National Repository of Grey Literature 396 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
The use of convolutional neural networks for predicting the financial failure of a company
Šebestová, Monika ; Chramcov, Bronislav (referee) ; Lenort, Radim (referee) ; Režňáková, Mária (referee) ; Dostál, Petr (advisor)
The doctoral thesis deals with the use of convolutional neural networks for predicting the financial failure of companies. A bibliometric analysis was used during the processing of the literature review, which enabled a better orientation in scientific works oriented to the methods and approaches used in the past to predict the financial failure of companies. On the basis of the obtained knowledge, a deep learning model based on the GoogLeNet architecture was proposed, with inputs consisting of financial and macroeconomic indicators of companies. The modeling was based on the transfer learning method, in which it is possible to fine-tune the parameters of the pre-established networks to accelerate the learning process of the convolutional neural network. The initial set of financial and macroeconomic indicators was compiled from the variables that were most often used in business failure prediction models in scientific papers. Appropriate statistical methods were used for the specific selection of indicators from which the model is built. Since convolutional neural networks work best with image processing, the quantitative values of the input indicators were graphically interpreted and it was investigated which type of graphical processing is most suitable for predicting the failure of companies. Due to the existence of an unbalanced data set, the effect of the SMOTE method on the accuracy of the model's prediction was analyzed in the thesis. The method was used to increase the number of samples of the minority class of firms. To model the prediction of financial default, several variants of models were proposed, which differed in the form of input data. It was tested how the removal of outliers from the data set, the point in time from which the data come or the method of predictor selection will affect the accuracy of the prediction. The parameters of the resulting model were further fine-tuned so that it was able to classify businesses from new real data. The research conducted showed that using the right type of graphical processing of input data, SMOTE technique and appropriate parameter settings, convolutional neural networks can predict the financial failure of companies with high accuracy.
Application of Fuzzy Logic for Evaluating Investments in Stock Markets
Šmerda, Patrik ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis focuses on the application of fuzzy logic in constructing a decisionmaking model for evaluating investment opportunities in stock markets, with a specific emphasis on the selection of exchange-traded funds. The model is based on essential criteria that play a crucial role in the efficient selection of funds. These criteria are implemented in two decision-making models that have been developed using Microsoft Excel and MATLAB tools. The results obtained from these models provide a solid foundation for further steps in the investment decision-making process.
Application of Fuzzy Logic for Evaluating Investments in Stock Markets
Jovič, Marko ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis deals with the application of fuzzy logic in supplementary models that serve as a support tool for solving decision-making questions in the field of stock market investments. The models encompass evaluative criteria and their attributes, which are used to evaluate various types of investment assets. The models are implemented in MS Excel using the VBA programming language and MATLAB from MathWorks.
The Application of Fuzzy Logic for Rating of Suppliers
Fedor, Tomáš ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis is prepared on the topic of choosing a suitable supplier for a company using fuzzy logic for a specific company. This thesis is developed in several environments, including MS Excel, the Python programming language, and MATLAB.
Optimal risk sensitive control in radical chains
Picek, Radovan ; Dostál, Petr (advisor) ; Maslowski, Bohdan (referee)
In the first segment this thesis deal with Markov chains with discreet time and a finite set of states. Subsequently there is introduced valuation of transitions and a possibility of controlling these chains. Yields from valuation of transitions are then appointed to exponential utility funcion and discounted to the begining. Afterwards there is estab- lished Howard's iterative algorithm, which finds optimal control. The control is optimal amongst homogeneous and non-homogeneous controls. In the second segment, Markov chains are generalized to so called radical chains, again with discreet time and a finite set of states. The generalization is executed by adding an opportunity of choosing radical decisions, which take place out of real time. Howard's iterative algorithm is modified for this more general case. The control found by the algorithm is optimal amongst homoge- neous and non-homogeneous controls. 1
Risk of Choosing a Supplier Using Fuzzy Logic
Sekáč, Jan ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis is focused on analysis and evaluation of supplier risk using the theory of fuzzy logic. The analysis and evaluation of suppliers' risks was compiled for the company PROBYT REAL s.r.o., which is looking for a supplier of construction work for the reconstruction of its building. Two decision models based on the principles of fuzzy logic were created in this work. The models were processed in MS Excel and MATLAB software. The selection of the least risky supplier is based on the results of the models.
The Use of Artificial Intelligence to Reduce Risk in the Company
Smija, Jakub ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis deals with the analysis and subsequent evaluation of selected commercial vehicle models from individual manufacturers, using artificial intelligence methods. The introductory chapters focus on the basics of risk science, fuzzy logic and software tools, their purpose is to acquaint readers with the issues addressed. The analytical part of the work contains a description of the selected company and also an introduction of specific suppliers. The main part contains decision criteria for the selection and also a description of the actual solution of the assignment. More specifically, two decision models based on fuzzy logic, which were created using MS Excel and MATLAB. In the end, the results from both models are compared, including the interpretation of the obtained results.
Supplier Risk Evaluation Using Fuzzy Logic
Novák, Lukáš ; Peštál, Ivan (referee) ; Dostál, Petr (advisor)
The diploma thesis deals with the evaluation of suppliers using fuzzy logic for a selected company. The created model will be used to make efficient and faster decisions about selecting the most suitable supplier for the given orders. Based on the criteria that are important for the selected company, a fuzzy model is created. The final evaluations of the most suitable suppliers are created in MS Excel and MATLAB.
Evaluation of Investment Risks Using Fuzzy Logic
Žáček, Jakub ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
The diploma thesis deals with the evaluation of an investment using fuzzy logic for a specific company. With the help of the created decision-making models, the company will be able to efficiently and quickly evaluate which investment brings the highest benefit. These models follow the criteria that are most important to the company when deciding on an investment. The work also contains theoretical background, which serves as a basis for creating and evaluating models.
Evaluating an appropriate investment strategy using fuzzy logic
Macharová, Aneta ; Janková, Zuzana (referee) ; Dostál, Petr (advisor)
This diploma thesis deals with the use of fuzzy logic in evaluating a suitable investment strategy for those interested in investing. Models created in MS Excel and MathWorks MATLAB will be used for this evaluation. The first part of the thesis presents the theory that is needed to understand the addressed problematics. The second part presents a selected company for which the work is processed, and the final part contains models, results and proposals found through evaluation via fuzzy logic.

National Repository of Grey Literature : 396 records found   1 - 10nextend  jump to record:
See also: similar author names
17 DOSTÁL, Petr
16 Dostal, Pavel
2 Dostál, Patrik
16 Dostál, Pavel
Interested in being notified about new results for this query?
Subscribe to the RSS feed.