Data Analyst with experience in data cleaning, statistical analysis, exploratory data analysis, data visualization, and dashboard development. Proficient in Python, SQL, R, Excel, and Power BI, with experience analyzing datasets, automating reports, building interactive dashboards, and delivering actionable business insights.
Tata Steel – TinPlate Division
Apr 2026 · Jamshedpur
Cleaned, classified, and analyzed 500+ HR records using Excel, improving data accuracy and consistency by 30%. Automated monthly reporting and developed KPI dashboards using Pivot Tables and charts, reducing reporting time by approximately 4 hours per month. Performed exploratory data analysis on employee training data to identify trends and patterns, generating insights that supported HR scheduling and workforce planning decisions.
MSc., Data Science & Analytics
2024 – 2026
GPA: 8.48/10
MSc., Applied Statistics
2025 – Present
Bachelor of Science, Statistics
2021 – 2024
GPA: 8.7/10
Aug 2026. Technologies: Python, SQL, Power BI, Statistics. Used SQL to query and analyze a 255K+ record loan default dataset, examining borrower and loan-level attributes linked to default risk. Performed EDA and statistical analysis in Python, with Power BI dashboards to visualize key credit-risk indicators.
July 2026. Technologies: Power BI, Python. Cleaned and analyzed employee attrition data using SQL to identify key workforce trends and attrition drivers. Developed an interactive Power BI dashboard with KPI cards, slicers, and visualizations to communicate HR insights to stakeholders.
Oct 2025. Technologies: Python, Scikit-learn, Decision Trees, Logistic Regression. Applied EDA and statistical analysis on real-world accident data to classify severity trends. Built a Decision Tree model that achieved 100% test accuracy, 80% above baseline, and produced a stakeholder-ready visualization report identifying top severity drivers for policy consideration.
Jan 2026. Technologies: Python, R, ARIMA, ETS, XGBoost, LSTM. Built and validated an ETL pipeline for five years of stock data across three companies. Benchmarked ARIMA, ETS, XGBoost, and LSTM models using MAE, RMSE, and MAPE; the LSTM model achieved approximately 85% accuracy, outperforming all other models.