🚀 Passionate about data-driven decision making
💡 2+ years of experience in Data Analytics & Machine Learning
📊 Skilled in:
    🔹 Python | SQL | Tableau | Power BI | Excel | Data Modeling | AI/ML
🌟 Built models using:
    🎯 Random Forest | XGBoost | Logistic Regression | SVM | KNN
📈 Created interactive dashboards in Tableau & Power BI

🔹 Customer Churn Prediction for DTH Customers - This project aims to develop a predictive churn model for a DTH provider facing intense competition. By analyzing customer data, the model identifies at-risk accounts, allowing the company to implement targeted and cost-effective retention strategies. With the potential to lose multiple customers per account, minimizing churn and maximizing retention are critical goals. The project ensures profitability, preserves revenue, and enhances customer satisfaction, helping the company maintain its competitive edge through personalized campaigns in a highly competitive market. Developed predictive models using eight different algorithms, including XGBoost, Random Forest, LDA, Logistic Regression, KNN, and SVM, while employing the SMOTE oversampling technique to address class imbalance. Improved retention by 15% using **Random Forest with SMOTE, achieving 97% accuracy.

🔹 Credit Default Prediction and Stock Market Risk Analysis - The FRA project consists of two parts. Part A focuses on credit default prediction, aiming to assess a company's ability to meet its debt obligations. Part B involves market risk analysis, where the mean and std deviation of stock returns are calculated to gain insights into stock performance and volatility. These analyses are valuable tools for investors, financial institutions, and stakeholders in making informed decisions related to creditworthiness and investment strategies.

🔹 Forecasting Wine Sales company - Forecasted wine sales using ARIMA and SARIMA models based on 5 years of historical data. Cleaned and decomposed the data to analyze trends and seasonality, achieving 92% accuracy. Provided sales predictions with 95% confidence intervals, resulting in a 15% reduction in overstock and improved demand planning during peak seasons.

• Languages: C/C++, Java, SQL, Python
• Machine Learning: Classification, Regression, Clustering (Decision Trees, NLP, PCA)
• Data Visualization: Tableau, matplotlib, seaborn, Power BI, MS Excel (Advanced), PowerPoint
• Statistical Methods: EDA, Outlier Detection, Hypothesis Testing, ANOVA, Feature Engineering, Time Series Forecasting
• Communication & Collaboration Tools: Slack, JIRA, Confluence

📌 Deakin University, Australia (Oct 2024 - Present)
🎓 Master's Degree in Data Science (Online)

📌 The University of Texas at Austin, United States (Sept 2023 - Sept 2024)
🎓 Post Graduate Program in Data Science and Business Analytics (Online) - CGPA: 3.97/5.00

📌 Kalinga Institute of Industrial Technology, Bhubaneshwar (July 2019 - June 2023)
🎓 Bachelor of Technology in Electronics and Telecommunication - CGPA: 8.62/10.00

• 🏅 Data Analysis using Excel - Link
• 🏅 SQL (Intermediate) - HackerRank
• 🏅 SQL (Advanced) - HackerRank
• 🏆 Ranked 5th among 180 students in UT Austin's Data Analytics Program - Certificate

💡 Thanks for stopping by! Keep exploring and analyzing! 🚀