Title Predviđanje nastavka poslovanja poduzeća metodom umjetnih neuronskih mreža Title (english) Forecasting company's going concern using artifical neural networks Author Dejana Dojčinović Drilo Mentor Neda Vitezić (mentor)Committee member Mira Dimitrić (predsjednik povjerenstva)Committee member Robert Zenzerović (član povjerenstva)Committee member Adnan Rovčanin (član povjerenstva) Granter University of Rijeka Defense date and country 2018-11-22, Croatia Scientific / art field, SOCIAL SCIENCES Universal decimal classificationUDC ) 338 - Economic situation. Economic policy. Management of the economy. Economic planning. Production. Services. Prices 004 - Computer science and technology. Computing. Data processing Abstract Nastavak poslovanja poduzeća je temeljna pretpostavka poslovanja poduzeća, a procjena nastavka poslovanja poduzeća od velike je važnosti za cjelokupnu poslovnu zajednicu i sve interesne skupine u lancu vrijednosti poslovanja poduzeća. Ključni faktor uspjeha u procjeni nastavka poslovanja poduzeća je odabir modela koji će na točan i objektivan način generirati ispravnu procjenu nastavka i omogućiti donošenje poslovnih odluka. Predviđanje nastavka poslovanja uglavnom se veže uz revizijske
... More angažmane, no u vrijeme brzih promjena u svjetskom ekonomskom okruženju i korporativnim financijama, procjena nastavka poslovanja postala je jedna od glavnih tema svjetskih istraživača u svim ekonomskim područjima u posljednjih 35 godina.
Svrha ovog rada je istražiti učinkovitost modela predviđanja nastavka poslovanja poduzeća temeljenih na kvantitativnim financijskim pokazateljima u hrvatskom gospodarstvu i predložiti novi model, temeljen na kvantitativnim i kvalitativnim pokazateljima, sukladno karakteristikama poslovanja hrvatskih poduzeća u okruženju održive ekonomije, posebno nakon nastupanja poslovne krize 2008. godine. Osnovni ciljevi rada su objasniti učinkovitost tradicionalnih i suvremenih modela u cilju predviđanja nastavka poslovanja poduzeća, istražiti učinkovitost Altmanovog Z'-score modela, Zmijewski modela i Ohlson modela u predviđanju nastavka poslovanja poduzeća, te predložiti novi model predviđanja nastavka poslovanja uključivanjem odabranih kvantitativnih (nefinancijskih) i kvalitativnih varijabli primjenom suvremene metode neuronskih mreža.
Empirijsko istraživanje i analiza učinkovitosti navedena tri statistička modela provela se na uzorku poduzeća iz hrvatskog gospodarstva, te su se istraživanjem i analizom potvrdile prve dvije pomoćne hipoteze rada kojima se dokazalo da tradicionalni modeli jesu uspješni u predviđanju poslovanja poduzeća u Republici Hrvatskoj, posebno uspješnih, ali da postoji razlika između učinkovitosti modela. Generalno gledano postoji nekoliko značajnih problema u primjeni tradicionalnih modela u poslovnoj praksi. Prvi signifikantan problem s tradicionalnim modelima predviđanja nastavka poslovanja s kojim se susreću korisnici je njihova općenita upotreba, odnosno problem generalne upotrebe u različitim specifičnim makroekonomskim okruženjima i
VI
nacionalnim ekonomijama. Drugi problem je njihova učinkovitost u predviđanju budućih poremećaja ili nastavka poslovanja s obzirom na činjenicu da se većina temelji na tradicionalnim statističkim metodama (MDA, probit i logit) koje nisu adekvatne za procjenu kompleksnih i dinamičnih okruženja. Treći problem je činjenica da većina takvih modela koristi isključivo financijske pokazatelje poslovanja temeljene na povijesnim računovodstvenim podacima. Iz tog razloga takvi modeli nisu dovoljno osjetljivi i ne osiguravaju rane znakove upozorenja korisnicima modela.
Iz navedenih rezultata istraživanja javila se potreba definiranja novog modela koji bi uzeo u obzir sve nedostatke postojećih modela. Posljednjih nekoliko godina metoda umjetnih neuronskih mreža predlaže se, u literaturi i praksi, kao prikladna i bolja metoda od tradicionalnih statističkih metoda koja daje točnije rezultate bez potrebe poštivanja striktnih statističkih pretpostavki tradicionalnih metoda. U ovom istraživanju stoga je, za definiranje novog prediktivnog modela, upotrjebljena umjetna neuronska mreže te logistička regresija za definiciju najznačajnijih varijabli u samom modelu. Rezultat rada je definicija novog modela te algoritam, temeljem umjetne neuronske mreže „širenja unatrag“, za buduće procjene nastavka poslovanja poduzeća. Dodatnom analizom najznačajnije varijable za procjenu nastavka poslovanja poduzeća pokazale su se: ukupne obveze / kapital, ukupne obveze / (kapital + rezerve), dugoročne obveze / ukupna imovina, EBIT / trošak kamata, dugotrajna imovina / (kapital + dugoročne obveze).
