top of page

Predicting U.S. State-Level Student Scores from Demographic and Financial Factors

Jul 23
1 min read

Student outcomes vary widely from state to state, and a lot of that variation tracks with demographic and financial context. This project models U.S. state-level student scores from those factors to support data-driven education strategy.

The approach

The problem is framed as a regression task: predict a continuous student-score outcome from demographic and financial predictors. Beyond raw prediction, the analysis examines how each factor relates to outcomes, so the model doubles as a lens on what's driving performance.

Technologies used

  • Python: the analysis and modeling workflow.

  • scikit-learn: regression models, evaluation, and analysis of feature relationships.

  • Pandas & NumPy: assembling and cleaning the demographic and financial datasets.

  • Matplotlib / Plotly: visualizing relationships between factors and scores.

Impact

The model links demographic and financial factors to student performance, giving education stakeholders a data-driven basis for strategy and resource decisions.

Tech stack: Python, scikit-learn, Pandas, NumPy, Matplotlib, Plotly, regression modeling.

 
 
 

Comments

bottom of page