Natural Language Query Assistant for Financial Calculations

Added Jun 2025 3 design docs

Finance professionals spend hours translating questions like how a fifty basis point rate rise changes weighted average cost of capital into spreadsheet models, and junior analysts often do not know which formula applies in the first place. An assistant that interprets financial questions and shows its working can compress that loop from hours to minutes. The intern builds a Flask web tool in Python where users type complex financial questions and receive AI-generated, context-aware explanations with step-by-step calculations. Generative AI is the core of the system: the intern designs prompts and guardrails so answers cite the formulas used, state their assumptions explicitly, and walk through the arithmetic rather than asserting a bare number. PostgreSQL stores user accounts, query history, and saved results, so professionals can revisit and export prior analyses, while authentication keeps each user's financial context private. The project develops real skill in natural language interfaces for quantitative domains: prompt engineering for accuracy, structuring AI output so humans can verify it, and wrapping everything in a dependable, database-backed web application.

Related projects

Investment Portfolio Tracker With Live Market Data Integration

Retail investors spread holdings across brokers and asset classes, then lose the overall picture: what the portfolio is worth right now, which positions drive returns, and how allocation has drifted. This project builds a portfolio tracker that restores that picture in real time. The intern implements a FastAPI and Python backend with PostgreSQL recording holdings, transactions, and valuation history, integrating third-party market data APIs so prices and portfolio values update live. Concurrency control keeps transaction records consistent even when updates overlap, an important discipline anywhere money is counted, and JWT authentication with role-based access protects every account. The React and TypeScript frontend, styled with Tailwind CSS, presents performance analytics and allocation breakdowns through rich interactive visualizations, alongside a complete transaction history. The intern learns to consume and cache external financial data, design schemas for auditable transaction records, and handle correctness under concurrent writes, then finishes with a fintech-grade application that demonstrates both engineering rigor and an understanding of what investors actually need to see.

financefastapifullstack+6

View project

Medium

Model Interpretability Dashboard Using SHAP and LIME for Credit Decisions

In lending and other regulated corners of finance, a model that cannot be explained cannot be shipped: risk officers, auditors, and regulators all expect a clear account of why a credit model scored an applicant the way it did. Data science teams need tooling that makes interpretability routine rather than a one-off notebook exercise. The intern builds a Streamlit dashboard where users upload a trained scikit-learn model together with a dataset, then explore global behavior through SHAP summary and feature importance plots and drill into individual predictions with local SHAP and LIME explanations. Pandas and NumPy handle the data wrangling behind the scenes, while the interface guides users from a dataset overview to per-row explanations and makes it easy to see where the two explanation techniques agree and where they diverge — a comparison that builds real judgment about when to trust each method. The project teaches the intern how modern explainability methods work mechanically, how to build analyst-facing tooling in pure Python, and how to communicate model behavior to non-technical stakeholders — a combination finance employers explicitly screen for when hiring into model risk and credit teams.

financedata-sciencemachine-learning+6

View project

Easy

Loan Default Risk Estimator With Random Forest and Interactive Inputs

Before extending credit, lenders need a defensible estimate of default risk — and loan officers need to explore that risk interactively, asking how the picture changes if income were higher or the loan amount smaller. This project builds a tool for exactly that kind of what-if analysis. The intern trains a random forest classifier with scikit-learn on loan applicant data, then builds a Streamlit interface where each input feature — income, loan amount, credit history, and so on — is controlled by a slider or selector. As users adjust the inputs, the app recomputes the default probability live and displays it with clear visual risk indicators, turning the model into an exploratory instrument rather than a static scorer. Feature importance charts show which factors the forest leans on most heavily, connecting the model's behavior back to intuitions about creditworthiness. The project teaches ensemble tree models on tabular financial data, probability-based classification output, and the design of interfaces that let non-technical users interrogate a model safely. The intern demonstrates they can carry a finance use case from raw dataset to an interactive decision-support tool.

financedata-sciencemachine-learning+3

View project