Srinibas Masanta

This repository contains the work completed for the Applied Data Science Capstone Project offered by IBM on Coursera. The capstone project is the final course in the IBM Data Science Professional Certificate series and serves as an opportunity to apply the skills and knowledge gained throughout the series to a real-world data science problem.

This repository contains my work from the Deloitte Forage Virtual Internship, where I analyzed factory telemetry data in Tableau to identify machine breakdown patterns and assessed gender pay equality using Excel. From interactive dashboards to insightful classifications, this project showcases hands-on data analysis and visualization skills. 🚀📊

End-to-end customer segmentation using RFM analysis and K-Means clustering on real-world retail data. The project includes preprocessing, outlier handling, cluster validation, and visualization to generate actionable business insights. Completed as part of an AI & ML internship with Edunet Foundation under the AICTE–IBM SkillsBuild program.

An interactive Power BI dashboard developed during my Infosys Springboard Internship to visualize Indian election trends. It integrates historical and live API data to analyze vote shares, turnout patterns, and demographic insights across constituencies, helping news agencies report results in real time.

👨‍💻 My GitHub profile README — a quick snapshot of who I am, my skills, and what I’m passionate about.

End-to-end credit risk prediction project featuring data preprocessing, feature engineering, exploratory data analysis, and model training with Random Forest and XGBoost, followed by evaluation using accuracy, precision, recall, and ROC-AUC, and deployment via an interactive Streamlit web app for real-time credit risk classification.

This project predicts medical insurance charges using machine learning models after performing data preprocessing, EDA, and feature engineering. It highlights key cost drivers like age and smoking status and uses trained models for accurate predictions. The entire workflow demonstrates an end-to-end approach to regression-based predictive modeling.

Interactive Power BI dashboard for insurance analytics using SQL Server as the data source. Includes policy, claim, and customer sentiment analysis with drill-through functionality, KPI cards, and AI-powered feedback classification. The dashboard offers insights into policy performance, claim trends, customer demographics, and sentiment patterns.

Interactive Power BI dashboard analyzing UK road accident data to uncover trends, high-risk areas, and severity patterns across time, weather, and infrastructure. Features dynamic KPIs, geospatial mapping, vehicle-type analysis, and actionable, policy-driven recommendations to support data-informed road safety improvements.

This repository contains my Coursera assignments, featuring hands-on data science projects. From predicting rainfall to analyzing house prices and stock trends, each notebook applies Python, Pandas, and machine learning to real-world data. Ideal for learners exploring EDA, feature engineering, and predictive modeling! 🚀

This repository features an interactive Tableau dashboard that visualizes electric vehicle (EV) adoption trends in the U.S. 🚗⚡ Explore EV growth, top manufacturers, regional distribution, and the impact of incentives—all in one dynamic view. 📊 Use filters to dive deeper into the data and uncover key insights! 🚀

No description provided.

This project analyzes Yelp business reviews using Python, Snowflake, and SQL, focusing on efficient data ingestion, transformation, and analysis. We preprocess JSON data, optimize ingestion via Amazon S3, classify sentiments with Python UDFs, and extract insights using SQL queries—showcasing a streamlined end-to-end workflow.

This project is a database management system built on PostgreSQL for a home care worker providing agency. It is designed to facilitate efficient scheduling, billing, user registration, and contract management, ensuring compliance with healthcare regulations.

This project leverages the Sentiment140 dataset with 1.6 million tweets to classify sentiment as positive or negative using Logistic Regression and Naive Bayes. It involves data preprocessing, TF-IDF, model evaluation, and visualizations like confusion matrices and word clouds, with models saved for future use.

The Olympics Analysis project explores Olympic data to uncover trends in athlete performance, medal distribution, and participation across countries and demographics. By leveraging detailed datasets, it provides insights into the evolution of the Games, highlighting key patterns and disparities over time.

This project focuses on analyzing hotel booking data to uncover key metrics and insights that drive revenue management decisions. By creating an interactive Power BI dashboard, the project aims to improve strategic decision-making, optimize occupancy rates, and enhance overall financial performance within the hospitality industry.

Data Profiler is a Streamlit app designed to provide insightful data analysis and visualization. Users can upload their datasets in '.csv' or '.xlsx' format, and the app generates a comprehensive profiling report using the YData Profiling library.

This repository contains a comprehensive analysis of Zomato's platform, focusing on various aspects of customer behavior, restaurant performance, and market trends. The analysis leverages data-driven insights to answer key questions that can guide business strategies, enhance customer satisfaction, and optimize operational efficiency.

Predicting flight fares using machine learning to optimize pricing strategies and boost customer engagement. This project involves data preprocessing, feature engineering, model building, and hyperparameter tuning to create an accurate predictive model that can help platforms like MakeMyTrip enhance revenue by offering strategic discounts.