Inspiration

Financial stress varies across multiple structural factors. As students interested in economics and consulting, we aimed to understand what drives financial vulnerability and to develop data-driven solutions.

What it does

We identify high-risk households and measure financial resilience using the Debt-to-Income Ratio (DTI): $$ DTI = \frac{Total\ Debt}{Annual\ Income} $$ We apply regression modeling to determine key financial and demographic drivers, and conduct a 10% rent shock simulation to evaluate how vulnerability changes under stress. We then translate findings into actionable policy recommendations.

How we built it

  • Cleaned and preprocessed the dataset
  • Defined and constructed the Debt-to-Income Ratio (DTI)
  • Built a linear regression model to analyze the relationship between key factors and DTI
  • Conducted a deeper analysis on the most influential factor groups
  • Performed shock simulation to assess financial resilience under stress

Challenges we ran into

  • Handling skewed, real-world data with outliers
  • Translating model results into practical solutions
  • Using Git with Jupyter Notebook for version control for the first time

Accomplishments that we're proud of

  • Isolating the strongest predictors of financial vulnerability
  • Combining predictive modeling with scenario simulation
  • Translating analytical insights into actionable strategies

What we learned

  • Financial vulnerability is driven by overlapping structural factors rather than a single variable.
  • Our analysis shows that housing tenure, age group, and other factors interact and jointly increase financial stress.

Built With

Share this project:

Updates