Harshita Agrawal

About Harshita Agrawal

As a Data Scientist, I specialize in Machine Learning (ML), Natural Language Processing (NLP), and Large Language Models (LLMs) to address complex data challenges. My expertise includes building and deploying predictive models, automating data extraction pipelines, and implementing real-time analytics solutions. Proficient in tools like Python, ElasticSearch, NLTK, SpaCy, and scikit-learn, I develop scalable workflows that enhance data processing and automate business insights.My work revolves around developing sentiment analysis, brand extraction, and topic classification models with high accuracy. By leveraging LLMs and custom NLP pipelines, I’ve optimized text analysis, improving performance in tasks like author identification and text categorization. I have successfully built and deployed APIs for large-scale data processing, enabling organizations to automate decision-making and enhance operational efficiency.Additionally, I focus on optimizing data retrieval systems using ElasticSearch to ensure fast and reliable querying, facilitating real-time data filtration. Through automation of web scraping using Selenium, Instaloader, and Instagrapi, I’ve streamlined data collection processes, delivering actionable insights into user behavior and engagement across platforms. I am committed to delivering scalable solutions that empower businesses to make data-driven decisions and gain deeper insights into their operations.

Experience

1. Data Scientist

   Skribe

   May 2022 — Present · Delhi, IN

   As a Data Scientist at Skribe, I am responsible for developing and deploying end-to-end machine learning (ML) and Natural Language Processing (NLP) solutions to tackle complex data challenges. My role involves designing and automating robust data extraction pipelines using tools like Selenium, BeautifulSoup, and Playwright, enabling efficient collection of large-scale web data for analysis. I leverage ElasticSearch to implement optimized data filtration systems, improving retrieval efficiency and enabling real-time data querying for high-demand client requirements.In addition, I work extensively with Large Language Models (LLMs) to enhance data processing capabilities, applying NLP techniques such as topic modeling, sentiment analysis, and brand extraction. I have developed high-accuracy models for category identification and author recognition using frameworks like SpaCy and NLTK. By building and deploying APIs for automated data processing, I enable clients to integrate these insights seamlessly into their workflows, driving smarter, data-driven decision-making. My work ensures that complex datasets are transformed into actionable insights, optimizing business strategies and improving operational efficiency.

Education

• Jaypee Institute Of Information Technology

  M.tech, Data Analytics

  2019 — 2021