Harshit Kumar
@user.2503971
Data Science Analyst | NLP | Machine Learning
Thane, India
Harshit Kumar is an experienced data analyst skilled in coding and data science techniques to extract actionable insights, with expertise in Python, SQL, PySpark, Databricks, Azure, and NLP. At Dun & Bradstreet India, he has led impactful projects including the acquisition and management of 16 million MSME data points and an adverse media sentiment analysis pipeline, collectively saving over 70 lakhs in operational costs. He holds a Master of Science in Data Science from Symbiosis International University and is pursuing ongoing professional development in data analytics.
Experience
Data Science Analyst
Dun & Bradstreet India
Led acquisition of 16M data points on MSMEs, saving 35 lakhs. Ingested 14.7M data points. Spearheaded scraping initiative obtaining 2300 CINs. Fetched and validated 1.1M contact details, saving 30 lakhs. Implemented web scraping and NLP for sentiment analysis of 1.7M data points, saving 13 lakhs. Engineered scalable XML data parsing pipeline. Orchestrated daily web scraping operations, saving 6.7 lakhs. Designed automated quarterly BSE data extraction for 4332 companies, saving 17 lakhs.
Junior Data Analyst
Satori Group India
Identified and documented business rules and use cases. Used statistical methods to analyze data and generate business reports. Developed tables, views and materialized views using SQL. Worked on OCR to convert unstructured data to structured format using Python.
Data Science Intern
Grabbd Inc
Managing timelines of data science projects. Growth and retention analysis. Reporting and analysis with data enhancements and cleaning. Web scraping and data analysis for recommendation engine.
Education
Symbiosis International University
Master of Science
Data Science
IMS Proschool Pvt Ltd
PGDM
Data Science
Bharat Junior College, Thane
Bachelor of Science
Information Technology