AirBnB Listing Analyzer

Built a full-stack map-based dashboard application designed for AirBnB real estate investors. The application predicts how profitable a future AirBnB listing might be by analyzing historical listing data, providing investors with data-driven insights to maximize their returns on rental property investments.

The AirBnB market is highly competitive and unpredictable. Investors considering purchasing rental properties need reliable data to make informed decisions, but there is no simple, unified tool that visualizes current market conditions, estimates potential revenue, and accounts for seasonal trends—all in one place. Without this data, investors are left making costly decisions based on guesswork.

Developed an address and map-based dashboard that aggregates AirBnB listing data from Inside AirBnB and custom data collection methods. The application applies linear regression models to predict key profitability metrics, then presents the results through an interactive map interface where investors can explore listings by location and compare performance data visually.

Profitability Prediction — Uses linear regression to forecast how profitable a potential AirBnB listing could be at a given location, based on features like neighborhood, property type, amenities, and room count from historical listing data.

Interactive Map Dashboard — A React.js-powered map interface that lets investors explore AirBnB listings geographically, viewing current profitability data, average daily rates, and occupancy metrics for properties in any area.

Seasonal Impact Analysis — Projects how seasonality affects revenue throughout the year, helping investors understand peak and off-peak periods for their target markets.

Revenue Forecasting — Estimates annual revenue, average daily rate, and occupancy rate projections for prospective listings, giving investors a comprehensive financial picture before making a purchase.

Current Market Overview — Displays how currently active listings in a given area are performing, providing a real-time benchmark for evaluating investment opportunities.

The application is built on a decoupled full-stack architecture with a React.js frontend and a Flask/Python backend, containerized with Docker for consistent deployment.

Frontend — A React.js single-page application that renders the interactive map, listing cards, and analytics dashboards. The UI communicates with the backend API to fetch predictions and market data.

Backend — A Flask API server that handles data processing, serves the machine learning model predictions, and manages data retrieval from the AirBnB dataset. The backend includes form handling for user inputs like address and property details.

Data Pipeline — Raw listing data from Inside AirBnB is preprocessed through exploratory data analysis (EDA), with an automated HTML report generated for data quality review. The cleaned dataset feeds directly into the regression model.

Containerization — The backend is fully Dockerized with a Makefile for streamlined build, run, and cleanup commands, ensuring reproducible environments across development and deployment.

• React.js — Frontend framework for the interactive map dashboard and UI components
• Flask — Python web framework powering the REST API backend
• Python — Data processing, EDA, and machine learning model development
• Linear Regression — Predictive model for estimating listing profitability
• Docker — Containerization for consistent backend deployment
• Inside AirBnB Dataset — Primary data source for historical listing information
• Pandas & NumPy — Data manipulation and statistical computation
• HTML/CSS — EDA report generation and frontend styling

• Project Presentation
• GitHub Repository