EXPERIENCE | pragati

WORK EXPERIENCE

Developed content-agnostic Logistic Regression model for Tesla’s email targeting campaigns to focus on high-intent leads, reducing recipients’ volume by 56%, maintaining high demo drive & order conversions with a recall of 0.96, and lowering unsubscribes by 61%.
Collaborated with business stakeholders to identify gaps in the Repeat Repair classification model and enhanced its accuracy by 6% through DistilBERT model retraining with additional customer narrative text data.
Automated monthly customer feedback analysis using BERTopic for semantic clustering and Llama 3 70B for feedback summarization.

Designed and built an NLP pipeline to classify intracranial hemorrhage (ICH) from over 30k+ radiology reports, leveraging BERT and advancing research into state-of-the-art Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG)
Developed a predictive model on AWS SageMaker to analyze electronic health records (EHR) and identify high-risk, unscreened females for breast cancer, driving proactive health interventions.
Implemented automation procedures to streamline extraction and integration of CMS Hospital Care Compare files and internal data from various vendors, cutting down manual effort of one full-time employee by ∼ 2 weeks per quarterly cycle.

Contributed to research on 'Neighborhood Similarity Feature Space - NSFS ' under Dr. Joshua Peeples' supervision, in collaboration with the Los Alamos National Laboratory, to design a novel feature extraction kernel utilizing pixel similarity.
Built a PyTorch Lightning framework for benchmarking similarity, robustness, and performance in models like ConvNeXT and ResNet.

Automation: Led a team of 4 to create ETL pipelines on Azure for data migration verification, reducing ∼ 2 hours of daily manual work.
Customer Segmentation and Engagement: Implemented a clustering model to segment credit card customers based on spending behavior. Through hyperparameter tuning, feature engineering, and evaluation, accomplished 12% increase in customer engagement.
Fraud Detection Model Optimization: Revamped a Credit Card Fraud Classification model, reflected in a significant improvement in AUC-ROC score from 0.82 to 0.89. Contributed to the deployment of the optimized model, enhancing fraud detection capabilities.
Interactive Data Visualizations: Took the initiative to automate & optimize various SQL and Excel-based reports into interactive and real-time Tableau Dashboards. Thereby reducing preprocessing and query time, resulted in savings ∼ 50 hours/month.
Data Modeling: Designed data models and schemas for relational databases, optimizing query performance and storage efficiency.

• Tutored high school/UG level students as an independent contractor on the Chegg platform, achieving a 95% satisfaction rate.

• Experience in teaching over 60+ students and conducting 80+ lessons through the platform.

• Taught students SQL, Database Management, Python/C++ Programming, and guided them in solving projects and assignments