End-to-end analysis of NYC Yellow Taxi trip data using PySpark, covering data cleaning, EDA, feature engineering, demand patterns, and fare prediction modeling.

Power BI dashboard analysing rail operations: ticket sales, delays, revenue, and customer behaviour.

Through exploratory data analysis and statistical evaluation, this project investigates how customer attributes specifically Gender, Age, and User Type influence ride duration. The analysis aims to identify patterns in trip behavior and assess whether demographic and subscription characteristics are associated with differences in usage.

Develop a predictive model to accurately forecast hourly traffic volumes at different road junctions based on historical traffic data

Apache Airflow ETL pipeline that consolidates multi-format toll road traffic data (CSV, TSV, fixed-width) into a unified, transformed dataset using BashOperators and scheduled workflows.

An end-to-end data analysis project focused on OLA ride-sharing data including trip patterns, demand analysis, driver performance metrics using SQL and Power BI.

Real-world Markov Process Simulation using Divvy Bike Data (GBFS), demonstrating SAS-to-Python migration for operational analytics and forecasting.

Difference-in-Differences analysis of bus-lane policies and ridership trends in Israel.

fmCSA carrier data extraction tool

30-year U.S. airline market analysis (1993–2024) examining pricing trends, competition effects, demand concentration, and route-level business intelligence in Python.

Deep exploratory analysis of NYC TLC trip data to understand demand patterns, zone-level variability, seasonality, and revenue distribution. Conducted structured EDA on spatial heterogeneity, temporal trends, skew, feature correlations, and lag effects. Built Prophet and LightGBM models.

Data analysis for Ride-sharing market and demand analysis for Chicago, integrating trip, competitor, and weather data to generate data-driven operational and strategic insights.

🚖 Analyze NYC Yellow Taxi trip data for fare prediction and demand insights using PySpark, enabling efficient data processing and accurate modeling.