Predicts flight arrival delays using operational flight features and a Random Forest model. Includes a Streamlit web application for interactive predictions.

Power BI dashboard analyzing airline loyalty program performance, including enrollments, cancellations, and flight booking trends with DAX-based insights.

Time series forecasting project for airline passenger demand using statistical models and ML, delivered via Streamlit.

An interactive Tableau dashboard that explores airline customer reviews to uncover passenger satisfaction, sentiment trends, and service quality insights.

“Predictive analytics project analyzing 3M+ U.S. flight records to forecast delays using Random Forest and XGBoost, improving operational decision-making for airlines.”

Airline Flight Delay Intelligence — 6.2M+ flights, 14 airlines, 628 airports, seasonal patterns, on-time performance, delay cause analysis | Python | Pandas | Matplotlib

Analyzing Frontier Airlines’ customer experience using real Skytrax reviews with route and aircraft context. Data is modeled in Snowflake (dbt), cleaned and analyzed with Python and SQL, and presented in an interactive Mode dashboard to surface clear insights.

Python analytics project analyzing airline disruptions, delays, cancellations, and passenger impact using a Disruption Severity Index (DSI).

End-to-end Data Analytics project in Power BI, analyzing 2M+ flight records to identify delay root causes and optimize operational efficiency.

⛈️ StormChain — identifying pilot flight sequences through DFW most vulnerable to weather-driven cascading delays. XGBoost (AUC 0.81) + 1,220 avoid recommendations + live METAR dashboard. Built for the EPPS-American Airlines Data Challenge.

Customer segmentation of East–West Airlines frequent flyer data using K-Means and Hierarchical Clustering. The project identifies optimal customer segments based on flying behavior, reward usage, and credit card activity, and provides data-driven business inferences for targeted marketing strategies.

End-to-end machine learning project to predict airline customer satisfaction using XGBoost, Random Forest and Neural Networks, combining EDA, PCA and SHAP explainability to identify the service, customer and travel variables that most strongly influence satisfaction and support data-driven service improvement strategies.

Airline Revenue Management Analytics project using SQL, Python (ARIMA forecasting), and Power BI to analyze passenger demand, pricing trends, and route performance.

Customer segmentation on airline loyalty data using LRFMC model and K-Means clustering to identify 5 distinct groups based on customer transaction behavior and provide data-driven marketing strategy recommendations.

Analyze flight data to identify delay patterns, seasonal trends, and airline performance metrics across US airports.