This document describes a fake news prediction model created by Garima Saigal. The objectives are to identify and counteract fake news in real time using natural language processing and machine learning. Existing systems were explored and analyzed for their model focus, lack of visual representations, simplicity, and limited interpretability. The proposed system aims to improve on these areas with convenience, visual representations, simple prediction, and high accuracy. The workflow involves exploring key concepts like logistic regression for binary classification of news and confusion matrices to evaluate model performance. The technology stack uses Python libraries for data preprocessing, modeling, and visualization of results from a news articles dataset to classify real and fake news.