This research introduces a hybrid stock price forecasting model using Nikkei 225 index data from 2013 to 2022 to mitigate investment risks. The model integrates Support Vector Regression (SVR) with multiple optimization approaches: Moth Flame Optimization (MFO), Artificial Bee Colony (ABC), and Genetic Algorithms (GA). MFO-SVR demonstrated the highest accuracy, achieving a Mean Absolute Percentage Error (MAPE) of 0.70. The model's accuracy was evaluated using MAE, MAPE, MSE, and RMSE.
Publisher
(IJACSA) International Journal of Advanced Computer Science and Applications
Published On
Mar 01, 2024
Authors
Xiao Duan
Tags
stock price forecasting
Nikkei 225
Support Vector Regression
Moth Flame Optimization
investment risks
mean absolute percentage error
optimization techniques
Related Publications
Explore these studies to deepen your understanding of the subject.
