Hybrid Model of Artificial Neural Networks and Flower Pollination Algorithm for Stock Price Prediction

Predicting the future behavior of the stock market is a difficult task due to its complex and ever-changing nature. This study focuses on predicting BBRI stock prices using an Artificial Neural Network (ANN) improved with the Flower Pollination Algorithm (FPA). We found that the model works well with a 9-100-1 setup, achieving accurate predictions with a Root Mean Square Error (RMSE) of 0.127579154. While FPA effectively reduces errors in the initial 10 iterations, it faces challenges in further improvement, especially in responding to sudden changes in stock prices. Despite performing well overall, the model tends to have a wider margin during unexpected market shifts, indicating a need for additional fine-tuning. This research provides valuable insights into stock price prediction, highlighting the importance of refining models to handle unexpected market changes.