Ishan Attri

• Analyzed multi-million-row datasets using SQL (Hive, Presto) to support analytics and ML decision systems.
• Built classification and segmentation models (Logistic Regression, Random Forest, Gradient-based models),
improving key model metrics by 8-12 percent over baseline.
• Applied feature engineering (missing value treatment, categorical encoding, feature selection), reducing overfitting
by approximately 15 percent.
• Evaluated model performance using Precision, Recall, F1-score, Accuracy, and AUC to support data-driven
decisions.
• Optimized complex SQL queries, reducing execution time by 20-30 percent and improving pipeline reliability.
• Worked with cross-functional teams to convert analytical findings into actionable business recommendations.
Tech Stack: Python, SQL, Hive, Presto, Pandas, NumPy, Scikit-learn