Rahul Bonagiri
Data Analyst @Capital One
Signup · Get unlimited contacts
WORK HISTORY
Data Analyst @Capital One
US
Designed classification models using Logistic Regression and XGBoost to predict credit delinquency, improving risk detection accuracy by 20% Enhanced ML-based credit scoring models to identify high-risk transactions across 100M+ records per day Created behavioral features such as spending velocity and credit utilization to improve model precision by 15% Implemented anomaly detection techniques to flag suspicious transaction patterns, reducing fraud false positives by 22% Evaluated model performance using cross-validation and ROC-AUC analysis, increasing prediction stability by 18% Deployed NLP pipelines for transaction text classification and sentiment analysis, improving fraud detection coverage by 25% Built a GenAI summarization solution using OpenAI APIs and RAG workflows, reducing manual document review time by 30% Established automated retraining and batch scoring workflows in Databricks, minimizing model drift by 20% Integrated ML and GenAI outputs into Snowflake and Power BI dashboards for real-time risk monitoring
EDUCATION
Christian Brothers University
Master's Degree, Master of Science in Data Science
ABOUT RAHUL BONAGIRI
Data Analyst with 5 years of experience delivering advanced analytics solutions across banking, financial services, and insurance domains. Strong expertise in Python, SQL, and PySpark, with hands-on experience applying Machine Learning, NLP, and Generative AI techniques to solve complex business problems in fraud detection, credit risk modeling, customer segmentation, and predictive analytics.Experienced in exploratory data analysis, feature engineering, model validation, and cross-validation, with a strong focus on building reliable and explainable models. Proven ability to integrate ML and GenAI outputs into Snowflake and Power BI dashboards to support real-time risk monitoring and data-driven decision-making.Hands-on experience across modern analytics platforms including Databricks, Snowflake, Apache Spark, Delta Lake, and cloud environments (Azure, AWS, GCP). Known for building scalable data pipelines, automating model retraining workflows, and collaborating closely with data scientists, engineers, and business stakeholders.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.