Optimized Ensemble Support Vector Regression Models for Predicting Stock Prices with Multiple Kernels

Abstract

Stock forecasting is a complicated and daily challenge for investors because of the non-linearity of the market and the high volatility of financial assets such as stocks, bonds and other commodities. There is a need for a powerful and adaptive stock prediction model that handles complexities and provides accurate predictions. The support vector regression (SVR) model is one of the most prominent machine learning models for forecasting time series data. An ensemble hyperbolic tangent kernel SVR (HTK-SVR-BO) is proposed in this paper, combining Tanh and inverse Tanh kernels with Bayesian optimization. Combining the strengths of multiple kernels using the ensemble technique and then using optimization to identify the optimal values for each SVR model to enhance the ensemble model performance is possible. Our proposed model is compared with an ensemble SVR model (LPR-SVR-BO), which uses well-known SVR kernel types, including linear, polynomial and radial basis function (RBF). We apply the proposed models to Microsoft Corporation (MSFT) stock prices. The mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R2 score (model accuracy) and mean absolute percentage error (MAPE) are the regression metrics used to compare the effectiveness of each ensemble model. In our comparison, HTK-SVR-BO performs better in terms of regression metrics compared to LPR-SVR-BO and achieves results of 0.27424, 0.13392, 0.36595, 0.99997 and 5.2331 respectively. According to the analysis, the proposed model is more predictive and may generalize to previously unknown data more effectively, so it can be accurate when forecasting future stock prices.

Improving Cryptocurrency Price Prediction Accuracy with Multi-Kernel Support Vector Regression Approach

“…Different kinds of kernel functions exist with different formulas. Kernel functions include the following [14,24,25].…”

“…These metrics play a crucial role in evaluating the performance of predictive models that focus on continuous numeric outcomes. Calculating the MAPE and the R 2 score will determine which model produces the most accurate results for the original time series [13,14]. Where M is the total number of records, 𝑧 𝑖 -Actual value, 𝑧 𝑖 ̂-Predicted value, and 𝑧 𝑖 ̅ -Mean value of 𝑧 𝑖…”

“…In addition, GSO seeks out the most effective configurations for the SVR model by systematically exploring hyperparameter combinations. Predictive models will be evaluated using comprehensive regression metrics, including R 2 scores and mean absolute percentage errors (MAPE) [13,14]. These metrics are used as benchmarks to assess how well a model captures and predicts cryptocurrency stock closing prices.…”