Additionally, we created a web application to display the schools and their classification visually on a map. We believe this is the most intuitive way of viewing the data, and would be a great help in understanding the numbers analyzed by our Machine Learning model.

Impact and Next Steps:

This analysis highlights the urgent need for equitable resource allocation. The clusters we identified show that certain groups of schools face systemic disadvantages that affect their ability to provide quality education. The data story is clear: educational inequity is tightly linked to socio-economic factors, and understanding these relationships can guide better policy decisions.

Going forward, this model can be used to:
- Predict future school outcomes based on socio-economic trends.
- Direct funding and resources more effectively to the schools and regions that need it most.
- Provide insights for long-term planning and policy reforms to ensure all students have equal opportunities to succeed.