Stack Overflow Analysis

Tech Stack: Python, AWS, Scipy, PySpark, Numpy, Pandas, Sklearn)

• Built expert-recommendation system using K-means clustering, by analyzing Stack Overflow data to find trends in data, & understand community user engagement dynamics for question routing using Python.
• Used graphical visualization techniques to identify top 5 % experts with high reputation score in particular domain and route relevant questions to them.
• Feature Engineered about 260,000+ user dataset Stack Exchange Data and API to perform data analysis and exploration.