Data Science Course with Placement Assistance

Designed and built an Excel-based Social Media Intelligence Solution by extracting, cleaning, and analyzing social media performance metrics. Conducted ROI, engagement, and correlation analysis to evaluate the relationship between ad spend, follower growth, and campaign performance. Generated actionable brand insights through interactive dashboards, enabling data-driven marketing strategies and informed business decision-making.

Developed an interactive Customer Retention Analytics Dashboard in Power BI by integrating customer demographics, transactions, loyalty program, and store performance data. Performed data modeling and transformations using Power Query, and created calculated columns and DAX measures to analyze churn, repeat purchase behavior, customer lifetime value (CLV), and loyalty tier effectiveness. Delivered actionable insights that informed strategies to reduce churn, improve loyalty program efficiency, and enhance customer retention across retail channels.

Developed a Python-based financial risk analysis system using transactional data to uncover customer behavior patterns and identify potential risk indicators. Performed data cleaning, segmentation, hypothesis testing, and anomaly detection, along with exploratory visualizations to highlight insights related to transaction trends, account performance, overdrafts, and balance volatility.

Designed a SQL-driven logistics analytics system to optimize delivery routes, analyze delays, and improve shipment efficiency for large-scale e-commerce operations. Performed data cleaning and preprocessing by handling duplicates, null values, and inconsistent date formats. Applied advanced SQL queries, aggregations, CTEs, subqueries, and window functions to evaluate delivery delays, route efficiency, warehouse bottlenecks, and agent performance.

Conducted Market Basket Analysis on e-commerce datasets to identify customer purchasing patterns and behavioral trends. Leveraged Python libraries such as pandas, NumPy, and scikit-learn to apply clustering algorithms, enabling insights into personalized product recommendations, bundling opportunities, and strategic marketing initiatives. The analysis contributed to data-driven decision-making by aligning product strategies with customer needs.

Designed and developed an AI-powered Historical Speech Classification System using Natural Language Processing and Machine Learning to categorize speeches into predefined themes. Performed text preprocessing, feature engineering, model training, and prediction on real-world datasets, enabling accurate speech classification, deeper textual insights, and data-driven content analysis.

Built an end-to-end predictive modelling project using real-world data scraped. Designed a Python web scraping script to collect 1,000+ records from a public website. Cleaned and preprocessed raw data by handling missing values, duplicates, and inconsistencies. Performed Exploratory Data Analysis (EDA) to identify key trends, patterns, and anomalies. Applied a machine learning model (classification / regression / clustering) to derive predictive insights. Evaluated model performance to ensure reliability. Developed an interactive dashboard using Power BI Translated technical results into business-friendly insights and recommendations.