top of page

Predicting U.S. High-School Dropout — and Explaining Why — with an Interactive Dashboard

Jul 23
1 min read

Predicting who is at risk of dropping out is useful; explaining why is what actually helps policymakers act. This project pairs a dropout-prediction model with an interactive dashboard that turns the model's findings into clear, actionable insight.

Prediction plus explanation

The model predicts U.S. high-school dropout rates, and — crucially — a feature-importance analysis identifies which factors contribute most to that risk. The emphasis is on interpretability: not just a score, but the reasons behind it.

The dashboard

The results are delivered through an interactive Python + Plotly dashboard that lets policymakers explore the most influential dropout factors and translate them into concrete, actionable strategies.

Technologies used

  • Python: data pipeline and modeling.

  • scikit-learn: the predictive model and feature-importance analysis.

  • Pandas & NumPy: cleaning and engineering the demographic and educational features.

  • Plotly: the interactive dashboard for exploring contributing factors.

Impact

The dashboard converts a predictive model into a decision-support tool — surfacing the biggest drivers of dropout and giving policymakers actionable insight.

Tech stack: Python, scikit-learn, Pandas, NumPy, Plotly, feature-importance analysis, interactive dashboards.

 
 
 

Comments

bottom of page