A ML project based on aqi data

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

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.

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

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

Sentiment analysis

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 …

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.

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

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

Predicting Heart Disease using Machine Learning model

Implemented machine learning algorithms to analyze historical weather 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.

This project focuses on building a predictive model to estimate the risk of stroke in individuals based on demographic and medical features. Early prediction of stroke risks can help healthcare providers take preventive measures and prioritize patient care.

Identifying Human and Bot Accounts on Twitter Using Machine Learning | Fall 2024

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.

The implementation of naive Bayes classification model using Bayesian statistics