To build a classification methodology to predict whether a website is a phishing website on the basis of given set of predictors.

A ML project based on aqi data

This project classifies and detects malicious websites by analyzing various factors such as the URL of the website, IP address, the geographic location of where the website is hosted and other factors.

This system integrates front-end (HTML, CSS, JavaScript) with Flask backend, using a CNN (VGG-16) for breast cancer classification, and SQL for data management.

A simple program for classification of fruits on basis of color using KNN.

Explore my Kaggle competition solution repository for the year 2912. Join in to help rescue passengers trapped in an alternate dimension!

This project is designed to identify fraudulent transactions with high accuracy.

Classifying Wine Quality Data Based on Different Supervised Learning Methods - Logistic Regression, Decision Tree, Random Forest & Support Vector Machine.

Built a predictive ML model for employee attrition using Python & scikit-learn on a 10K-row HR dataset. Tackled class imbalance with balanced weights across Logistic Regression, Random Forest, and Gradient Boosting hitting 82% ROC-AUC while spotlighting top risks like low job satisfaction, long commutes, and stalled promotions.

Steam is a video game digital distribution service with a vast community of gamers globally. A lot of gamers write reviews at the game page and have an option of choosing whether they would recommend this game to others or not. However, determining this sentiment automatically from text can help Steam to automatically tag such reviews extracted …

Predicting Heart Disease using Machine Learning model

Learning ML through real-world loan approval prediction: preprocessing, feature engineering, model comparison, hyperparameter tuning, and understanding why tree models dominate tabular data.

Collaborated with Davies Biological Sciences Lab at the University of New Brunswick to automate the manual sorting of 45k shadowgraph images captured underwater in the Bay of Fundy for research purposes. Utilized computer vision and deep learning to develop an ensemble model that achieved a 94.42% accuracy rate, striking an optimal False Positive-F

Building multi-class classification models to predict the type of "crop" and identify the single most importance feature for predictive performance.

Implemented machine learning algorithms to analyze historical weather data

Classification model to predict if the client will subscribe to a term deposit based on the given bank dataset

This project aims to predict customer churn using machine learning techniques in R. By analyzing customer data, we identify patterns and build models to help businesses improve customer retention strategies.

This is the repo for my fourth year Honour Thesis project repository

This project is an end-to-end solution for classifying emails as spam or not spam using machine learning techniques. The system is built with a Flask API serving a trained model and a React frontend for interacting with the service. Additionally, MLflow is integrated to track experiments.