

Name: Jatin Mehra
Profile: Data Scientist
Email: jatinmehra119@gmail.com
Phone: (+91) 9910364780
GitHub: Jatin-Mehra119
Languages, Frameworks, and Tools
- Language: Python, C++, C, Java
- Database: MySQL
- Frameworks: Pandas, Scikit-learn, Numpy, Streamlit, Tensorflow
- Visualization: Matplotlib, Seaborn
- API Integration: FastAPI, FlaskAPI
- Tools: Jupyter Notebook, Visual Studio, Anaconda, Power BI, Microsoft Excel, Tableau
About Me
Results-driven Data Scientist with expertise in machine learning, natural language processing (NLP), and automation. Currently pursuing a Master of Science in Data Science, I specialize in building AI-powered solutions that enhance business efficiency and automate workflows. My portfolio showcases projects in predictive analytics, AI-driven automation, chatbots, and financial forecasting. Proficient in Python, Scikit-learn, Pandas, NumPy, SQL, Streamlit, and cloud computing.
Resume
My professional background
Summary
Jatin Mehra
Results-driven Data Scientist with expertise in machine learning, NLP, and automation. Specializing in AI-powered solutions that enhance business efficiency and automate workflows.
Education
Master of Science in Data Science
2025 - Present
Chandigarh University, Punjab, India
Bachelor of Computer Applications
2022 - 2025
Chandigarh University, Punjab, India
CGPA: 7.89
Professional Experience
Sales Operations Analyst
Dec 2022 - Present
NB ENTERPRISER (India Today Group), Delhi, India
- Designed daily inventory analytical reports using Excel, improving decision-making.
- Built KPI dashboards in Tableau, enhancing strategic insights for leadership.
- Automated bank statement reconciliation for 1000+ transactions/month, reducing manual work by 80% and 5x faster processing using pdfplumber, OpenPyXL, and Pandas.
- Developed the WMPL SAP Report Generator, a Python & Streamlit tool for automated SAP-compatible Excel reports.
Technical Skills
Programming
- Python
- SQL
- Java
ML & AI
- Scikit-learn
- PyTorch
- Hugging Face Transformers
- Pandas & NumPy
Web & API
- FastAPI
- Streamlit
- Flask
DevOps & Cloud
- Git & Docker
- Google Cloud Platform
- Hugging Face Spaces
- GitHub Actions
Projects
Explore my work across various domains of data science and AI
- All Projects
- Generative AI
- Machine Learning
- Data Analysis
- NLP
- Computer Vision
CrawlGPT 🤖
A powerful web content crawler with LLM-powered RAG (Retrieval Augmented Generation) capabilities. CrawlGPT extracts content from URLs, processes it through intelligent summarization, and enables natural language interactions using modern LLM technology.
🎥 AI-Powered YouTube Video Summarizer & Fact-Checker
This Web APP extracts captions from YouTube videos, generates summary, text embeddings, and allows users to search within podcast transcripts. It also refines the context and fact-checks claims using AI models and web crawlers.
PDF Insight Pro: RAG APP
PDF Insight Pro is a Streamlit-based web application that allows users to upload PDF documents and interact with them using AI-driven insights. The application processes PDFs to extract text and uses a language model to answer user queries about the content of the documents. Users can adjust model parameters, manage their uploaded documents, and interact with the AI to gain insights from the PDFs.
Plagiarism detector using Fine-tuned smolLM2 135M LLM
The smolLM2 135M Ins. MODEL was fine-tuned on the MIT Plagiarism Detection Dataset for improved performance in identifying textual similarities. This model provides binary classification outputs, indicating if two given documents are plagiarized or original.
 Project.webp)
Automated Essay Scoring System
Developed a state-of-the-art AI model for automated essay evaluation as part of the Kaggle AES competition. The project aimed to reduce manual grading effort and enhance the feedback process for students and educators.
Crypto Intelligence Pro
Crypto Intelligence Pro is an advanced market analysis tool for cryptocurrencies. It provides real-time price trends, sentiment analysis, technical indicators, and AI-powered market forecasts.



BrisT1D Blood Glucose Prediction Competition
Forecasted blood glucose levels one hour ahead using LightGBM regression, targeting participants with type 1 diabetes. Preprocessed data, addressed missing values, and engineered cyclical time-based features for time-series prediction.





Gas Turbine Electricity Prediction with LSTM Neural Networks
Developed a deep learning solution for predicting gas turbine electricity output using LSTM neural networks. The model processes time-series data to forecast power generation with high accuracy (RMSE < 370), outperforming traditional prediction methods and reducing the need for manual monitoring.

Cat/Dog Image Classifier
In this project I trained a model by using transfer learning and data augmentation to improve generalization. It uses MobileNetV2 as the base model with pre-trained weights from ImageNet then fine-tuned to enhance its accuracy.

Apps
Interactive applications I've developed
CrawlGPT 🤖
A powerful web content crawler with LLM-powered RAG (Retrieval Augmented Generation) capabilities. CrawlGPT extracts content from URLs, processes it through intelligent summarization, and enables natural language interactions using modern LLM technology.
Try it liveCrypto Intelligence Pro
Crypto Intelligence Pro is an advanced market analysis tool for cryptocurrencies. It provides real-time price trends, sentiment analysis, technical indicators, and AI-powered market forecasts.
Try it livePDF Insight Pro:RAG APP
PDF Insight Pro is a web application that allows users to upload PDF documents and interact with them using AI-driven insights.
Try it liveAPP for Plagiarism Detection using LLM
The app leverages a custom fine-tuned version of the SmolLM (135M parameters) that has been trained on the MIT Plagiarism Detection Dataset for improved performance in identifying textual similarities. This model provides binary classification outputs, indicating if two given documents are plagiarized or original.
Try it liveEssay Scorer Pro
Essay Scorer Pro is a Streamlit-based web application that uses AI to score essays on a scale of 1 to 6. Users can input essay text directly or upload a CSV file containing essays to get predictions. The model used for scoring is based on a pre-trained model from Hugging Face.
Try it liveCat/Dog Classifier APP
This app is a part of my project. It can classify Cats and Dogs images accurately.
Try it liveHeart Disease Predictor
A Web App that predicts whether the person has heart disease or not using Machine Learning.
Try it liveAPP for Detecting SPAM/HAM Email
A Web App that predicts whether the entered text/E-mail is Spam or not, Using Logistic Regression Algorithm
Try it live