Regression model building and forecasting in R

This repository contains machine learning projects. The code for each project is provided, and the explanations can be found in the ReadMe.md file of each project !

End-to-end Predictive Analytics ML Project

📊🚀 Explore the Data Science Universe! Unlock insights and master data skills with hands-on assignments spanning machine learning, visualization, and more. Your journey to becoming a data expert starts here! 🎯💡 DataScienceJourney

Data Science 2023-24

Analyzed customer churn using transaction data. Built ML model to predict lapses. Dataset includes customer status, collection/redemption info, and program tenure. Delivered business presentation outlining modeling approach, findings, and churn reduction strategies.

Data Enthusiast | Predictive Modeler | Turning Insights into Strategies

Autoregressor: simple and robust time series model selection

End-to-end machine learning pipeline to predict daily sales for Rossmann stores using historical, promotional, and store metadata.

Data Science Project (Logistic Regression M7)

Full ENM framework with improved tuning, model performance assessment and selection. Based on MaxEnt, but transferrable to any presence-only ML algorithm.

Solution in the form of a tutorial article wherein the key decisions made in conducting a CFA are validated through recent literature and presented within a dynamic document framework.

A modular AutoML engine for automated model training, tuning, and benchmarking.

Bank Customer Churn Prediction with MLflow and MLOps

End-to-end Predictive Analytics ML Project

This project aims to predict the success of mobile applications on the Google Play Store using machine learning. By analyzing various features such as app category, rating, number of installs, size, type (free or paid), and content rating, the model can classify whether an app is likely to be successful or not.

Using linear regression models to assess the most important aspects of winning baseball

A machine learning project to predict medical insurance charges based on user features like age, BMI, and smoking status. Used Gradient Boosting Regressor for accurate cost prediction. Streamlit app enables real-time, interactive user input and predictions. Built with Python, Pandas, scikit-learn, and joblib.

Time series analysis on the United States Housing Price Index data using ARIMA models

A Spark Streaming and Kafka-based project for processing health data in real-time. Includes a machine learning pipeline for predictions, Dockerized infrastructure, and scripts for data ingestion, model training, and streaming pipelines.