Portfolio - Moksh Jain

GenAI Project

E-Commerce Chatbot

Domain/Function: E-Commerce/Retrieval Augmented Generation

LLM-powered e-commerce chatbot that classifies user intent into product search, FAQs, or general queries. Converts natural language into filters/SQL for product retrieval, uses semantic search for FAQs, and generates grounded, conversational responses.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Other Tools

Chroma DB

SQLite

Streamlit

Semantic Router

Groq

A Streamlit UI of an e-commerce chatbot, depicting how it can help the users: • Product Search • FAQ • General Talk

The bot suggests Nike shoes based on the user's query, including price, discount, rating, and URL. Also, providing the source-grounded output to the general FAQs.

Project Details

An LLM-powered chatbot that enables users to find the perfect product just by defining filters and also responds to the FAQ queries along with general talk.

☑️ 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:
• Intent classification of a user using the 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗿𝗼𝘂𝘁𝗲𝗿 (threshold above 70%) + LLM to route query into 𝗙𝗔𝗤𝘀, 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝘀𝗲𝗮𝗿𝗰𝗵 and 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝘁𝗮𝗹𝗸.
• 𝗚𝗿𝗼𝗾-powered LLM for generating natural language responses and safe, read-only SQL queries.
• Structured product retrieval from SQLite by converting the user filter message into a query using LLM.
• Retrieval-Augmented Generation using 𝗖𝗵𝗿𝗼𝗺𝗮𝗗𝗕 to provide source-grounded FAQ responses.
• A 𝗳𝗮𝗹𝗹𝗯𝗮𝗰𝗸 𝗺𝗲𝗰𝗵𝗮𝗻𝗶𝘀𝗺 to store the query and the user-suggested route into sheets for further utterance modification.
• An interactive bot using 𝗦𝘁𝗿𝗲𝗮𝗺𝗹𝗶𝘁, accessible from different systems.

GenAI Project

Research Assistant

Domain/Function: Retrieval-Augmented Generation

An AI-powered RAG system that responds to the user query just by adding the URL. The system fetches the webpage, chunks the text, and stores it in Chroma DB. Extract similar chunks for the query and pass them to LLM to generate source-grounded output.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Other Tools

Python

Lang Chain

Hugging Face Embedding

Streamlit

Initially, it processes the URLs first by accessing the data ingestion pipeline. Once the data is ingested, it provides us with the relevant answers.

Here's the next question, asked by the bot, about the model capabilities and the purpose of launching the model.

Project Details

Manually scanning articles, Wikipedia pages, and long-form blogs is slow and inefficient. This project addresses that gap by building a Research Assistant powered by Retrieval-Augmented Generation (RAG), enabling users to submit up to three URLs and receive precise answers grounded strictly in those sources.

Features:
• Drop and process the URL to fetch article content.
• The content is fetched using Web Base Loader powered by Langchain.
• The extracted content is divided into chunks using the Recursive text splitter.
• Construct a vector store to store embeddings of these chunks into ChromaDB to enable swift retrieval of relevant content.
• Queries are created using the Langchain Prompt template and provide flexibility to the user and their queries.
• Interacts with the LLM(llama 3 via Groq) by inputting queries to receive answers with the source URL.

Deep Learning Project

Car Damage Detection

Domain/Function: Computer Vision

Developed an AI-based system using CNN and transfer learning to detect and classify damage into six categories. The model helps automate vehicle inspection with an accuracy of 80% and is deployed using Streamlit.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Other Tools

Python

Pytorch & TorchVision

Streamlit

Scikit-learn

The model shows this car has "Rear Crushed" damage.

The model shows this car has "Front Breakage" damage.

Project Details

This Project, "Car Damage Detection", aims to automate the process of visual inspection of car damage and classify the damage using Deep learning. This model is trained on a 2300-labelled car image dataset. To improve model performance, extensive data augmentation was performed, including contrast adjustment, rotation, and colour jittering.

Model Details:
1. It can classify the damage into six categories:
•Front Normal
•Front Breakage
•Front Crushed
•Rear Normal
•Rear Breakage
•Rear Crushed
2. The model uses a transfer learning approach with pre-trained weights of ResNet50.

Tools & Tech Stack:
• Torch & Torch Vision Training CNN models, Image transformations and data loading.
•Matplotlib: Visualizing different car images.
• EfficientNet-B0, ResNet50: Using Pre-trained weights with the help of transfer learning.
• Optuna: Hyper Parameter Tuning
• Scikit-learn: Model evaluation through accuracy and confusion matrix.

