Team 17

Inspiration

Financial stability is often measured with narrow indicators like income or credit score, but these fail to capture how well someone can actually withstand unexpected financial shocks. With rising living costs and increasing financial uncertainty—especially for adults aged 18–55—we saw a need for a more holistic, data‑driven way to understand resilience. Our goal was to build a tool that helps institutions, researchers, and individuals identify financial vulnerability before it becomes a crisis.

What it does

Our project generates a Financial Resilience Score for each individual in the dataset by analyzing a wide range of personal‑finance behaviors. The score reflects a person’s ability to absorb financial shocks based on factors such as income stability, spending patterns, savings habits, debt levels, and credit utilization. We also surface the key drivers of resilience, highlight vulnerable demographic segments, and visualize how resilience varies across the population.

How we built it

Cleaned and preprocessed the personal‑finance dataset to ensure consistency and usability. Engineered features capturing financial behavior, stability, and risk exposure. Conducted exploratory data analysis to uncover patterns and correlations. Built a scoring model using statistical and machine‑learning techniques to quantify resilience. Validated the model and interpreted factor importance to ensure transparency. Created visualizations to communicate insights clearly to stakeholders.

Challenges we ran into

Defining “financial resilience” in a measurable, data‑driven way required careful feature selection and weighting. Balancing interpretability with predictive power was difficult—complex models performed well but were harder to explain. The dataset contained missing values and inconsistent patterns that required thoughtful cleaning. Ensuring the score was fair across demographic groups required additional checks and adjustments.

Accomplishments that we're proud of

Developed a clear, interpretable Financial Resilience Score that integrates multiple financial dimensions. Identified the most influential factors driving resilience across different age and income groups. Built visual tools that make the insights accessible to non‑technical stakeholders. Created a framework that financial institutions and community groups could realistically use to support early intervention.

What we learned

Financial resilience is multi‑dimensional and cannot be captured by a single traditional metric. Feature engineering plays a critical role in modeling real‑world financial behavior. Interpretability matters—stakeholders need to understand why a score is high or low, not just the number. Collaboration and iteration are essential when working with complex, messy datasets.

What's next for Team 17

We plan to refine the scoring model using additional behavioral and demographic variables, incorporate time‑series analysis to capture financial trends, and explore fairness adjustments to ensure equitable scoring across groups. We also hope to build an interactive dashboard that allows users to explore resilience factors and simulate how changes in financial behavior could improve their score.