|
Using data mining methods in the analysis of credit risk data
Tvaroh, Tomáš ; Witzany, Jiří (advisor) ; Matejašák, Milan (referee)
This thesis focuses on comparison of selected data mining methods for solving classification tasks with the method of logistic regression. First part of the thesis briefly introduces data mining as a scientific discipline and classification task is shown in the context of knowledge data discovery. Next part explains the principle of particular methods amongst which, along with logistic regression, artificial neural networks, classification decision trees and Support Vector Machine method were selected. Together with mathematical background of each algorithm, demonstration of how the classification functions for new examples is mentioned. Analytical part of this thesis tests decribed methods on real-world data from the Lending Club company and they are compared based on classification accuracy. Towards the end, an evaluation of logistic regression is made in terms of whether its majority position is due to historical reasons or for its high classification accuracy compared to other methods.
|
|
Methods of computer detection of fraud and anomalies in financial data
Spitz, Igor ; Mejzlík, Ladislav (advisor) ; Pelák, Jiří (referee)
This thesis analyzes techniques of manipulation of accounting data for the purpose of fraud. It is further looking for methods, which could be capable of detecting these manipulations and it verifies the efficiency of the procedures already in use. A theoretical part studies method of financial analysis, statistical methods, Benford's tests, fuzzy matching and technologies of machine learning. Practical part verifies the methods of financial analysis, Benford's tests, algorithms for fuzzy matching and neural networks.
|
|
Design and implementation of Data Mining model with MS SQL Server technology
Peroutka, Lukáš ; Maryška, Miloš (advisor) ; Smutný, Zdeněk (referee)
This thesis focuses on design and implementation of a data mining solution with real-world data. The task is analysed, processed and its results evaluated. The mined data set contains study records of students from University of Economics, Prague (VŠE) over the course of past three years. First part of the thesis focuses on theory of data mining, definition of the term, history and development of this particular field. Current best practices and meth-odology are described, as well as methods for determining the quality of data and methods for data pre-processing ahead of the actual data mining task. The most common data mining techniques are introduced, including their basic concepts, advantages and disadvantages. The theoretical basis is then used to implement a concrete data mining solution with educational data. The source data set is described, analysed and some of the data are chosen as input for created models. The solution is based on MS SQL Server data mining platform and it's goal is to find, describe and analyse potential as-sociations and dependencies in data. Results of respective models are evaluated, including their potential added value. Also mentioned are possible extensions and suggestions for further development of the solution.
|
|
Character recognition of real scenes using neural networks
Fiala, Petr ; Neumann, Lukáš (advisor) ; Berka, Petr (referee)
This thesis focuses on a problem of character recognition from real scenes, which has earned significant amount of attention with the development of modern technology. The aim of the paper is to use an algorithm that has state-of-art performance on standard data sets and apply it for the recognition task. The chosen algorithm is a convolution network with deep structure where the application of the specified model has not yet been published. The implemented solution is built on theoretical parts which are provided in comprehensive overview. Two types of neural network are used in the practical part: a multilayer perceptron and the convolution model. But as the complex structure of the convolution networks gives much better performance compare with the classification error of the MLP on the first data set, only the convolution structure is used in the further experiments. The model is validated on two public data sets that correspond with the specification of the task. In order to obtain an optimal solution based on the data structure several tests had been made on the modificated network and with various adjustments on the input data. Presented solution provided comparable prediction rate compare to the best results of the other studies while using artificially generated learning pattern. In conclusion, the thesis describes possible extensions and improvements of the model, which should lead to the decrease of the classification error.
