Bengaluru, Karnataka · ananya.iyer@email.com · +91 98765 43210 · github.com/ananya-iyer
M.Sc Data Science graduate (2025) aiming for a Data Scientist role, skilled in Python, machine learning and SQL. Built a review classifier for mixed Hindi and English text that beat a simple baseline by 13 points.
M.Sc Data Science, Christ University, Bengaluru2023 – 2025 · CGPA 8.6
B.Sc Mathematics, Mount Carmel College, Bengaluru2020 – 2023 · 82%
Languages: Python, SQL
Libraries: pandas, scikit-learn, PyTorch
Areas: machine learning, NLP, model evaluation, forecasting
Cloud: AWS
Hindi–English review classifier | PyTorch, NLP | Team of 2Aug 2024
• An NLP model that tags product reviews written in mixed Hindi and English as positive, negative or neutral.
• Fine-tuned a small multilingual model in PyTorch on 8,000 reviews we labelled ourselves; hosted a demo on AWS.
• 84% accuracy on 1,000 held-out reviews, against 71% for a word-count baseline.
Loan default prediction | Python, scikit-learn | SoloJan 2025
• Trained machine learning models on a public dataset of 300,000 loan applications to flag likely defaulters.
• Cleaned the data with pandas and compared logistic regression with gradient boosting in scikit-learn.
• Wrote up the model evaluation: gradient boosting reached 0.81 AUC on a held-out set, and the five features that mattered most.
Data Science Intern, Shopwise, BengaluruMay 2024 – Jul 2024
• Wrote SQL to pull 18 months of orders and built a weekly demand forecasting model in Python for 40 products.
• The forecast missed by 12% on average, against 20% for the team’s spreadsheet method.