Hello!

I'm Harsh Gupta



A Data professional

LinkedIn GitHub

Name: Harsh Gupta

Job Role: Data Scientist

Experience: 2+ years

Address: Gurugram, Haryana, India

Skills

SQL 80%
PYTHON 90%
Deep Learning and Generative AI 70%
Statistical Analysis 90%
Machine Learning 95%

About

About Me

With over 1.5 years of comprehensive experience in the field of data science & analytics, accompanied by a bachelor's degree in data science and Programming from IIT Madras. Proficient in data analysis, statistical analysis, hypothesis testing,MLOps, Deep Learning & machine learning. Demonstrated success in leading impactful projects and providing effective mentorship.

  • Profile: Data Science & Analytics
  • Domain: IT
  • Education: Bachelor of Data Science and Applications
  • Language: English, Hindi
  • ML & DL Tools: Sklearn, tensorflow, Seaborn, Matplotlib
  • Other Skills: Cloud, Excel, PowerBi, Google Analytics & SEO
  • Interest: Teaching, Movies

0 +   Projects completed

LinkedIn

Resume

Resume

Experience


2022-2024

Stats & ML project Mentor

IIT Madras BS

  • I instructed statistics to more than 200 students in the IIT Madras BS program.
  • I assisted students with diverse Kaggle projects in Machine Learning, covering classification, regression, and NLP tasks.
  • I earned recognition as one of the top Teaching Assistants for statistics and Machine Learning, receiving a certificate for my contributions.

Dec 2023- April 2024

Data Science Intern

Metagauss

Metagauss is a Canadian startup specializing in WordPress site extensions and a range of web products.

  • Developed an innovative RAG system integrating ChatGPT and ChromaDB, hosted on AWS, leveraging internal document and hiring process data.



Education


2019-2022

Bachelor of Mathematics

Pratap University, Jaipur

Grade: 6.9 CGPA.

2021-2025

BS in Data Science & Applications

IIT Madras

Grade: 9 CGPA

Download CV

Projects

Projects

Below are the sample Data Analytics projects on SQL, Python, ETL & ML.

Upstox-API ETL project on AWS

Built an ETL pipeline on AWS to fetch, transform, and load Reliance stock data from Upstox API into S3. Utilized Amazon EventBridge for daily triggers, Lambda functions for data extraction and transformation, and AWS Glue for cataloging. Data extracted in JSON format is transformed into CSV for better analysis accessibility. Transformed data is stored in S3, cataloged in an AWS data catalog database, and analyzed using Amazon Athena.

E-commerce ML prediction.

I delved into e-commerce data using Python, conducting exploratory analysis to uncover insights. Additionally, I crafted a powerful Machine Learning model that achieved remarkable accuracy, propelling me to the top 15 out of over 800 participants in a Kaggle competition.

Library Management System - Flask web app

This Flask-based library management system enables users to browse, request, and manage books online. It provides two user roles: regular users and librarians, each with distinct privileges and functionalities. Features include secure authentication, book management (addition, deletion, and updates), feedback submission, and statistical analysis of library activities. The system ensures secure password handling, image uploading, and PDF downloading, with error handling and a user-friendly interface. It offers a robust platform for efficiently managing library operations in a digital environment.


Business Analysis of a Ration Shop Specializing in Cattle Feed

This project analyzes the operations of 'Mahendra Kumar and Brothers', a ration shop specializing in cattle feed distribution. It addresses challenges in inventory management and declining sales due to discontinued credit sales and increased competition. Through data analysis and tools like Pareto analysis and correlation, the project aims to identify factors influencing sales and profitability. The analysis covers a period from November 2022 to April 2023, with data collected manually from ledger records. Expected outcomes include actionable recommendations to mitigate challenges, reduce losses, and enhance overall business performance.

Web Scraping and Sentiment Analysis

This Python script facilitates web scraping and sentiment analysis tasks efficiently. It leverages libraries such as pandas, Beautiful Soup, and NLTK to extract text from URLs, preprocess it, and compute sentiment metrics. Users define input Excel files with URLs and output files for result storage. Upon execution, the script automates scraping, analysis, and result storage processes. Results, including sentiment analysis and text metrics, are presented comprehensively in an output Excel file. Customization options allow users to adjust stop words and word lists to suit specific needs. Overall, it's a powerful toolkit for gaining insights from web text effortlessly.

0 Projects
0 Mentored Students
0 Cups of coffee

More projects on Github

I love to solve business problems & uncover hidden data stories


GitHub

Contact

Contact Me

Below are the details to reach out to me!

Address

Gurugram, Haryana, India

Contact Number

8890817327

Email Address

[email protected]

Download Resume

resumelink



Have a Question? Click Here


  • Find me on