|
|
Bankruptcy Prediction Modelling in the Agriculture Business
Pokorný, Petr ; Peter,, Markovič, (referee) ; Karas, Michal (advisor)
This master’s thesis is focused on problematic within the prediction of bankruptcy of companies operating in the field of agriculture in Czech republic. First part consists of introduction to companies that do business in field of agriculture and it describes bankruptcy models that are used in academicals sphere. Other part of thesis is divided into two sub-parts. First part is dedicated to an application of data into models of bankruptcy and their evaluation. Second part is focused on improvement of the best model and its main goal is to maximize the precision of the bankruptcy.
|
|
|
Explainable Convolutional Neural Networks
Kamenický, Daniel ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The aim of this work was to compare several methods for visualizing the features of each class on the input pixel layer of the CNN. Each method uses a different algorithm, based on gradients, to compute the resulting values. Using the implementation of each method, the resultant values of the methods are obtained by using the equation of energy concentration. The resultant values are presented in tables and graphs from which the success rate of the result of the work can be read. The difference between the methods and comparison of their results can be read from the work. This makes it possible to get an overview of gradient based visualization methods.
|
|
| |
|
|
Multiple-criteria Decision Making and Data Envelopment Analysis
BRABCOVÁ, Michaela
This thesis explores methods of multiple-criteria decision making in connection with data envelopment analysis. A model task is to compare all the countries of the European Union according to the growth of their small and medium-sized enterprises. The differences and similarities of the chosen approaches are shown on the selected data. The results include the ranking of countries based on efficiency according to the CCR model and a comparison of the results from data envelopment analysis and the described multi-criteria methods using Spearman coefficients. As the results of the multi-criteria evaluation of alternatives depend strongly on the weights, their stability for the weighted sum approach and PROMETHEE was therefore examined.
|
|
|
Explainable Convolutional Neural Networks
Kamenický, Daniel ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The aim of this work was to compare several methods for visualizing the features of each class on the input pixel layer of the CNN. Each method uses a different algorithm, based on gradients, to compute the resulting values. Using the implementation of each method, the resultant values of the methods are obtained by using the equation of energy concentration. The resultant values are presented in tables and graphs from which the success rate of the result of the work can be read. The difference between the methods and comparison of their results can be read from the work. This makes it possible to get an overview of gradient based visualization methods.
|
|
|
Multicriteria analysis of current accounts on the Czech banking market
Pacovská, Lucie ; Jablonský, Josef (advisor) ; Kuncová, Martina (referee)
This diploma thesis deals with the analysis of current accounts on the Czech banking market. Its goal is to find the most appropriate accounts for different types of clients. The work is divided into three parts. The theoretical part describes the problem of multicriteria decision making, basic concepts and principles, methods for calculating weight of the criteria and individual methods of multicriterial evaluation of alternatives. The second part is devoted to the description of the currently offered current accounts for individuals and a description of the selected criteria according to which the individual alternatives are evaluated. The last computational part tries to find the most appropriate accounts for those clients. Weights are calculated using the scoring method and DEMATEL method. Subsequently, the best accounts are selected by WSA, TOPSIS, ELECTRE III and MAPPAC. The calculations are made by using MS Excel add-in application Sanna.
|
|
|
Bankruptcy Prediction Modelling in the Agriculture Business
Pokorný, Petr ; Peter,, Markovič, (referee) ; Karas, Michal (advisor)
This master’s thesis is focused on problematic within the prediction of bankruptcy of companies operating in the field of agriculture in Czech republic. First part consists of introduction to companies that do business in field of agriculture and it describes bankruptcy models that are used in academicals sphere. Other part of thesis is divided into two sub-parts. First part is dedicated to an application of data into models of bankruptcy and their evaluation. Second part is focused on improvement of the best model and its main goal is to maximize the precision of the bankruptcy.
|
|
|
Students euro account evaluation
VAŇATOVÁ, Jana
The main aim of this diploma thesis was to evaluate accounts of foreign exchange for students. The evaluation was made for two potencial students with different preferences. Another aim is carried out survey and later compare all results.
|
|
|
Evaluation of the suppliers of KVM Impex, s.r.o.
Popelík, Tomáš ; Houška, Milan (advisor) ; Horáková, Tereza (referee)
The bachelor thesis predominantly focuses on the use of multi-criteria decision analysis for the solution of the optimal selection of existing suppliers of a selected company. The objective of this thesis is to analyse data with methods of multi-criteria decision-making and to make a recommendation to the managing directors of a tire dealercompany. With the inflow of non-European suppliers (producers) who are entering the Czech market, it is necessary to closely followtheselected productportfolio of these suppliers. Consequently, it is essential to analyse it and to select, which suppliers are the most suitable ones, and then to strenghten and deepen mutualcooperation with these suppliers. The first part of the thesis is focused on a theoretical description of the Saaty Model, as well as of theAspiration Level Model, Scoring Model, Ranking Model, Weighted Sum Model and the TOPSIS Model, including practical examples of all these models. All mentioned models are then applied in the second part of this bachelor thesis. The elimination of suppliers with a narrow product portfolio was performed based on an analysis according to the Aspiration Level Model. The Saaty Model, theScoring Model, and the Ranking Modelfor the subjective criteria evaluation were used for the determination of the ranking of suppliers in the portfolio. This final suppliers ranking can be recommended to the company's decision-makers as the most suitable strategy for the deepening of the cooperation with suppliers.
|
|
|
Multiple Criteria Decison Making in Firm Practice
Maček, Jiří ; Dömeová, Ludmila (advisor) ; Hlavatý, Robert (referee)
This bachelor thesis focuses on the theme Multiple Criteria Decision Making in Firm Practise. The aim of the thesis is to choose an appropriate sowing machine for the company Agro K+M s. r. o.
The beginning of the theoretical part describes the definitions of the basic terms which are connected to the theme. The following overview is concerning the most important theories of the decision making and their related elements. The thesis uses some of the methods of the multiply criteria decision making. At the end of the theoretical part, there is a description of some important terms such as the ploughing and the no-ploughing soil tillage.
The practical part applies the appropriate methods of multiply criteria analysis of variants in the selection of universal sowing machine. At first there are established criteria, afterwards there is used the Saaty Method of quantitative pair-wise comparison. As the best alternative is used Analytic Hierarchy Process (AHP) method for the calculation of the benefits of individual variants. At the end of the bachelor thesis, variants are ordered according to their benefits. The best variant is consulted with the user.
Keywords: Multiple Criteria Decision Making, model, weight, firm practise, Multiple Criteria Analysis of Variant, criterion
|
guest ::
