A collection of heterogeneous distance functions handling missing values.

A repository for various Data Science projects I've worked on, both university-related and in my spare time.

Data fetched by wafers is to be passed through the machine learning pipeline and it is to be determined whether the wafer at hand is faulty or not apparently obliterating the need and thus cost of hiring manual labour.

This project focuses on predicting customer churn in an e-commerce setting using machine learning techniques.

Feature Engineering with Python

This repository is a collection of basic code templates for Data Preparation. All codes I am sharing are from the practical exercises I did from the Data Science Infinity Program.

📘 This repository predicts OLA driver churn using ensemble methods—Bagging (Random Forest) and Boosting (XGBoost)—with KNN imputation and SMOTE. It reveals city-wise churn trends and key performance drivers, powering smarter, data-backed retention strategies for the ride-hailing industry.

This project focuses on predicting whether a customer will default on their credit card payment in the upcoming month. Utilizing historical transaction data and customer demographics, the project employs various machine learning algorithms to distinguish between risky and non-risky customers for better credit risk management.

This repository is totally focused on Feature Engineering Concepts in detail, I hope you'll find it helpful.

Data imputation is used when there are missing values in a dataset. It helps fill in these gaps with estimated values, enabling analysis and modeling. Imputation is crucial for maintaining dataset integrity and ensuring accurate insights from incomplete data.

What Are the Challenges and Solutions of Missing Data in Electronic Health Records?

No description provided.

Modelling the relationship between a player’s first-time eligible arbitration salary and multiple variables.

Predicting employee burnout using machine learning algorithms: Random Forest and k-Nearest Neighbors.

My Capstone for the HarvardX Course "Introduction to Data Science with Python"

Machine learning models for enhanced fraud detection in e-commerce transactions, exploring feature engineering, distance prediction, and clustering analysis.

Kaggle UK Used Car challenge

we perpuse a method to fill nan values using clustering

Streamlit app developed for bank customer deposit prediction, using a fine-tuned XGBClassifier model.

No description provided.

The company develops efficiency solutions for heavy industry. The model should predict the amount of pure gold extracted from gold ore. You have the data on extraction and purification. The model will help optimize production and eliminate unprofitable parameters.

Built a model to determine the risk associated with extending credit to a borrower. Performed Univariate and Bivariate exploration using various methods such as pair-plot and heatmap to detect outliers and to monitor the behaviour and correlation of the features. Imputed the missing values using KNN Imputer and implemented SMOTE to address the imbalanced data. Trained the model using KNN, Decision Trees, Logistic Regression and Random Forest to achieve the best accuracy of 93%.

No description provided.

This flask web app is used to detect if a wafer(sensor chip) is default or not based on sensor readings.

[Kaggle Submission] -Using XGBRegressor with shap, grid search and hyperopt to predict house prices

Analysis about Accident Aviation from 1962 up to 2023

Filling missed data-points with the most common values among nearest neighbors

No description provided.