Shafaque Naaz

Analytical professional with expertise in Python, SQL, Power BI, Tableau, and Advanced Excel, backed by hands-on experience in machine learning, data visualization, and statistical analysis. Published an IEEE conference research paper and delivered projects in fraud detection, healthcare analytics, and predictive modeling. Adept at converting data into meaningful insights and building analytical solutions to address complex business problems.

Banking & Financial Analytics Intern - Indian Bank - New Delhi, India

(2026-05 - 2026-07)

• Developed an end-to-end Credit Risk Prediction solution using a dataset of 9,939 customer records to assess loan default risk and support data-driven lending decisions.
• Performed data cleaning, preprocessing, exploratory data analysis (EDA), feature selection, and SMOTE-based class balancing to improve data quality and enhance model performance.
• Built and compared Logistic Regression, Random Forest, and XGBoost models for credit risk prediction, with XGBoost achieving the best performance of 95% accuracy.
• Evaluated model performance using Accuracy, Precision, Recall, F1-Score, and ROC-AUC, where the final XGBoost model achieved 98% Precision, 91% Recall, and 95% F1-Score.
• Designed an interactive Power BI dashboard to visualize customer credit risk distribution, model performance, and key risk indicators, enabling effective business decision-making.

Master of Science - Banking and Finance Analytics - Jamia Milia Islamia (2024-08 - 2026-07)

Bachelor of Science - Data Science and Analytics - Sharda University (2021-10 - 2024-05)