Chitranshu Harbola

Machine Learning Engineer | Data Scientist

Chennai, IN.

About

Results-driven Data Science student with a strong foundation in Machine Learning, NLP, and full-stack development, currently pursuing a Bachelor of Science at IIT Madras. Proven ability to leverage advanced analytical techniques and cloud platforms to build impactful solutions, from developing conversational AI platforms to optimizing data pipelines. Seeking to apply robust technical skills and innovative problem-solving to contribute to cutting-edge data science and machine learning initiatives.

Work

Research Project / Internship

|

Machine Learning Engineer - Intern

→

Summary

As a Machine Learning Engineer Intern, developed and fine-tuned language models to enhance personality-based responses and knowledge integration.

Highlights

Generated synthetic data using DSPy and fine-tuned Medium Language Models (MLMs) to effectively incorporate knowledge, enhancing model performance and applicability.

Implemented insights from Big5 Personality Traits research papers into Large Language Models (LLMs), significantly improving the nuance and accuracy of personality-based responses.

AlGurukul

|

Full Stack Web Developer

→

Summary

Led the development and deployment of an AI chatbot web application for a learning platform, integrating multiple APIs for seamless user interaction.

Highlights

Developed and deployed an AI chatbot web application using Streamlit, integrating multiple APIs to enable seamless and interactive learning experiences.

Managed AWS infrastructure, including EC2 instances, job scheduling, and storage solutions, ensuring high availability and scalability for the platform.

Contributed to key features of VidyaRANG, including YouTube chat integration, payment gateway implementation, user segregation, and CSV-based storage management.

Freelance / Self-employed

|

Machine Learning and Data Science Tutor

→

Summary

Provided personalized one-on-one tutoring and developed educational content in Data Science and Machine Learning for students and professionals.

Highlights

Conducted personalized one-on-one online GMeet sessions, educating students and working professionals in complex data science concepts.

Created and published educational content for the YouTube channel 'Harbola DataScience,' reaching a broad audience interested in data science.

Produced a comprehensive 3-hour video lecture series for a US-based startup, receiving high ratings and demonstrating expertise in content creation.

Research Project / Internship

|

Data Engineer - Intern

→

Summary

As a Data Engineer Intern, designed and implemented a robust data pipeline for real-time stock price extraction and cloud storage.

Highlights

Developed a scalable data pipeline to extract real-time stock prices from AngelOne API, ensuring efficient and timely data acquisition.

Utilized Google Cloud Platform (GCP) services and virtual instances to automate data collection and processing, optimizing data flow and reducing manual effort.

Stored extracted real-time stock data securely in Google Cloud Bucket, establishing a reliable foundation for subsequent analysis.

Freelance

|

Freelance Website Developer

→

Summary

Developed and deployed e-commerce and portfolio websites for local businesses, enhancing their online presence and reducing reliance on third-party platforms.

Highlights

Developed multiple e-commerce websites using WordPress for local businesses, including Minizone.in, to establish a direct online sales channel.

Designed and deployed custom portfolio websites for hotels and eyecare brands, significantly reducing their dependency on third-party booking and listing platforms.

Education

Indian Institute of Technology, Madras

→
Bachelor of Science Data Science

Courses

Data Science Fundamentals

Machine Learning

Deep Learning

Natural Language Processing

Statistical Modeling

Big Data Analytics

Kendriya Vidyalaya, Ranikhet, Uttarakhand

→
High School Diploma Science & Mathematics Grade: 81%

Courses

Physics

Chemistry

Mathematics

Computer Science

English

Army Public School, Ranikhet, Uttarakhand

→
Secondary School Certificate General Studies Grade: 92%

Courses

Mathematics

Science

Social Science

English

Hindi

Publications

VidyaRANG paper presentation

Conference on Digital Economy, Varanasi, India

Presented research on the VidyaRANG platform at the Conference on Digital Economy, showcasing innovative applications of conversational AI in the learning sector.

Extractive Text Generation paper presentation

Conference on Digital Economy, Varanasi, India

Presented a research paper on advanced extractive text generation techniques at the Conference on Digital Economy, contributing to the field of natural language processing and information retrieval.

VidyaRang - Conversational Learning-Based LLM Platform

arXiv

Authored and published a research paper detailing the development and capabilities of VidyaRang, a novel conversational learning platform powered by Large Language Models, contributing to advancements in educational AI.

Peer-reviewed paper in AIMLSystems 2024

AIMLSystems 2024, Louisiana, USA

Had a peer-reviewed paper accepted for presentation at AIMLSystems 2024, a prestigious conference, validating research rigor and contribution to the AI/ML community.

Languages

Hindi

English

Skills

Libraries

Numpy, Pandas, Matplotlib, NLTK, BeautifulSoup, Selenium, Flask, Scikit-Learn, TensorFlow, PostgreSQL, Streamlit.

Technologies

AWS, Google Cloud Platform (GCP), Linux.

Programming Languages

Python, CSS, HTML, SQL.

Data Science & Machine Learning

Machine Learning, Deep Learning, Natural Language Processing (NLP), Predictive Analysis, Web Scraping, Data Preprocessing, Exploratory Data Analysis (EDA), Data Cleaning, Data Visualization, Personality Modeling, Data Engineering, Cloud Storage.

Web Development

WordPress, E-commerce Platforms, Portfolio Websites.

Interests

Hobbies

Travelling, Cooking, Learning skills.

Professional Interests

Business, Startups, Research.

Projects

E-commerce Advertisement Analysis

→

Summary

Conducted predictive analysis on online advertisement impressions based on various factors using scraped data from Facebook Ads Library.

Sentiment Analysis on YouTube Comments

→

Summary

Developed a sentiment analysis model for YouTube comments, utilizing NLP techniques for data extraction and preprocessing.

Zomato Dataset Exploratory Data Analysis

→

Summary

Conducted comprehensive exploratory data analysis (EDA) on a Zomato dataset, focusing on data cleaning, visualization, and handling missing values.