Stock prices prediction is a critical aspect of financial analysis that helps investors in making informed decisions and effectively managing risk. This work presents a machine learning framework that utilizes machine learning and historical market data to predict and visualize stock prices. The proposed work provides a comprehensive dataset for analysis by retrieving daily closing stock prices of 20 years’ worth from Yahoo Finance (yfinance). The system incorporates moving averages, specifically the 100-day and 250-day moving averages, to evaluate long-term stock performance. These pointers assist in classifying trends and offer insights into historical price movements. At the core of the framework is a pre-trained neural network model. This model detects patterns and estimates future stock prices with enhanced accuracy by utilizing sequential historical data. To improve the model’s effectiveness, MinMaxScaler is applied for data normalization, which ensures that all values are adjusted within a designated range. This preprocessing step boosts the reliability of predictions and aids in the more efficient convergence of the neural network. Following the processing of scaled stock data, the model discerns significant patterns and predicts future prices based on historical trends. Users can input stock symbols, visualize historical stock trends, and easily compare actual prices with projected ones through an intuitive interface. The proposed framework simplifies the interpretation of complex financial data by employing real-time visualizations, such as moving averages and prediction overlays. This initiative makes stock market analysis more accessible by combining advanced machine learning methods, thorough data preparation, and interactive visualization. It provides a valuable resource that demonstrates how predictive analytics can enhance investment strategies for both novice and experienced investors.