Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Sudheer Kumar Vangapandu, a data scientist with over 5 years of experience driving business outcomes in finance and healthcare. I specialize in analyzing large datasets to uncover patterns, solve complex problems, and inform strategic decisions. My toolkit includes Python, R, SQL, and the SciPy stack (NumPy, Pandas, Matplotlib), along with a strong foundation in statistical methods, time series analysis, and dimensionality reduction. I thrive in cross-functional teams and enjoy translating technical insights into actionable business recommendations. I focus on practical process improvements, cost reductions, and understanding customer and patient behavior through data, with hands-on experience deploying scalable ML pipelines on AWS and building production-ready dashboards with Power BI and Plotly.…I am Sudheer Kumar Vangapandu, a data scientist with over 5 years of experience driving business outcomes in finance and healthcare. I specialize in analyzing large datasets to uncover patterns, solve complex problems, and inform strategic decisions. My toolkit includes Python, R, SQL, and the SciPy stack (NumPy, Pandas, Matplotlib), along with a strong foundation in statistical methods, time series analysis, and dimensionality reduction. I thrive in cross-functional teams and enjoy translating technical insights into actionable business recommendations. I focus on practical process improvements, cost reductions, and understanding customer and patient behavior through data, with hands-on experience deploying scalable ML pipelines on AWS and building production-ready dashboards with Power BI and Plotly.

Sudheer Kumar Vangapandu

Data Scientist, Data Analyst, AI Engineer, +1





I am Sudheer Kumar Vangapandu, a data scientist with over 5 years of experience driving business outcomes in finance and healthcare. I specialize in analyzing large datasets to uncover patterns, solve complex problems, and inform strategic decisions. My toolkit includes Python, R, SQL, and the SciPy stack (NumPy, Pandas, Matplotlib), along with a strong foundation in statistical methods, time series analysis, and dimensionality reduction. I thrive in cross-functional teams and enjoy translating technical insights into actionable business recommendations. I focus on practical process improvements, cost reductions, and understanding customer and patient behavior through data, with hands-on experience deploying scalable ML pipelines on AWS and building production-ready dashboards with Power BI and Plotly.…I am Sudheer Kumar Vangapandu, a data scientist with over 5 years of experience driving business outcomes in finance and healthcare. I specialize in analyzing large datasets to uncover patterns, solve complex problems, and inform strategic decisions. My toolkit includes Python, R, SQL, and the SciPy stack (NumPy, Pandas, Matplotlib), along with a strong foundation in statistical methods, time series analysis, and dimensionality reduction. I thrive in cross-functional teams and enjoy translating technical insights into actionable business recommendations. I focus on practical process improvements, cost reductions, and understanding customer and patient behavior through data, with hands-on experience deploying scalable ML pipelines on AWS and building production-ready dashboards with Power BI and Plotly.

Available to hire

I am Sudheer Kumar Vangapandu, a data scientist with over 5 years of experience driving business outcomes in finance and healthcare. I specialize in analyzing large datasets to uncover patterns, solve complex problems, and inform strategic decisions. My toolkit includes Python, R, SQL, and the SciPy stack (NumPy, Pandas, Matplotlib), along with a strong foundation in statistical methods, time series analysis, and dimensionality reduction.

I thrive in cross-functional teams and enjoy translating technical insights into actionable business recommendations. I focus on practical process improvements, cost reductions, and understanding customer and patient behavior through data, with hands-on experience deploying scalable ML pipelines on AWS and building production-ready dashboards with Power BI and Plotly.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Data Scientist at Freddie Mac

July 1, 2024 - Present

Led end-to-end ML initiatives across data preparation, model development, validation, and deployment to scale campaign personalization and improve conversion rates by 15%. Defined KPIs and performance metrics to monitor model effectiveness, informing executive decisions in marketing optimization and credit risk management. Built reproducible Python and SQL pipelines to accelerate analytics across business teams. Designed and deployed scalable ML infrastructure on AWS, reducing release cycles by 30% and cutting compute costs through automation. Managed version control and integration testing with Jenkins CI/CD to enhance production reliability. Engineered features and performed data quality checks, cleansing, and transformation to improve model precision and reduce data drift. Delivered business-facing visualizations using Power BI, Matplotlib, and Seaborn, improving stakeholder visibility into marketing and risk metrics. Implemented Snowflake analytics for fraud detection and inventory

Data Scientist at Aspire Fintech

November 1, 2022 - October 15, 2025

Executed risk monitoring by analyzing sensitive user activity data across sources to support regulatory compliance. Designed an interactive Plotly dashboard to track early engagement and inform credit strategy decisions. Applied process mining with pm4py to identify bottlenecks in loan applications, increasing processing efficiency by 25% and customer satisfaction by 30%. Performed risk-profile analyses using metadata and behavioral data, segmenting users with K-Means to improve credit evaluation accuracy. Led A/B testing for credit term modifications across segments, achieving a 15% lift in product adoption. Developed classifiers (Logistic Regression, Decision Trees, KNN, Naive Bayes) for credit scoring and data preprocessing in pandas to improve data quality and reduce variance.

Data Scientist at Hexaware Technologies

January 1, 2020 - October 15, 2025

Led a fraud detection initiative analyzing 4M+ transactions by integrating data from payment gateways, customer profiles, and historical fraud records. Applied normalization, scaling, and supervised models (Logistic Regression, Decision Trees, Random Forest, XGBoost, Autoencoders) to improve detection precision and reduce false positives. Employed SVM, Random Forest, Naive Bayes, and KNN for customer risk scoring and segmentation. Used BERT-based methods to extract structured data from unstructured medical documents (500K entries), reducing missing data and improving reporting. Built NLP workflows with NLTK for entity recognition, sentiment tagging, and keyword tagging. Architected Kafka and Spark pipelines for large-scale log analysis and real-time anomaly detection dashboards. Created a modular ETL pipeline transforming 2.5+ GB of claims data into analytics-ready formats.