Novi definirani model demonstrirao je uspješnost od 97,69% u predviđanju nastavka poslovanja poduzeća što je više od tradicionalnih modela istraženih u radu čime se potvrdila osnova hipoteza rada: „Suvremeni model predviđanja temeljen na kvantitativnim i kvalitativnim varijablama, odabranih pomoću statističke metode neuronskih mreža uvažavajući specifičnosti hrvatskog gospodarskog okruženja, omogućava učinkovitiju procjenu nastavka poslovanja u poduzećima u odnosu na postojeće modele i na taj način doprinosi stabilnosti i održivosti nacionalne ekonomije.“
Podaci korišteni u definiciji modela prikupljeni su u Republici Hrvatskoj koja reprezentativno predstavlja tranzicijske zemlje te je model primjenjiv u regionalnim tranzicijskim zemljama sa sličnim makroekonomskim i institucionalnim uvjetima. Less Abstract (english) The going concern concept is the basic prerequisite for company’s business activities and its forecasting is essential for the entire business community as well as for the large number of stakeholders participating in company’s value chain. The key success factor in going concern forecasting is the selection of the most appropriate model that can factually and accurately generate efficient going concern prediction, thus enabling the key decision makers to make the right decision. The
... More going concern prediction is mostly connected to audit engagements, but in time of fast changes in global economic environment and corporate finance, going concern prediction has, in the last 35 years, become one of the global key economics research topics.
The purpose of this work was to examine the effectiveness of the going concern forecasting models based only on quantitative financial indicators in the Croatian economy and to propose the new model. The model should be based on both quantitative and qualitative indicators, considering major Croatian economy business characteristics in a sustainable economy environment, especially after financial crisis in 2008. The main goals of the thesis were to explain the effectives of traditional and contemporary going concern prediction models, examine the effectiveness of Altman Z’-score model, Zmijewski model and Ohlson model and to propose the new going concern prediction model based on selected financial, quantitative (non-financial) and qualitative variables developed with the support of artificial neural network method.
Empirical research and efficiency analysis performed on the selected three statistical models were conducted on the data sample from companies operating in Croatian economy. Conducted research and analysis confirmed the two supporting hypotheses of the work proving that traditional models are actually efficient in business performance prediction in Croatian economy, especially for the successful companies, but that there is a difference in the models’ accuracy. In general, there are several main challenges in the traditional models’ implementation in business practice. The first problem regarding traditional forecasting models users come across is their application in difference specific macroeconomic environments and national economies due to their general application set up. The second main issue is the models’ accuracy rate
VIII
in business failure or going concern forecasting due to the fact that the models are based on traditional statistical methods (MDA, probit and logit) that are not always adequate for forecasting complex and dynamic situations. The third problem is the fact that majority of traditional models is based solely on financial business indicators resulting from historical accounting data. All things considered, these models do not ensure appropriate sensitivity and cannot guarantee early warning signals to models’ users.
The need for the new model, that would take into account all disadvantages of the current models, came out as the result of the empirical research. In the last several years, artificial neural networks method is being suggested, both in theory and practice, as more appropriate and efficient method than traditional statistical methods, without respecting all restrictive statistical prerequisites of traditional methods. Therefore, artificial neural networks statistical method was used in this empirical research in order to define new forecasting model, as well as logistic regression to define the most important variables in the forecasting model. The main results of the thesis is the new model and algorithm, based on the backpropagation algorithm of the artificial neural networks, for the company’s going concern forecasting. The most important variables for the forecasting are: total debt / equity, total debt / (equity + reserves), long-term liabilities / total assets, EBIT / interest, total assets / (equity + long-term liabilities).
The new defined model demonstrated the accuracy rate of 97.69% in companies’ going concern prediction, which is higher than at traditional statistical methods analyzed in the thesis by which the main thesis hypothesis was confirmed: “Contemporary forecasting model, based on selected quantitative and qualitative variables by statistical method of neural networks and taking into account the specificity of the Croatian economic environment, can more efficiently assess companies’ going concern in comparison to traditional models, thus contributing to the stability and sustainability of the national economy.”
Data used in the forecasting model definition was collected in the Croatian economy and Croatia, as the country, successfully represents transitional countries. This makes the new model applicable in regional transitional countries with similar macroeconomic and institutional conditions. Less Keywords
prediktivni modeli
nastavak poslovanja
Altman model
Ohlson model
Zmijewski model
financijske i nefinancijske varijable
kvantitativne i kvalitativne varijable
umjetne neuronske mreže
Keywords (english)
predictive models
going concern
Altman model
Ohlson model
Zmijewski model
financial and non-financial variables
quantitative and qualitative variables
artificial neural networks
Language croatian URN:NBN urn:nbn:hr:192:650131 Study programme Title: Economics and Business Economics Catalog URL http://libraries.uniri.hr/cgi-bin/lb08/unilib.cgi?form=U117062406099999904 Type of resource Text File origin Born digital Access conditions Open access Terms of use Created on 2019-01-14 14:48:01
