Padmavathi Moorthy

Background

About Padmavathi Moorthy

I transformed scattered financial data into automated forecasting engines that boosted cash visibility by 30% and cut reporting time from hours to minutes—while architecting ML models that achieved 99.99% accuracy in cybersecurity threat detection across 1M+ daily events. Here’s how I help organizations unlock production-ready machine learning. As a results-driven Data Science and ML professional with expertise in healthcare, finance, and cybersecurity, I architect end-to-end ML solutions that deliver measurable impact. Currently pursuing my MS in Data Science at SUNY Buffalo, I drive innovation through 15+ projects spanning forecasting, anomaly detection, and advanced AI implementations. Core strengths: Production ML Excellence Proficient in Python, TensorFlow, PyTorch, and MLOps, I’ve built models achieving 99.9% accuracy in threat detection, 92% precision in medical imaging, and F1 scores of 0.855 in decision support. My automated solutions cut manual processes by 85% and improved forecast accuracy by 25% through time series modeling, deep learning, and LLM integration. End-to-End Pipeline Architecture Using Snowflake, Spark, Hadoop, and cloud platforms, I engineered multi-tenant ETL pipelines processing 55M+ records—reducing scoring latency from 10 minutes to under 1, handling 1M+ daily transactions, and sustaining 99.9% API uptime. AI-Powered Business Intelligence I translate technical complexity into scalable solutions. Highlights: LLM-powered financial insights automating 85% of analysis, anomaly detection auto-scaling to 50 nodes, and dashboards improving forecast accuracy by 18% across 20+ stakeholders. Cross-Domain Innovation From CNN-based medical image similarity models processing 1,200+ images to hybrid pricing for 55M+ NYC taxi records, I apply CV, NLP, and ML to challenges in forecasting, risk, cybersecurity, and decision support. Recent highlights: BCNF-normalized database schemas with automated risk scoring, GPT-2-based AI music generation, real-time churn prediction for financial institutions, and research on robust fare prediction with XGBoost, GAT, and TimesNet. Passionate about bridging research and practice, I’ve delivered 15+ AI systems—optimizing supply chains, enhancing fraud detection, and building recommendation engines. My goal: transform data challenges into lasting competitive advantages.#DataScience #MachineLearning #MLOps #ArtificialIntelligence