|
|
Neural Networks in R
Arzumanov, Eduard ; Bašta, Milan (advisor) ; Žižka, David (referee)
The aim of this work was to present the issue of neural network, which is still, despite the fact it exist and has been applied for several years, remains quite unknown for a considerably big part of public and academical environment. The aim of the practical part was to verify via practical application if neural network are truly a better instrument of statistical analysis, than the commonly used ones, especially when the goal is to analyze and describe complex processes and relationships between them. Further aim of the work was to investigate and describe the relationships between the development of trading volumes of Apple shares and the shares of competitive companies regarding the market of smart phones such as Google, HTC, Nokia, Samsung using neural network models. The attainment of these goals was realized through a rather extensive description of neural networks theory as well as the presentation of valuable theoretical tools for avoiding the frequent barriers occurring during the practical implementation. This practical application was realized via software called R, which has widely spread lately due to its availability and a vast range of flexibility, which is provided to users. The value of this work is familiarization and the creation of an integrated knowledge within readers about the issue of neural networks and the deliverance of a proof, that neural networks are indeed a better tool compared to the commonly used ones (ARMA models, linear regression). The author of the work gained a lot of useful knowledge about neural networks, learned how to use them in practice especially in the environment of R software, by which he shifted his proficiency with the current software to a whole new level.
|
|
Neural and Fuzzy Modelling of Hydrological Data
Neruda, Roman ; Coufal, David
The main goal of this work is to model flood waves based on runoff and precipitation data. We utilize data from the Smeda rivera catchment provided by the CHMI in order to build several models of flood episodes. Multilayer perceptron networks and Fuzzy system models are used and their performance is compared to traditional hydrological approaches.
Fulltext: content.csg - PDF Plný tet: v1172-12 - PDF
|
|
Statistical Expectation of High Energy Physics Data Sets Separation Algorithms
Hakl, František
Article focuses on the application of the basic results of the statistical learning theory known as Probabilistic Approximately Correct learning in the evaluation and post-processing of unique physical data obtained from the detectors of particle accelerators. The aim of this article is not direct separation of the measured data but evaluation of the appropriateness of separation methods used. The main principles and results of the PAC learning theory are briefly summarized, the main characteristics of selected multivariable data separation algorithms are studied from the VC-dimension point of view. Finally, based on actual data sets obtained from Tevatron D$\emptyset$ experiment, some practical hints for separation method selection and numerical computation are derived.
|
|
Robustness Aspects of Knowledge Discovery
Kalina, Jan
The sensitivity of common knowledge discovery methods to the presence of outlying measurements in the observed data is discussed as their major drawback. Our work is devoted to robust methods for information extraction from data. First, we discuss neural networks for function approximation and their sensitivity to the presence of noise and outlying measurements in the data. We propose to fit neural networks in a robust way by means of a robust nonlinear regression. Secondly, we consider information extraction from categorical data, which commonly suffers from measurement errors. To improve its robustness properties, we propose a regularized version of the common test statistics, which may find applications e.g. in pattern discovery from categorical data.
|
|
Using data mining to manage an enterprise.
Prášil, Zdeněk ; Pour, Jan (advisor) ; Novotný, Ota (referee)
The thesis is focused on data mining and its use in management of an enterprise. The thesis is structured into theoretical and practical part. Aim of the theoretical part was to find out: 1/ the most used methods of the data mining, 2/ typical application areas, 3/ typical problems solved in the application areas. Aim of the practical part was: 1/ to demonstrate use of the data mining in small Czech e-shop for understanding of the structure of the sale data, 2/ to demonstrate, how the data mining analysis can help to increase marketing results. In my analyses of the literature data I found decision trees, linear and logistic regression, neural network, segmentation methods and association rules are the most used methods of the data mining analysis. CRM and marketing, financial institutions, insurance and telecommunication companies, retail trade and production are the application areas using the data mining the most. The specific tasks of the data mining focus on relationships between marketing sales and customers to make better business. In the analysis of the e-shop data I revealed the types of goods which are buying together. Based on this fact I proposed that the strategy supporting this type of shopping is crucial for the business success. As a conclusion I proved the data mining is methods appropriate also for the small e-shop and have capacity to improve its marketing strategy.
|
|
Modern trends in the area of computer physics
SURYNEK, Radek
The theme of the thesis is to make a list few fundamental modern methods which can be used in computerized physics. The thesis describes parallel computing, neural networks,genetic algorithms, fuzzy logic. Every chapter include theoretical description, simplified mathematical expression, proposals of technical solution. Applications are briefly mentioned here too. The printed matter is completed with a few simple examples. The closing part of the thesis acquired information about these methods and outlines their future development.
|