Rewati Sinha
About Rewati Sinha
Rewati Sinha is a Data Scientist II - Lead at Trellance in Tampa, Florida, with a strong background in machine learning and data analytics. She holds a Bachelor of Engineering in Electronics and Communications Engineering and a Master of Science in Business Analytics & Information Systems.
Work at Trellance
Rewati Sinha has been employed at Trellance since 2020, where she currently holds the position of Data Scientist II - Lead. In this role, she has spent the last two years leading data science initiatives. Her work focuses on developing insights-based data models, including Member Attrition, Product Propensity, and Member Segmentation. Sinha has designed and implemented an end-to-end ML Ops process that encompasses model development, training, deployment, monitoring, and inference capabilities.
Education and Expertise
Rewati Sinha earned her Bachelor of Engineering (B.E.) in Electronics and Communications Engineering from the Bangalore Institute of Technology, completing her studies from 2008 to 2012. She further advanced her education by obtaining a Master of Science (MS) in Business Analytics & Information Systems from the University of South Florida in 2017. Sinha's expertise includes conceptualizing and executing machine learning pipelines and applying unsupervised learning techniques for clustering members based on financial interactions.
Background
Before joining Trellance, Rewati Sinha worked as a Business Intelligence Analyst at Ultimate Medical Academy from 2018 to 2020. She also served as a Graduate Teaching Assistant and Research Assistant at the University of South Florida in 2017. Earlier in her career, she worked at Tata Consultancy Services as a BI Analyst and QA Analyst from 2012 to 2015. This diverse background has equipped her with a strong foundation in data science and analytics.
Technical Skills and Projects
Rewati Sinha is proficient in managing proof-of-concepts using various tools such as Dataiku, Azure ML Studio, and Alteryx to create a cloud-based AI/ML platform. She has demonstrated her skills in designing scalable machine learning models and implementing an efficient ML governance framework between Dataiku and Snowflake. Additionally, she is skilled in training and fine-tuning ensemble models, including trees, XGBoost, LightGBM, and Deep Learning models.