Predicting financial distress of JSE-Listed companies using Bayesian networks

Simple item page
dc.contributor.advisorKruger, Ryanen_ZA
dc.contributor.authorCassim, Ziyaden_ZA
dc.date.accessioned2016-07-20T06:56:47Z
dc.date.available2016-07-20T06:56:47Z
dc.date.issued2016en_ZA
dc.description.abstractThis study aims to test the suitability of using Bayesian probabilistic models to predict bankruptcy of JSE-listed companies. A sample of 132 companies is considered with fourteen years of financial statement information and macroeconomic indicators used as predictor variables. Various permutations of Bayesian models are tested relating to different learning algorithms, intervals of discretisation and scoring metrics. In contrast to previous research, we explore a variety of evaluation measures and it is found that predictive accuracy for bankrupt firms does not exceed 70% in any model augmentation. On comparison to other popular models such as the Altman Z-score and the logit model, it is found that Bayesian networks produce marginally better predictive accuracy. Furthermore, a comparison to previous research on the same subject is carried and reasons for significantly different results are considered. Finally, the reasons for low predictive accuracies is considered with issues relating specifically to South Africa being discussed.en_ZA
dc.identifier.apacitationCassim, Z. (2016). <i>Predicting financial distress of JSE-Listed companies using Bayesian networks</i>. (Thesis). University of Cape Town ,Faculty of Commerce ,Division of Actuarial Science. Retrieved from http://hdl.handle.net/11427/20484en_ZA
dc.identifier.chicagocitationCassim, Ziyad. <i>"Predicting financial distress of JSE-Listed companies using Bayesian networks."</i> Thesis., University of Cape Town ,Faculty of Commerce ,Division of Actuarial Science, 2016. http://hdl.handle.net/11427/20484en_ZA
dc.identifier.citationCassim, Z. 2016. Predicting financial distress of JSE-Listed companies using Bayesian networks. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Cassim, Ziyad AB - This study aims to test the suitability of using Bayesian probabilistic models to predict bankruptcy of JSE-listed companies. A sample of 132 companies is considered with fourteen years of financial statement information and macroeconomic indicators used as predictor variables. Various permutations of Bayesian models are tested relating to different learning algorithms, intervals of discretisation and scoring metrics. In contrast to previous research, we explore a variety of evaluation measures and it is found that predictive accuracy for bankrupt firms does not exceed 70% in any model augmentation. On comparison to other popular models such as the Altman Z-score and the logit model, it is found that Bayesian networks produce marginally better predictive accuracy. Furthermore, a comparison to previous research on the same subject is carried and reasons for significantly different results are considered. Finally, the reasons for low predictive accuracies is considered with issues relating specifically to South Africa being discussed. DA - 2016 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2016 T1 - Predicting financial distress of JSE-Listed companies using Bayesian networks TI - Predicting financial distress of JSE-Listed companies using Bayesian networks UR - http://hdl.handle.net/11427/20484 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/20484
dc.identifier.vancouvercitationCassim Z. Predicting financial distress of JSE-Listed companies using Bayesian networks. [Thesis]. University of Cape Town ,Faculty of Commerce ,Division of Actuarial Science, 2016 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/20484en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentDivision of Actuarial Scienceen_ZA
dc.publisher.facultyFaculty of Commerceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherActuarial Scienceen_ZA
dc.titlePredicting financial distress of JSE-Listed companies using Bayesian networksen_ZA
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMPhilen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_com_2016_cassim_ziyad.pdf
Size:
635.67 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters