Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/329120 
Year of Publication: 
2024
Citation: 
[Journal:] Economies [ISSN:] 2227-7099 [Volume:] 12 [Issue:] 8 [Article No.:] 194 [Year:] 2024 [Pages:] 1-12
Publisher: 
MDPI, Basel
Abstract: 
In this study, we compare the performance of stochastic processes, namely, the Vasicek, Cox-Ingersoll-Ross (CIR), and geometric Brownian motion (GBM) models, with that of machine learning algorithms, such as Random Forest, Support Vector Machine (SVM), and k-Nearest Neighbors (KNN), for predicting the trends of stock indices XLF (financial sector), XLK (technology sector), and XLV (healthcare sector). The results showed that stochastic processes achieved remarkable prediction performance, especially the CIR model. Additionally, this study demonstrated that the metrics of machine learning algorithms are relatively lower. However, it is important to note that stochastic processes use the actual current index value to predict tomorrow's value, which may overestimate their performance. In contrast, machine learning algorithms offer a more flexible approach and are not as dependent on the current index value. Therefore, optimizing the hyperparameters of machine learning algorithms is crucial for further improving their performance.
Subjects: 
financial prediction
machine learning algorithms
stochastic processes
support vector machine
trading
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.