Data Scientist with 3+ years of experience in interpreting and analyzing data for driving business solutions. Proficient in distribution, predictive, and hypothetical modeling.
Overview
5
5
years of professional experience
Work History
Data Scientist (Fast Track Promotion)
Tiger Analytics
Jersey City, NJ
01.2024 - Current
Detected 9M+ patients with an 81% recall rate by applying advanced tree-based methods and clustering algorithms for customer segmentation based on lifestyle activities (Epsilon data). Enhanced segmentation by integrating sentiment analysis using Google Trends.
Designed and executed experiments for HPV and pneumococcal vaccine campaigns, leveraging A/B testing and multi-armed bandit algorithms, resulting in a 10x increase in campaign effectiveness.
Developed and deployed models using ensemble methods and deep learning neural networks on AWS SageMaker to identify high-probability vaccination patients.
Developed an advanced survey automation tool using sentence vectorization and OpenAI’s GPT-4 for generating dynamic customer segmentation and marketing strategies, with AWS Glue for data integration.
Associate Data Scientist
Tiger Analytics
Jersey City, NJ
05.2022 - 01.2024
Forecasted vaccine sales for the next four years with
Applied Bayesian inference and MCMC methodologies to assess the factors affecting doctors' decisions on vaccine brands, employing AWS SageMaker for efficient model training and evaluation.
Implemented the Cox Proportional-Hazards model alongside survival analysis methods for precise prediction of patient regimen switches. Identified a significant cohort of 200K patients with potential impacts surpassing $2 billion.
Collaborated with data scientists to develop a strategy for deploying ML and AI solutions at scale across an organization.
Implemented automated data pipelines for collecting and preprocessing large datasets from multiple sources such as LAAD and Komodo data.
Data Science Research Assistant
Proctor & Gamble (collaboration with University of Cincinnati)
Cincinnati, OH
09.2021 - 04.2022
Implemented XGBoost classifier on a database of 1.6 million personal care newsletters, selecting the top 20 relevant newsletters for the R&D team using predicted probabilities.
Developed and implemented a Power BI dashboard to measure newsletter effectiveness based on click data
Analyzed data from over 1000 sensor-embedded devices, utilizing time series modeling and A/B testing techniques in R&D. Discovered abnormal behavior patterns for a hair care product and provided recommendations to mitigate failure risks.
Analytics Consultant
IQVIA
Pune, India
06.2019 - 08.2021
Managed AWS enterprise data lake operations and supported client in restructuring and optimizing data storage, leading to $5 million USD cost reductions.
KPIs analyzed included market share, claim approval rates, and sales trends.
Spearheaded the development of an incentive compensation model (IC Model) for ~400 sales reps at national, state, and territory levels. Evaluated the influence of various factors such as market share and manager rating through Monte Carlo simulation.
Education
Master of Science in Business Analytics (Data Science Certification) -
University of Cincinnati
Cincinnati, OH
Bachelor of Engineering in Computer Science -
Savitribai Phule Pune University
Pune, India
Skills
Python, R, SQL, PySpark
Hadoop/Spark
Statistical Analysis
Time Series Analysis
Experiment Design
Machine Learning Techniques
NLP (Natural Language Processing)
Deep Learning
Data Visualization Tools
Machine Learning Pipeline
Timeline
Data Scientist (Fast Track Promotion)
Tiger Analytics
01.2024 - Current
Associate Data Scientist
Tiger Analytics
05.2022 - 01.2024
Data Science Research Assistant
Proctor & Gamble (collaboration with University of Cincinnati)
09.2021 - 04.2022
Analytics Consultant
IQVIA
06.2019 - 08.2021
Master of Science in Business Analytics (Data Science Certification) -