Filters








98 Hits in 7.4 sec

Bankruptcy prediction using SVM models with a new approach to combine features selection and parameter optimisation

Ligang Zhou, Kin Keung Lai, Jerome Yen
2012 International Journal of Systems Science  
In this study, a new approach based on direct search and features ranking technology is proposed to optimize features selection and parameters setting for 1-norm and least square SVM models for bankruptcy  ...  This approach is also compared to the SVM models with parameters optimization and features selection by the popular Genetic Algorithm (GA) technique.  ...  Acknowledgements We thank two reviewers for their comments and suggestions.  ... 
doi:10.1080/00207721.2012.720293 fatcat:ygdtwjfvord3vgfoty7ojap4m4

Self-Adaptive MOEA Feature Selection for Classification of Bankruptcy Prediction Data

A. Gaspar-Cunha, G. Recio, L. Costa, C. Estébanez
2014 The Scientific World Journal  
This paper provides a methodology for feature selection in classification of bankruptcy data sets using an evolutionary multiobjective approach that simultaneously minimise the number of features and maximise  ...  The proposed methodology makes use of self-adaptation by applying the feature selection algorithm while simultaneously optimising the parameters of the classifier used.  ...  The aim of this work is to further investigate into the feature selection problem in bankruptcy prediction using a multi-objective approach, including self-adaptation of the classification algorithm parameters  ... 
doi:10.1155/2014/314728 pmid:24707201 pmcid:PMC3953468 fatcat:uchsp5yecjaqbmtr66g3lnimqe

Metaheuristics for Rich Portfolio Optimisation and Risk Management: Current State and Future Trends

Jana Doering, Renatas Kizys, Angel A. Juan, Àngels Fitó, Onur Polat
2019 Operations Research Perspectives  
In particular, these optimisation methods are becoming the solving approach alternative when dealing with realistic versions of several decision-making problems in finance, such as rich portfolio optimisation  ...  This paper reviews the scientific literature on the use of metaheuristics for solving NP-hard versions of these optimisation problems and illustrates their capacity to provide high-quality solutions under  ...  Acknowledgement This work has been partially supported with a doctoral grant from the Universitat Oberta de Catalunya and the Erasmus+ program (2018-1-ES01-KA103-049767).  ... 
doi:10.1016/j.orp.2019.100121 fatcat:ncxpgmkqczdgfl34albgx7z32m

An Intelligent System for Business Data Mining

Shian-Chang Huang, Tung-Kuang Wu, Nan-Yu Wang
2017 GLOBAL BUSINESS & FINANCE REVIEW  
Particularly in bankruptcy predictions, we need to analyze large amounts of information from financial statements and stock markets. This paper proposes a new strategy to deal with the problem.  ...  It's easy to deal with a wide class of nonlinearity in financial data, and can reduce the computational loading of subsequent prediction classifier.  ...  Combined with a sparsity promoting regularizer on d , this can be used for non-linear dimensionality reduction and feature selection for appropriate choices of A .  ... 
doi:10.17549/gbfr.2017.22.2.1 fatcat:5rx2nmjrsvbd5f65c7djb2wr3i

Machine Learning Applied to Banking Supervision a Literature Review

Pedro Guerra, Mauro Castelli
2021 Risks  
Papers were then screened and selected according to their relevance.  ...  The most relevant ML techniques encompass k-nearest neighbours (KNN), support vector machines (SVM), tree-based models, ensembles, boosting techniques, and artificial neural networks (ANN).  ...  The authors stress the importance of model-based feature selection as well as the use of Bayesian hyper-parameter optimisation to achieve better predictive results.  ... 
doi:10.3390/risks9070136 fatcat:gqjub6czvjao3fbqwf34otgwre

Handling class imbalance in direct marketing dataset using a hybrid data and algorithmic level solutions

Mohammad Majid Al-Rifaie, Haya Abdullah Alhakbani
2016 2016 SAI Computing Conference (SAI)  
class, and additionally, optimising the cost parameter, the gamma and the kernel type of Support Vector Machines (SVM) using a grid search.  ...  In this paper, a model is proposed to solve imbalanced data using a Hybrid of Data-level and Algorithmic-level solutions (HybridDA), which involves oversampling the minority class, undersampling the majority  ...  HybridDA model uses SVM and a grid search to optimise the C, gamma and the kernel type.  ... 
doi:10.1109/sai.2016.7556019 fatcat:is3otfxiwvgydltrec4fo33jdi

On the parameter optimization of Support Vector Machines for binary classification

Paulo Gaspar, Jaime Carbonell, José Luís Oliveira
2012 Journal of Integrative Bioinformatics  
Techniques for feature selection and SVM parameters optimization are known to improve classification accuracy, and its literature is extensive.In this paper we review the strategies that are used to improve  ...  the classification performance of SVMs and perform our own experimentation to study the influence of features and hyper-parameters in the optimization process, using several known kernels.  ...  This method is applied, for instance, by Wu et al [6] to optimize an SVM model capable of predicting bankruptcy.  ... 
doi:10.1515/jib-2012-201 fatcat:ozphynvf2jd77lxawbampf72wa

On the parameter optimization of Support Vector Machines for binary classification

Paulo Gaspar, Jaime Carbonell, José Luís Oliveira
2012 Journal of Integrative Bioinformatics  
Techniques for feature selection and SVM parameters optimization are known to improve classification accuracy, and its literature is extensive.  ...  In this paper we review the strategies that are used to improve the classification performance of SVMs and perform our own experimentation to study the influence of features and hyper-parameters in the  ...  This method is applied, for instance, by Wu et al [6] to optimize an SVM model capable of predicting bankruptcy.  ... 
doi:10.2390/biecoll-jib-2012-201 pmid:22829572 fatcat:cdtcfppctvbfdlup6dginjk7ru

