Optimized Hybrid Machine Learning Approaches for Stock Market Forecasting and Time Series Analysis
The research introduces an innovative hybrid model of KPCA, ESVM, and TLBO to analyze stock price variation and time series forecasting. To handle the issue of high dimensionality of the financial data and the nonlinear dependencies amongst the variables, the model employs KPCA for feature extraction, thus identifying, and retaining only the feature space that is most relevant. Subsequently, the features extracted are passed through ESVM for regression – aiding in correct estimations on stock prices. To improve the outcome, prediction accuracy and to fine transient parameters of the model TLBO as a metaheuristic algorithm is used. The application of KPCA-ESVM-TLBO establishes optimal characteristics from the above methodologies, producing efficiency in tackling complications and nonlinearity of the data structures. KPCA looks for hidden structure; ESVM does regression with the kernel; and TLBO twiddles appropriate knobs such as λ and kernel coefficients. By using real-world financial data sets, the experimental evaluations presented show that the reported method outperforms the conventional benchmarks in relations of predictive accuracy. MAE, RMSE, and accuracy confirm its relevance: predictive accuracy of 99.99%. This approach to using artificial neural networks in tandem with a nearest neighbor algorithm presents the prospect of a potent weapon for forecasting and decision making in ever complex and volatile market.
Volume & Issue
Vol. Volume 12 / Iss. Issue 1