Component-based decision trees for classification

Delibašić, Boris; Jovanović, Miloš; Vukičević, Milan; Suknović, Milija; Obradović, Zoran

doi:10.3233/ida-2011-0489

Cited by 19 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, component DT design, introduced by Delibasic, Jovanovic, Vukicevic, Suknovic, and Obradovic (2011), enables user to intelligently select in advance implemented components, best suited for specific data set. Such defined algorithms can provide much higher accuracy of classification, as well as the lower complexity of generated tree from the original DT algorithms.…”

Section: Resultsmentioning

confidence: 99%

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Kašćelan¹,

Kašćelan²,

Jovanovic³

2014

Intelligent Automation & Soft Computing

View full text Add to dashboard Cite

In this study we developed a support vector machine (SVM) rule extraction method for discovering the effects of the features of investors and stock and corporate performance on stock trading preferences. We used this system to combine strengths of two approaches: SVM as an accurate classifier and a decision tree (DT) as a generator of interpretable models. The method is applied to Montenegro data in order to generate interpretable rules for stock market decision-makers. The results showed that this method, in terms of accuracy and interdependency of factors, outperformed the methods for detecting stock trading preferences from previous studies.

show abstract

Section: Resultsmentioning

confidence: 99%

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Kašćelan¹,

Kašćelan²,

Jovanovic³

2014

Intelligent Automation & Soft Computing

View full text Add to dashboard Cite

show abstract

“…That framework was further evaluated in [13]. Because of the large space of algorithms in component-based algorithm design, the need for AAD emerged.…”

Section: Related Workmentioning

confidence: 99%

“…The question of whether the combination of components could improve algorithm performance asked by [42] is positively answered in [13]. This approach is strongly supported by the series of No Free lunch theories [50] where authors proved that there is no optimal algorithm for every problem, but one can always design an optimal algorithm for the data at hand.…”

Section: Component-based Designmentioning

confidence: 99%

“…To fulfill these goals (standardize algorithms, and extend the space of available algorithms), component-based design of data mining algorithms was proposed in [12,13]. This approach allows users Fig.…”

Section: Introductionmentioning

confidence: 99%

“…In [13] 80 component-based decision tree algorithms have been proposed and evaluated on 15 datasets. Results of components' influence on algorithm performance, as statistical significance of the differences found were presented.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary approach for automated component-based decision tree algorithm design

Jovanović

Delibašić

Vukičević

et al. 2014

IDA

View full text Add to dashboard Cite

This paper proposes a framework for automated design of component-based decision tree algorithms. These algorithms are being constructed by interchanging components extracted from decision tree algorithms and their partial improvements. Manual selection of the best-suited algorithm for a specific problem is a complex task because of the huge algorithmic space derived from component-based design. The proposed framework searches through the algorithmic space with an evolutionary algorithm by interchanging components and tuning parameters, and finds a near optimal algorithm for a specific problem. Through experiments we show that using this meta-heuristic is justified in automated component-based algorithm design. This approach is useful not only as an algorithm design help, but also as a technology enhanced learning tool, which aids the understanding of the algorithms.

show abstract

Techniques of Decision Tree Induction

Grąbczewski

2013

Studies in Computational Intelligence

View full text Add to dashboard Cite

Component-based decision trees for classification

Cited by 19 publications

References 22 publications

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Evolutionary approach for automated component-based decision tree algorithm design

Techniques of Decision Tree Induction

Contact Info

Product

Resources

About