🚀 Senior Data Scientist at Citi Bank | 🎓 PhD Scholar in Data Science | 🏆 Kaggle Expert | ✍️ Blogger on AI & Big Data
Welcome to my GitHub! I specialize in building scalable machine learning solutions, automating data pipelines, and crafting insights using Big Data technologies. With over 6 years of experience, I thrive at the intersection of data science and engineering, creating impactful solutions for real-world problems.
- Developing credit card fraud detection models using XGBoost, PyTorch, and Hugging Face.
- Feature engineering, model optimization, and explainability for black-box models.
- Expertise in GenAI, transformers, and model interpretability.
- Analyzing large-scale datasets to derive actionable insights.
- Proficient in predictive modeling, time-series analysis, and exploratory data analysis.
- Experienced in distributed systems with Apache Spark, Hadoop, Hive, and Snowflake.
- Building scalable solutions to process terabytes of data seamlessly.
I love competing on Kaggle, where I tackle data challenges across domains. Check out my Kaggle contributions:
- Participated in Kaggle Competitions to solve real-world problems.
- Created reusable notebooks for predictive modeling, EDA, and feature engineering.
- LinkedIn: Indrajit Swain
- Medium: @indrajeetswain
- Twitter: @indrajeetswain
- Kaggle: My Profile
- Email: [email protected]
When I'm not training ML models, I love exploring GenAI advancements, reading research papers for my PhD or casually, writing blogs, and mentoring aspiring data scientists!