Pravallika Reddy

>Built and deployed end-to-end machine learning systems to drive customer personalization and business decision-making >Developed recommendation engines that improved product engagement and conversion >Designed churn prediction models enabling proactive retention strategies >Implemented NLP models (BERT/transformers) to extract insights from customer feedback data >Engineered scalable data pipelines using PySpark for large-scale processing >Deployed production models on AWS SageMaker ensuring reliability and scalability >Built real-time analytics pipelines enabling faster operational insights >Automated model retraining workflows improving efficiency and reducing manual effort >Integrated ML models into production via REST APIs and microservices >Developed Tableau/Power BI dashboards to monitor KPIs and model performance >Conducted A/B testing to measure and validate business impact >Improved model performance through feature engineering and hyperparameter tuning

Applied advanced ML to protect the financial system — fraud detection, credit risk, and anomaly detection across high-volume transaction data. • Built fraud detection models that significantly improved detection accuracy and reduced financial losses across multiple transaction systems • Developed credit risk scoring models that improved lending decisions and reduced exposure to default risk • Designed anomaly detection systems to flag unusual transactional patterns in near real-time • Architected scalable ETL pipelines to ingest and transform large volumes of financial data from multiple sources • Maintained enterprise data warehouses and data lakes supporting organization-wide analytics • Ensured full compliance with financial data governance policies and regulatory standards

Used machine learning to improve patient outcomes — working directly with EHR data to build models that supported clinical decision-making. • Developed patient risk stratification models to predict health deterioration, enabling earlier clinical intervention • Applied clustering algorithms to segment patient populations for targeted care management programs • Built dashboards and reporting tools for clinical and operational teams to monitor patient health metrics • Processed and transformed large-scale EHR datasets, ensuring data quality and compliance with healthcare standards • Collaborated with clinicians and healthcare professionals to translate medical requirements into ML solutions