Support Vector Machines with Evolutionary Feature Selection for Default Prediction

Wolfgang K. HHrdle, Dedy Dwi Prastyo, Christian M. Hafner
2012 Social Science Research Network  
The SVM with evolutionary feature selection is applied to the CreditReform database.  ...  We use classical methods such as discriminan analysis (DA), logit and probit models as benchmark On overall, GA-SVM is outperforms compared to the benchmark models in both training and testing dataset.  ...  Dedy Dwi Prastyo was also supported by a scholarship from Directorate General for Higher Education, Indonesian Ministry of Education and Cultur through Department of Statistics, Institut Teknologi Sepuluh  ... 
doi:10.2139/ssrn.2894201 fatcat:jafwiz5ia5fxldx5kiktqmrva4

Support Vector Machines with Evolutionary Model Selection for Default Prediction [chapter]

Jeffrey S. Racine, Liangjun Su, Aman Ullah, Wolfgang Karl Härdle, Dedy Dwi Prastyo, Christian M. Hafner
2014 The Oxford Handbook of Applied Nonparametric and Semiparametric Econometrics and Statistics  
The SVM with evolutionary feature selection is applied to the CreditReform database.  ...  We use classical methods such as discriminan analysis (DA), logit and probit models as benchmark On overall, GA-SVM is outperforms compared to the benchmark models in both training and testing dataset.  ...  Dedy Dwi Prastyo was also supported by a scholarship from Directorate General for Higher Education, Indonesian Ministry of Education and Cultur through Department of Statistics, Institut Teknologi Sepuluh  ... 
doi:10.1093/oxfordhb/9780199857944.013.011 fatcat:qoebcuz7uzdo3anqqq7ewnecxe

Machine learning as a tool for choice of enterprise development strategy

M Krichevsky, E Serova, V. Breskich, A. Zheltenkov, Y. Dreizis
2020 E3S Web of Conferences  
This paper deals with the issues of machine learning implementation and how intellectual models and systems can be used to support the process of strategic planning.  ...  At the preprocessing stage on the basis of a modeled base of examples of strategy options, the use of clustering methods for forming groups of similar parameters that influence the choice of strategies  ...  We have the model defined with the accuracy of some parameters, and learning is the execution of the computer program for optimisation of model parameters.  ... 
doi:10.1051/e3sconf/202022403006 fatcat:pd5e5tuqynhovdysmveheoqftm

Bankruptcy Prediction: A Comparison of Some Statistical and Machine Learning Techniques [chapter]

Tonatiuh Peña, Serafín Martínez, Bolanle Abudu
2011 Dynamic Modeling and Econometrics in Economics and Finance  
Our contribution to the field of computational finance is to introduce GP's as a potentially competitive probabilistic framework for bankruptcy prediction.  ...  Data from the repository of information of the US Federal Deposit Insurance Corporation is used to test the predictions.  ...  If the selection of prior covariance is adequate, then ARD may be a very useful method for ranking and selecting features as it effectively orders inputs according to their importance and eliminates those  ... 
doi:10.1007/978-3-642-16943-4_6 fatcat:oyrxjezcu5ddvhmunhup65ghiq

Bankruptcy Prediction: A Comparison of Some Statistical and Machine Learning Techniques

Tonatiuh Pena Centeno, Serafin Martinez Jaramillo, Bolanle Abudu
2009 Social Science Research Network  
Our contribution to the field of computational finance is to introduce GP's as a potentially competitive probabilistic framework for bankruptcy prediction.  ...  Data from the repository of information of the US Federal Deposit Insurance Corporation is used to test the predictions.  ...  If the selection of prior covariance is adequate, then ARD may be a very useful method for ranking and selecting features as it effectively orders inputs according to their importance and eliminates those  ... 
doi:10.2139/ssrn.1525947 fatcat:kaj5cmht7vbrbohpw5byavjdhy

Methodological approach of construction business failure prediction studies: a review

Hafiz A. Alaka, Lukumon O. Oyedele, Hakeem A. Owolabi, Saheed O. Ajayi, Muhammad Bilal, Olugbenga O. Akinade
2016 Construction Management and Economics  
., and Yen, J. (2014). Bankruptcy prediction using SVM models with a new approach to combine features selection and parameter optimisation.  ...  In fact, with AI techniques like ANN and SVM, it is very possible to build a model with a 100% prediction accuracy when tested on training (i.e. model building) data.  ...  Khademolq orani et al. total asset; ratio of the current assets to the current liabilities; ratio of the amount of cash and equivalents, short, and accounts receivable, term investments to the current  ... 
doi:10.1080/01446193.2016.1219037 fatcat:ifmzr5jebrdgbe7fbrx7d5df5i

Forecasting Corporate Distress in the Asian and Pacific Region

Russ Moro, Wolfgang K. HHrdle, Saeideh Aliakbari, Linda Hoffman
2011 Social Science Research Network  
With respect to forecasting accuracy the SVM has a lower model risk than the Logit on average and displays a more robust performance. This result holds true across different years.  ...  An analysis of the dependencies between PD and financial ratios is provided along with a comparison with Europe (Germany).  ...  These two parameters of the SVM used in our study were r = 2.5 and c = 1 for a low complexity SVM with high generalisation ability, which is expected to perform well on a broad range of data sets.  ... 
doi:10.2139/ssrn.2894232 fatcat:um3vnyeevjgsbkaext5245wljq
« Previous Showing results 1 — 15 out of 98 results