Stock Price Prediction with Mathematical Model Based on Secant Method

Stock price prediction is a complex problem involving various factors, including market volatility and historical data. This study proposes a mathematical model based on the secant method to predict stock prices. The secant method, as a simple but effective numerical algorithm, is used to approximate nonlinear solutions to stock price trends. Historical stock data is analyzed to form a function that represents the pattern of price changes. This function is the basis for applying the secant method to predict stock prices at a certain time. The study was conducted using stock data from several companies, with performance evaluation based on the level of prediction error compared to actual data. The results show that the secant method is able to produce predictions with a low average error rate and high computational efficiency. This makes it an attractive choice compared to more complex models, especially in resource-constrained environments. However, accuracy decreases in highly volatile market conditions, indicating the need for further development. This method offers a simple yet reliable approach to stock price prediction, so it can be used as a tool for investors or market analysts, taking into account its limitations.