About

        Me!

Hello, I'm Ananta Verma, a data scientist driven by curiosity, impact, and love for solving real-world problems with data. I recently graduated with a Master's degree in Data Science from the University of the Pacific, San Francisco. Throughout my academic and professional journey, I've specialized in predictive analytics, data wrangling, and machine learning, while continuously expanding my skill set to keep pace with evolving technologies.

I've developed hands-on experience with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) systems, and Multi-Agent Systems, building intelligent workflows using tools like CrewAI. My research on "Machine Learning Models for Early Detection of Cardiac Arrest Risk Factors" was published in the 2025 IEEE International Conference. I've also strengthened my cloud engineering foundation through AWS coursework, and expanded my big data expertise with Hadoop and Apache Spark.

From ELT pipelines and customer churn prediction to AI-powered travel assistant, I design robust, scalable solutions that bridge the gap between data and decision-making. I'm passionate about building data products that are technically sound, intuitive, and impactful—always looking forward to learning, creating, and making a difference.
‍
Key Projects:
‍
‍Customer Churn Data Analysis: This project focuses on predicting customer churn using machine learning models, including Random Forest and XGBoost.
‍
Veterans Affairs Benefits Portal: Developed a web-based system to assist veterans in navigating and claiming disability benefits.
‍

Research Publication:

"Machine Learning Models for Early Detection of Cardiac Arrest Risk Factors" - Published in IEEE International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), 2025.

Co-authored and presented research on early cardiac arrest prediction using ML models on real-time clinical data (n=1368, 60 features)

Achieved 98.17% accuracy with Random Forest, outperforming KNN, Logistic Regression, and XGBoost.

DOI- 10.1109/IC3ECSBHI63591.2025.10990532

‍
Technical Skills:
‍
‍Languages: Python, R, SQL
‍Tools & Frameworks: TensorFlow, Scikit-Learn, Pandas, Matplotlib, Numpy, FastAPI, Docker, Plotly, Pytorch, Streamlit, Flask, Power BI, Tableau, NLTK, Langchain,and AWS
‍Concepts: Machine Learning, Natural Language Processing, Neural Networks, Data Mining, Predictive Data Analytics, Clustering, LLMs, RAG, Data Wranlging, AI Agents

‍

‍Educational Background:
‍
‍Master of Science in Data Science, University of the Pacific
‍Bachelor of Technology in Mechanical Engineering (Minor in Data Science), Symbiosis Institute of Technology