Personal portfolio website of Avijit Jana — Data Scientist, AI Builder, and System Architect. Built with HTML, CSS, and JavaScript, this site highlights projects in data science, AI model deploymen…

Python CRM Product Management System with Streamlit UI, Pandas, Altair, and SQLite. Features include interactive dashboards, customer/product tracking, purchase management, 15+ analytics reports, d…

End-to-end Used Car Price Prediction project with a modular ML pipeline integrating Python, Pandas, NumPy, Scikit-learn, and EDA. Features robust preprocessing, feature engineering, and regression …

A Streamlit-based application leveraging Selenium to automate data scraping from Redbus, enabling efficient collection, analysis, and visualization of bus travel data for improved operational effic…

An end‑to‑end application leveraging Hugging Face pretrained models for multiple NLP and vision tasks—text summarization, next‑word prediction, story generation, chatbot, sentiment analysis, questi…

Basic FastAPI project with Uvicorn showcasing complete CRUD endpoints (GET, POST, PUT, DELETE). Ideal for beginners learning REST APIs, Python web development, and backend fundamentals. Lightweight…

Lightweight Retrieval‑Augmented Generation (RAG) demo with Streamlit UI. Ingest PDF/TXT docs, chunk & embed with Google GenAI or other providers, store in Pinecone, and query via chat. Optional Mon…

Machine learning project for classifying cybersecurity incidents (TP, BP, FP) using the GUIDE dataset. Includes data preprocessing, feature engineering, model benchmarking, and evaluation with macr…

This project predicts horse racing outcomes using machine learning models trained on historical race and horse data from 1990-2020. It explores feature engineering, odds analysis, and performance m…

A comparative benchmark of popular Convolutional Neural Network architectures (LeNet‑5, AlexNet, GoogLeNet, ResNet, Xeception) on MNIST, Fashion‑MNIST and CIFAR‑10 using PyTorch. Includes analysis …

SeqFlipAttention is a forward‑looking PyTorch demonstration of sequence‑to‑sequence learning enhanced by attention, trained on a synthetic reverse‑sequence task and complete with training scripts, …

Explore how Bitcoin market sentiment influences trader behavior and performance using real trading data and emotional indicators like the Fear & Greed Index. This project applies data science, clus…

A deep learning framework for automated diagnosis of Diabetic Retinopathy, AMD, and Glaucoma using a Hybrid Attention-CNN model. Combines ResNet50 with self-attention for enhanced accuracy and inte…

My clone repository

AI-powered assistant for querying financial documents (PDF, Excel, reports). Extracts key data, answers natural language questions, and generates insights from balance sheets, cash flow, and statem…

Data scientist and architect of insights, focused on transforming complex data into actionable intelligence. I build predictive models, design modular workflows, and curate authoritative technical …

Predicting future Domino’s sales using historical data to optimize ingredient ordering, reduce waste, prevent stockouts, and improve inventory and supply chain efficiency.

A Data Analysis project performing Exploratory Data Analysis (EDA) on Global Electronics' data to uncover insights that enhance customer satisfaction, optimize operations, and drive business growth.