Stock Trend Prediction Using KNN Algorithm

Abstract

Stock forecasting has always been a difficult task for statisticians and financial analysts. The key strategy used to make this prediction is buying stocks with a high probability of price growth and selling stocks with a high probability of price decline. There are typically two approaches to stock market forecasting. One of them is fundamental analysis, which is dependent on a company's methodology and fundamental data. The performance of the supervised machine learning algorithm KNN (K-Nearest Neighbor) is evaluated by the author in this study. Stock trading is one of the most significant activities in the world of finance. Trying to anticipate the future value of a stock or other financial instrument traded on a financial exchange is known as stock market prediction. Python is the computer language used to make stock market predictions using machine learning. In this article, we present a Machine Learning (ML) approach that will be trained using the stock market data that is currently accessible, gain intelligence, and then use the learned information to make an accurate prediction. This study employs prices with both daily and up-to-the-minute frequencies and a machine learning method known as K-Nearest Neighbor to forecast stock prices for both large and small capitalizations and in the three separate marketplaces.