|
| |
|
|
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.
|
|
|
Evaluation of Economy of Selected Non Profit Organization
Bartušková, Jana ; Šebestová, Monika (referee) ; Lajtkepová, Eva (advisor)
The bachelor thesis deals with the evaluation of the economy development of the selected nonprofit organization “Integrované centrum sociálních služeb Jihlava”, and that is for the period from 2017 to 2021. The aims and methods of the work are introduced at the beginning of the thesis. The theoretical part defines the basic concepts for the processing of the analytical part. The analytical part deals with the description of the selected organization, and the analysis of the costs, revenues and selected indicators of modified financial analysis. The proposals for the organization are presented in the conclusion.
|
|
|
Evaluation of Economy and Fundraising of Selected Non Profit Organization
Štraubová, Veronika ; Šebestová, Monika (referee) ; Lajtkepová, Eva (advisor)
The bachelor thesis focuses on economic evaluation and fundraising activities of selected non-governmental non-profit organization called Dobrovolnické centrum Kladno.In the theoretical part of the bachelor's thesis there is a description of the issues of the non-profit sector and fundraising which is presented on the basis of selected literature. In the analytical part of the bachelor's thesis there is an analysis of costs and revenues and modified financial analysis. Based on these analyses there is a summary of development of the economy and fundraising. The last part of the bachelor's thesis is dedicated to own proposals for improving weaknesses.
|
|
|
Using Artificial Intelligence to Reduce Risk in a Company
Friedl, Pavel ; Šebestová, Monika (referee) ; Dostál, Petr (advisor)
Presented diploma thesis is focused on evaluation of the supplier’s risk and the selection of the most suitable supplier with the use of artificial intelligence. The main part of the diploma thesis deals with the creation of the decision models. The decision models will be created in MS Excel and MATLAB based on the rules of the fuzzy logic. These models will determine the most suitable supplier for the company expert Elektro GOLA s.r.o. and they will also evaluate the supplier’s risk.
|
|
| |
|
|
The Application of Fuzzy Logic for Rating of Suppliers for the Firm
Ondruch, Lukáš ; Šebestová, Monika (referee) ; Dostál, Petr (advisor)
The master’s thesis deals with the use of fuzzy logic for evaluating the quality of suppliers of IT goods and other material for a selected company. The fuzzy model should facilitate decisions when selecting individual suppliers who should deliver goods for the implementation of IT projects. The model created in Microsoft Excel and MathWorks MATLAB should be helpful to the company's management and sales representatives.
|
|
| |
|
| |
|
|
Implementation of the information system
Marečková, Veronika ; Šebestová, Monika (referee) ; Novák, Lukáš (advisor)
This bachelor thesis focuses on the selection of a suitable system for internal business process requisitions. The output of my work will be an application for general requests. The first part contains theoretical concepts. The second part contains basic information about the company and possible solutions. The third part is about creating application.
|
guest ::
RSS feed.