The objective is to develop a model that accurately predicts whether users will cancel their tickets. Each cancellation incurs a fine for the ticket registration site from the passenger company.

This project utilizes advanced data analysis and machine learning techniques to predict equipment failures before they occur. The goal is to detect anomalies and possible defects in equipment and processes to enable preemptive maintenance, thereby reducing downtime and costs.

A model to identify hate speech (racist or sexist tweets) on Twitter

98% accurate - This stroke risk prediction Machine Learning model utilises ensemble machine learning (Random Forest, Gradient Boosting, XBoost) combined via voting classifier. We tune parameters with Stratified K-Fold Cross Validation, ROC-AUC, Precision-Recall Curves and feature importance analysis.