Build a predictive machine learning model that could categorize users as either, revenue generating, and non-revenue generating based on their behavior while navigating a website. In order to predict the purchasing intention of the visitor, aggregated page view data kept track during the visit along with some session is used and user information as input to machine learning algorithms. Oversampling/Undersampling and feature selection techniques are applied to improve the success rates and scalability of the models.

SVM, Logistic Regression, K-Nearest Neighbors Classifier, GaussianNB, Random Forest, XGBoost, DecisionTree Classifier, Ensembled Classifier, ExtraTrees Classifier, Voting Classifier

A Django Application Interface for Hate Speech Detection Mini Project

The SER model is capable of detecting eight different male/female emotions from audio speeches using MLP and RAVDESS model

No description provided.

No description provided.

This project uses supervised machine learning algorithms to build a model that predicts which IPL team has a higher probability of winning a match.

The above model has been created by using the titanic dataset present in the kaggle website and has been constructed by performing Eda and constructing various ml models inorder to reach to the best possible outcome

This project focuses on predicting the likelihood of a person having diabetes based on various health-related attributes. It employs a Voting Classifier, which combines the predictions of multiple machine learning models, to improve prediction accuracy.

Ensemble Learning to predict whether a patient is diabetic or not.