Headline

Data Scientist | Data Analyst | Machine Learning Engineer | Python · SQL · NLP · LLM | Kaggle Expert Top 3% | Power BI

About

I started with a question most students never ask: Why does this data exist, and what is it trying to tell us? - That question took me from a B.Tech classroom in Anna University Chennai to building ML systems that processed 50,000+ records, detected speech patterns in 8,000+ audio samples, and earned me a rank of Top 3% globally on Kaggle — among 57,000+ data scientists worldwide. - Along the way, the Tamil Nadu Government noticed. I received a ₹10,000 Research Grant to build an AI-OCR system preserving handwritten historical documents — one of the most meaningful things I've built. Here's what I bring to a team: 🔹 Machine Learning — Random Forest, XGBoost, BERT, Neural Networks (81–88% accuracy on real-world datasets) 🔹 NLP & Generative AI — Sentiment analysis, text classification, transformer pipelines 🔹 Data Analytics — SQL, Power BI, Python — turning raw data into decisions 🔹 Fast execution — From data to deployed model, end to end I'm not looking for a role to learn the basics. I've already done that. I'm looking for a team that has hard problems and wants someone who will care deeply about solving them. Open to Data Scientist, Data Analyst and Machine Learning Engineer roles across any industry — India (Gurugram, Bangalore, Mumbai, Hyderabad, Pune, Ahmedabad) and Remote globally. 📩 prashantkumaryt53@gmail.com

Location

Gurugram

Work experience

Machine Learning Researcher & Kaggle Notebook Expert at Kaggle, Aug 2024 - Present · 1 yr 11 mos, India, - Ranked Top 3% globally (2,044 / 57,125 participants) — Kaggle Expert status with 7 medals - Built 10+ end-to-end ML pipelines covering data preprocessing, feature engineering, model training and evaluation - Specialized in NLP, predictive modeling and classification using Random Forest, XGBoost, BERT and Neural Networks - Published high-quality notebooks recognized by the Kaggle community across competitions and datasets - Applied Python, Pandas, Scikit-learn, TensorFlow on real-world business datasets

Machine Learning Intern at Suvidha Foundation (Suvidha Mahila Mandal), Dec 2024 - Feb 2025 · 3 mos, India, - Built Hindi stuttering detection system analyzing 8,000+ speech samples with 82% accuracy using Machine Learning algorithms and NLP techniques. - Reduced manual assessment time by 45%, enabling therapists to evaluate 3x more patients daily through automated ML-powered speech analysis. - Developed customer churn prediction model analyzing 7,000+ telecom records achieving 81% accuracy, identifying 20% high-risk customers for targeted retention. - Applied feature engineering and statistical analysis using Python (Pandas, Scikit-learn, XGBoost) improving model performance through data-driven optimization techniques. - Partnered with 5+ clinical therapists for ethical data annotation, ensuring responsible AI deployment in healthcare and business analytics settings.

AI & Data Analysis Intern at Edunet Foundation, Oct 2024 - Nov 2024 · 2 mos, India, - Deployed AI-powered tourism chatbot handling 20,000+ queries with 89% accuracy using Logistic Regression, TF-IDF vectorization, and NLP techniques. - Automated 70% of customer inquiries saving 15 hours weekly, eliminating 2-hour wait times and improving tourist support efficiency significantly. - Developed sentiment analysis engine processing 10,000+ customer reviews achieving 88% accuracy using BERT Transformer and traditional ML classification models. - Engineered NLP pipeline with tokenization, text preprocessing, and JSON structuring enabling multi-language scalability for global tourism expansion. - Built end-to-end machine learning workflow from data collection to model deployment using Python, NLTK, Transformers, and statistical validation.

Data Science Intern Job Simulation at Boston Consulting Group (BCG), Sep 2024 - Oct 2024 · 2 mos, India, - Completed BCG Data Science consulting simulation analyzing business problems using machine learning, predictive analytics, and statistical modeling techniques. - Applied data-driven approaches developing analytical frameworks for strategic decision-making and business intelligence solutions. - Leveraged Python and SQL for data analysis presenting insights and recommendations to solve complex consulting challenges.

Education

Bachelor of Technology - B.Tech, Information Technology, Anna University Chennai

Intermediate, Non Biology, Chhattisgarh Board of Secondary Education (CGBSE)