Machine Learning Project

Credit Risk Modelling

Domain/Function: Finance/Credit Risk Modelling

Built a Streamlit app that automates the process of credit risk evaluation using machine learning. This app is designed for a loan processing officer to check an applicant's creditworthiness for the applied loan by providing the default probability, credit score and rating associated with it.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Other Tools

Python

Scikit Learn

XGBoost

Streamlit

FastAPI

Increased Loan-to-income ratio and higher delinquent months are more prone to becoming a defaulter

Significantly low Loan-to-income ratio resulting in less default probability.

Project Details

This app enables a finance company to quickly assess the credit risk of loan applicants, reducing decision-making time while improving accuracy. It predicts the probability of default, generates a credit score (300–400) with corresponding ratings, and provides clear insights for decision-making.
The major contributors to finding the default probabilities are: Loan-to-income ratio, Credit utilization ratio and Delinquency ratio.

Features:
• Probability of the applicant being a defaulter
• Generates credit score & rating for easy interpretation
• Achieved >90% accuracy and 93% recall for identifying defaulters
• Strong model performance with AUC 98% and KS Statistic 85.9
• Built with Logistic Regression, XGBoost, SMOTE Tomek, Optuna

Leaveraged Tools:
• Python(Programming Language)
• Numpy, Pandas, Matplotlib, Seaborn (Data Visualization & Analysis)
• Sickit-learn, XGBoost, Optuna (Model training and tuning)
• Ml-flow (Experiment Tracking)
• Streamlit (Deployment)

Project video

Machine Learning Project

Health Care Premium Prediction

Domain/Function: Health Care

This Streamlit web application predicts the expected health insurance premium based on a user’s personal, health, and lifestyle details. It helps users estimate their annual premium by leveraging a machine learning model trained on real-world data.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Other Tools

Python

Sickit Learn

XGBoost

Streamlit

FastAPI

A patient is having a lower age, no medical history does not have much impact on the premium, but bmi category of Overweight increases some premium.

In this case a patient has relatively more age, with a severe medical history, and a gold plan increases the premium amount.

Project Details

Manually finalizing health premiums is time-consuming; for that, I have built an application that provides healthcare premium for each patient based on certain parameters, reducing decision-making time with low error. These major parameters include: Premium plan, Age, Medical history, and BMI category.

Features:
• Based on medical history, generates a risk score.
• Stremlit UI for the interface.
• Two different models for age groups(>18,>25)
• High accuracy of 97%.
• Error percentage of less than 10%.

Python Project

Expense Management System

Domain/Function: Fintech

Failed to track your daily expenses? Here is the solution to it: an 𝗘𝘅𝗽𝗲𝗻𝘀𝗲 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁 𝗦𝘆𝘀𝘁𝗲𝗺 It allows you to track your daily expenses and manage, and visualize them with some bar charts and pie charts built with Python, MySQL and Streamlit.

View Project
Engagement

View Project
on GitHUB

Other Tools

Python

SQL

Streamlit

FastAPI

Pandas

Adding expenses to the respective date with their categories and notes

The visual shows the total amount spent for a day with a category-wise distribution and a pie chart.

Project Details

Designed and deployed an interactive Expense Management app using Streamlit with a MySQL backend, where you can track your daily expenses of different categories. It will allow you to visualize your daily spending per category, monthly spending, etc.

𝗞𝗲𝘆 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:
  • Add & manage daily expenses with a multi-entry form
  • View & delete records in a structured tabular layout
  • Dashboard analytics with pie charts and bar graphs
  • Month-wise breakdown & category summaries
  • Clean and interactive UI with instant updates

𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄:
  • A SQL Backend server to connect with Python and to retreive and update expenses stored in the database
  • A FastAPI server to create a backend that communicates with Streamlit and SQL using localhost
  • Streamlit UI application that takes information from FastAPI and displays it to the frontend, through which the user communicates

Hello, I am

Moksh Jain

2

1

1

2

About

Key

My

E-Commerce Chatbot

Research Assistant

Car Damage Detection

Credit Risk Modelling

Health Care Premium Prediction

Expense Management System

My

Awards

Contact Me

Email

Github

Linkedin

Moksh Jain

Download Resume