AmoghRamagiri
{ }
Data Scientist focused on shipping real ML systems: risk models, forecasting pipelines, and GenAI/RAG tooling. Currently a Master's student at George Washington University.
building systems that listen to data.
Data Scientist focused on shipping real ML systems: risk models, forecasting pipelines, and GenAI/RAG tooling. Currently a Master's student in Data Science at George Washington University. I care about the boring parts: clean data, honest metrics, and telling the truth about what a model can and can't do.
I care about the boring parts: clean pipelines, honest metrics, and interfaces that let humans stay in the loop. I've worked across risk modeling, sustainability analytics, and product, and I tend to ship the thing.
Good data science is 10% modeling and 90% telling the truth about what the data can and can't say.
where I've worked and studied.
A short trail of roles, research, and the occasional late-night pipeline fix.
work
Built a mortgage default prediction model (Random Forest) at 91% recall on high-risk applications. Led Azure (Data Factory, Synapse) migration and rebuilt 37+ Power BI dashboards on Microsoft Fabric.
Built SKU-level demand forecasting (XGBoost, 92% accuracy), cutting stockouts 13%. Engineered features from 2M+ customer records and ran A/B tests that lifted conversion 15%.
Built a multi-modal biometric auth system (DeepFace + MFCC, PyTorch) for offline Raspberry Pi deployment, +30% accuracy over baseline. Edge-to-cloud pipeline streamed records with sub-200ms latency.
Automated marketing reporting across 13+ clients (~75% less weekly effort). Real-time dashboards cut wasted ad spend 20%, and clustering identified 5 high-value cohorts that lifted conversion 12%.
education
CCAS Dean's Award. Coursework in ML, statistics, large-scale data systems, and deep learning.
AI/ML specialization. Coursework in algorithms, statistics, and computer vision, plus a capstone ML research project.
things I've built.
A mix of shipped products, ML research, and experiments. Each one taught me something I couldn't learn from a course.
Built an ML pipeline to predict student performance using academic and socio-economic data, achieving 87% accuracy. Automated deployment via AWS CodePipeline and Elastic Beanstalk, reducing manual effort by 80%.
Developed an interactive Streamlit app for analyzing university building energy data with ML models. Implemented Random Forest algorithms to identify consumption patterns.
Engineered dual-layer authentication system integrating DeepFace for facial recognition and MFCC features for voice recognition with 30% improved accuracy.
Researched and developed LDSVM (LR + DT + SVM) model for optimized prediction of Leukemia cancer cells using machine learning and deep learning techniques.
Built responsive portfolio website using modern web technologies with interactive animations and optimized performance for showcasing professional work.
Developed a credit card fraud detection model using supervised ML and ensemble methods (Logistic Regression, SVM, Random Forest, Bagging, Boosting). Achieved high accuracy with real-world data, minimizing false positives and boosting financial security.
what I work with.
Languages, frameworks, and habits I lean on daily. No prescription, just whatever matches the problem.
let's build something.
Open to roles, collaborations, and interesting problems. Drop a line or grab a slot on my calendar.