Data Analytics & AI Projects
Data Analytics & AI Projects
This project explores employee training and performance data to uncover actionable insights. Using EDA, PCA, clustering, and A/B testing, the analysis examines how training impacts outcomes, segments employees into distinct groups, and evaluates program effectiveness.
Conduct Exploratory Data Analysis (EDA) to understand employee demographics, training records, and outcomes.
Apply Principal Component Analysis (PCA) to identify underlying themes driving performance.
Segment employees using KMeans clustering to reveal distinct workforce groups.
Perform A/B testing to measure the impact of training interventions.
Identified three key workforce themes: individual skills & curiosity, day-to-day operational tasks, and career direction.
Revealed distinct workforce clusters, enabling targeted learning and development strategies.
Demonstrated that training participation significantly improved performance outcomes, curriculum validated through A/B testing.
Delivered an interactive dashboard that allows stakeholders to explore workforce patterns, compare regions, and track program effectiveness dynamically:
This project analyzes customer purchase behavior and revenue patterns using SQL queries and interactive visualization. By combining transactional data with Tableau dashboards, it highlights key drivers of revenue and customer value.
Query and aggregate customer transaction data with SQL.
Identify high-value customers and revenue contribution by segment.
Visualize revenue trends, churn risk, and customer lifetime value.
Segmented customers by revenue contribution, revealing that a small share of clients drives the majority of sales.
Tracked monthly/quarterly revenue trends, identifying seasonal peaks and downturns.
Delivered insights to support targeted marketing and retention strategies.
Built a dynamic dashboard enabling stakeholders to filter by region, customer type, and time period:
This project evaluates the feasibility of developing a Class B multifamily property by analyzing city-level market data and applying financial modeling in Excel. The analysis integrates rent growth, vacancy rates, and expense ratios to assess profitability and risk under different scenarios.
Analyze city-level metrics (Rent CAGR, Vacancy, Expenses) to compare markets.
Develop financial models to project NOI, payback periods, and returns.
Apply scenario and sensitivity analysis to test assumptions.
Provide a structured framework for market selection and investment feasibility.
Identified New Hope as the most promising city based on growth and vacancy performance.
Built Excel-based models demonstrating profitability across different assumptions.
Conducted sensitivity testing on cap rates and NOI to understand risk exposure.
Delivered a data-driven investment recommendation supported by scenario modeling.