Stocks play a vital role in the economy and serve as an indicator of business value and investor sentiment. To leverage improved decision-making aligned with investment strategies and market trends, real-time stock predictions enhance outcomes by offering immediate insights and enabling investors to make more informed decisions. Various machine learning techniques have been applied to this problem, but most of them rely on historical data and do not account for the dynamic and volatile nature of the stock market. In this project, we propose a novel approach for stock price prediction using real-time data streamed from Yahoo Finance with Apache Kafka. A simple linear regression model, trained on the historical data, enables to predict the closing price of the stock for every fifth minute based on the opening price. The machine learning algorithm provides a better and more efficient way to predict the prices and facilitate decision-making.