Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 5

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  support vector machines
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

Bankruptcy prediction of small- and medium-sized enterprises in Poland based on the LDA and SVM methods

100%
Ptak-Chmielewska A.
Statistics in Transition new series
|
2021
|
vol. 22
|
issue 1
179-195
EN
The impact the last financial crisis had on the small- and medium-sized enterprises (SMEs) sector varied across countries, affecting them on different levels and to a different extent. The economic situation in Poland during and after the financial crisis was quite stable compared to other EU member states. SMEs represent one of the most important segments of the economy of every country. Therefore, it is crucial to develop a prediction model which easily adapts to the characteristics of SMEs. Since the Altman Z-Score model was devised, numerous studies on bankruptcy prediction have been written. Most of them involve the application of traditional methods, including linear discriminant analysis (LDA), logistic regression and probit analysis. However, most recent studies in the area of bankruptcy prediction focus on more advanced methods, such as case-based reasoning, genetic algorithms and neural networks. In this paper, the effectiveness of LDA and SVM predictions were compared. A sample of SMEs was used in the empirical analysis, financial ratios were utilised and non-financial factors were taken account of. The hypothesis assuming that multidimensional discrimination was more effective was verified on the basis of the obtained results.
2
Publication available in full text mode
Content available

Clustering Methods Applied to Reduce the Training Sample Size in Support Vector Machines

100%
Trzęsiok M., The Karol Adamiecki University of Economics in Katowice
Acta Universitatis Lodziensis. Folia Oeconomica
|
2009
|
vol. 225
EN
Support vector machines belong to the group of methods of supervised learning. They generate non-linear models with good generalization abilities. The core of SVMs algorithm is the quadratic program which is solved for obtaining the optimal separating hyperplane. Because finding the solution of this quadratic program is computationally expensive, SVMs are not feasible for very large data sets. As a solution Wang, Wu and Zhang (2005) suggested to combine the AT-means clustering technique with SVMs to reduce the number of support vectors. The paper presents a common approach using K-medoids and compares it with the original SVMs.
PL
Metoda wektorów nośnych jest metodą dyskryminacji generującą nieliniowe modele o dużym stopniu uogólnienia (małych błędach klasyfikacji na zbiorach testowych). Jednak ze względu na dużą złożoność obliczeniową, związaną z koniecznością rozwiązania zadania optymalizacji wypukłej, które jest podstawowym elementem algorytmu metody, stosowanie metody, szczególnie w przypadku zbiorów uczących o dużej liczebności, nie zawsze jest możliwe. Złożoność obliczeniowa algorytmu metody wektorów nośnych zależy przede wszystkim od liczby obserwacji w zbiorze uczącym. Jako rozwiązanie tego problemu Wang, Wu i Zhang zaproponowali pogrupowanie danych ze zbioru uczącego za pomocą taksonomicznej metody AT-średnich i zastosowanie metody wektorów nośnych na dużo mniej licznym zbiorze środków ciężkości tak otrzymanych klas. W artykule przedstawiona została ocena analogicznego podejścia, wykorzystującego do grupowania metodę K-medoidów oraz porównanie z oryginalną metodą wektorów nośnych.
3
Publication available in full text mode
Content available

On Some Properties of Support Vector Clustering

100%
Trzęsiok M., Department of Mathematics K. A. U. o. E.
Acta Universitatis Lodziensis. Folia Oeconomica
|
2009
|
vol. 228
PL
Celem referatu jest przedstawienie analizy wybranych formalnych własności taksonomicznej metody wektorów nośnych (SVC). Wyniki dotyczące nowej metody SVC zestawiono i porównano z własnościami innych znanych metod taksonomicznych. Ponieważ na ogół nie jest możliwe wskazanie, która z metod taksonomicznych daje najlepsze rezultaty, stojąc wobec konkretnego problemu, badacz musi dokonywać wyboru metody w oparciu o wiedzę dotyczącą ich własności. Zadaniem badacza jest wtedy ustalenie preferencji w zbiorze własności metod by następnie użyć ich przy doborze odpowiedniego narzędzia. Wiedza dotycząca formalnych własności metod taksonomicznych jest w referacie rozszerzona o nową- taksonomiczną metodę wektorów nośnych.
EN
The aim o f this paper is to analyse the relatively new clustering method - Support Vector Clustering (SVC) in terms o f fulfilling admissibility conditions. The results are compared within a group o f four other clustering methods. Since it is not possible to assess which clustering method is the "best" in general, given a specific problem the user can decide which method to apply considering some properties o f clustering methods, known as admissibility conditions. This paper expands the knowledge about the properties o f clustering methods with the properties o f SVC.
4

A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

75%
Zekić-Sušac M., Pfeifer S., Šarlija N.
Business Systems Research Journal
|
2014
|
vol. 5
|
issue 3
82-96
EN
Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.
5
Publication available in full text mode
Content available

Robustness of Support Vector Machines in Algorithmic Trading on Cryptocurrency Market

51%
Ślepaczuk R., Zenkova M.
Central European Economic Journal
|
2018
|
vol. 5
|
issue 52
EN
This study investigates the profitability of an algorithmic trading strategy based on training SVM model to identify cryptocurrencies with high or low predicted returns. A tail set is defined to be a group of coins whose volatility-adjusted returns are in the highest or the lowest quintile. Each cryptocurrency is represented by a set of six technical features. SVM is trained on historical tail sets and tested on the current data. The classifier is chosen to be a nonlinear support vector machine. The portfolio is formed by ranking coins using the SVM output. The highest ranked coins are used for long positions to be included in the portfolio for one reallocation period. The following metrics were used to estimate the portfolio profitability: %ARC (the annualized rate of change), %ASD (the annualized standard deviation of daily returns), MDD (the maximum drawdown coefficient), IR1, IR2 (the information ratio coefficients). The performance of the SVM portfolio is compared to the performance of the four benchmark strategies based on the values of the information ratio coefficient IR1, which quantifies the risk-weighted gain. The question of how sensitive the portfolio performance is to the parameters set in the SVM model is also addressed in this study.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.