This document summarizes a research paper that proposes a machine learning approach to detect fake reviews on Amazon using the k-nearest neighbors algorithm. It first discusses how fake reviews can negatively impact both customers and vendors. It then reviews related work on fake review detection using techniques like sentiment analysis, logistic regression, and support vector machines. The document outlines the methodology of the proposed system, which will scrape review data, extract relevant information, input the data into a machine learning model for training, and use the trained model to determine if other reviews are fake.