Computer Science graduate with expertise in SQL, Python, and data visualization. Skilled in translating complex data into actionable business insights to support informed decision-making within teams. Passionate about leveraging technical skills to drive organizational success through data-driven strategies.
Programming: Python (Pandas, NumPy), SQL
undefinedSales Intelligence Dashboard using SQL
• Developed a data-driven solution to help retail businesses optimize inventory and marketing by analyzing 1M+ rows of real-time sales data.
• Identified top-selling products, customer churn, and monthly sales trends using JOIN, GROUP BY, CTE, WINDOW FUNCTIONS, and CASE.
• Implemented cohort analysis, customer segmentation (RFM), and regional performance breakdowns.
• Demonstrated how SQL-based insights can improve decision-making in real-world retail and e-commerce scenarios.
Disease Prediction Using Machine Learning
• Developed a machine learning model to predict diseases based on patient symptoms, age, gender, and health indicators.
• Applied robust data preprocessing, including label encoding, rare case removal, and normalization.
• Tackled class imbalance using RandomOverSampler to improve generalization.
• Trained a RandomForestClassifier, achieving high accuracy in predicting multi-class disease outcomes.
• Mapped predictions back to disease names using reverse encoding for interpretability.
House Price Prediction with Python
• Cleaned and preprocessed real estate data using Pandas & NumPy.
• Handled outliers like unrealistic sqft/BHK ratios.
• Used Seaborn & Matplotlib to visualize price distribution and feature relationships.
• Identified feature-to-price patterns that drive pricing anomalies.
IBM Data Science