My Data, ML and AI Projects

Marketing Content Generation API Using Large Language Models

Large Language Models (LLMs) have revolutionized content creation for marketing purposes, enabling businesses to craft compelling blogs, emails, and social media posts efficiently. This project demonstrates an end-to-end solution for building a Python-based API that generates tailored marketing content based on user-defined inputs such as topic, format, emotion, and length.

Webpage-Based Question Answering API

The emergence of Large Language Models (LLMs) has significantly advanced Natural Language Processing (NLP) tasks, enabling complex interactions with textual data. This project showcases a Python-based API that leverages LLMs to answer user queries based on the content of a given webpage.To create an API that extracts relevant information from a specified webpage and generates concise, accurate answers to user queries. The solution also gracefully handles cases where the information is not available.

Predicting customer churn for a Telecom company

The project successfully developed a predictive model for customer churn, allowing the identification of customers likely to leave. By focusing retention efforts on this segment, the Telco service provider can improve customer retention rates, reduce the cost of acquiring new customers, and enhance profitability. The insights gained from the exploratory data analysis and the best-performing model provide actionable recommendations for targeted retention campaigns, ensuring better financial performance and customer satisfaction.

FRA - Default Prediction and Stock Market Risk Analysis

The FRA project consists of two parts. Part A focuses on default prediction and financial analysis, aiming to assess a company's ability to meet its debt obligations. Part B involves market risk analysis, where the mean and std deviation of stock returns are calculated to gain insights into stock performance and volatility. These analyses are valuable tools for investors, financial institutions, and stakeholders in making informed decisions related to creditworthiness and investment strategies

Customer Buying Patterns & Revenue Boost: Auto Parts & Grocery

This Project has two Parts. Part A & Part B. Part A aims to find the underlying buying patterns of the customers of an automobile part manufacturer based on the past 3 years of the Company's transaction data and hence recommend customized marketing strategies for different segments of customers. Part B involves conducting a thorough analysis of Point of Sale (POS) Data for providing recommendations through which a grocery store can increase its revenue by coming up with attractive combo & disco.

Deploying Machine Learning Model using Streamlit

This repository contains a machine learning project to predict sales for Big Mart stores using historical sales data. The application is built with Python and deployed using Streamlit to create a simple and interactive user interface.This project implements a Machine Learning model to predict loan eligibility based on user inputs such as gender, marital status, applicant income, and loan amount. The model is deployed as a web app using Streamlit and is accessible via a public URL using ngrok.

Building an Agentic Corrective RAG System with LangGraph

Building an Agentic Corrective RAG System with LangGraph This project will cover a full hands-on workflow and demonstration of how to build an Agentic Corrective RAG (CRAG) System with LangGraph.The idea is to couple a RAG system with a few checks in place and perform web searches if there is a lack of relevant context documents to the given user query. We can build this as an agentic RAG system by having a specific functionality step as a node in the graph and use LangGraph to implement it. Key steps in the node will include prompts being sent to LLMs to perform specific tasks as seen in the detailed workflow