|
|
Integrating Artificial Intelligence into Fast-Moving Consumer Goods
Bagi, Juraj ; Hříbek, David (referee) ; Rozman, Jaroslav (advisor)
Accurate sales forecasting is pivotal for operational efficiency in the Fast-Moving Consumer Goods (FMCG) sector. This thesis explores the application of Long Short-Term Memory (LSTM) models, a specialized form of recurrent neural networks, to enhance the precision of sales predictions. Unlike traditional statistical methods, LSTMs are adept at capturing temporal dependencies within sales data, potentially offering more accurate forecasts. By applying LSTM models to historical sales data from a food industry company, this research demonstrates improvements over conventional forecasting techniques. The findings suggest that LSTMs can significantly help FMCG companies in optimizing inventory management and demand planning, thereby contributing valuable insights into artificial intelligence applications in supply chain management. These results emphasize the practical implications for FMCG stakeholders to embrace advanced artificial intelligence technologies to remain competitive in a dynamic market environment.
|
|
|
Automated trading systems
Šafář, Vítězslav ; Hříbek, David (referee) ; Rozman, Jaroslav (advisor)
Trading in the financial market is something almost everyone has heard of these days, but automated trading is still a novelty for most. The aim of this bachelor's thesis is to design and create several automatic trading systems using the application programming interface provided by XTB, and subsequently evaluate these automated trading systems using historical data. The thesis presents four differently complex automated trading systems, achieving various profits at certain risk levels. Furthermore, the thesis demonstrates the usability of the mentioned XTB application programming interface. The best-designed system evaluated was the one utilizing the MACD indicator,which achieved an average annual return of around 13.5 % with a level of risk of loss, approximately 39 %.
|
|
|
Automatic System for Shares Trading
Škorpík, Josef ; Rozman, Jaroslav (referee) ; Hříbek, David (advisor)
Thesis presents the possibilities of automatic trading on the stock market and options of brokers that allow different ways of automatic stock trading. They were trading strategies were described and then implemented in Python. Furthermore, the following is described an application created to test these strategies, which allows users to perform testing with different parameters over different time periods. Also, the strategies can be deployed ei- ther on a real or demo account of the Alpaca Markets trading platform. In addition, one can manipulate one’s own accounts with this broker through the application and enter or cancel orders. In this thesis, the design of the solution of this system is described and the implementation is described. The next part of the thesis deals with a thorough testing of all strategies over the European index STXE 600 and the US SP 500 index using predefined evaluation parameters. Subsequently, the strategies were run over real data for several days over a portfolio of demo account.
|
|
|
Automatic System for Options Trading
Vintoňak, Roman ; Rozman, Jaroslav (referee) ; Hříbek, David (advisor)
Options are becoming very popular tool for traders. In this theses I will first explain basic principles of markets, options, stocks and other relevant topics. Then I will perform research of brokers, who are working within Czech Republic and allow options trading. After that I will come up with various trading strategies for trading options, implement an environment for backtesting said strategies and analyse them. Finally I will implement an application for automated trading based on those strategies.
|
|
|
Automatic System for Cryptocurrency Trading
Mráz, Filip ; Rozman, Jaroslav (referee) ; Hříbek, David (advisor)
The thesis focuses on the creation of an automatic trading system (ATS) that is capable of simulating trading on historical stock exchange data and performing automated trading on the account of a selected broker. The system can statistically process and graphically display achieved results. User operates the system via a clear graphical user interface. Individual trading sessions are managed by the system in separate subprocesses. ATS implements 5 trading strategies of varying complexity, which are responsible for managing the trading decisions. Strategies use elements of technical analysis to interpret historical price move- ments, which serve as the basis for making buying and selling decisions. The fifth strategy utilizes a trained XGBoost model for its decision-making. Implemented strategies were tho- roughly tested on historical data, selecting periods with different market moods and price volatilities. Test results did not reveal any consistently profitable strategy, instead defining the strategies as high-risk.
|
|
|
Active Learning for Processing of Archive Sources
Hříbek, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work deals with the creation of a system that allows uploading and annotating scans of historical documents and subsequent active learning of models for character recognition (OCR) on available annotations (marked lines and their transcripts). The work describes the process, classifies the techniques and presents an existing system for character recognition. Above all, emphasis is placed on machine learning methods. Furthermore, the methods of active learning are explained and a method of active learning of available OCR models from annotated scans is proposed. The rest of the work deals with a system design, implementation, available datasets, evaluation of self-created OCR model and testing of the entire system.
|
|
|
Semi-Automatic Word Normalization in Parish Records
Hříbek, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work deals with the extension of DEMoS web application for the management of parish records by the possibility of normalization (assignment of a normalized form of writing to individual words) of names, surnames, occupations, domiciles and other types of words occurring in parish records. In the solution, a duplicate record detection process was used, which allowed sorting of the records from parish records into clusters of similar words. As a result of the clustering, it was possible to share normalized word variants within these clusters. Thus, DEMoS suggests normalized variants for words entered by users, used not only for the same words, but also for similar words. In this work, automatic testing of word clustering was proposed. In total, 640 different combinations of clustering parameters were tested for each word type. Subsequently, the best clustering parameters were selected for each word type. By normalizing words, DEMoS application significantly increases the efficiency of searching in parish records. Records are also easier to read.
|
|
|
Detection of Fake News Using Machine Learning
Koreň, Matej ; Zbořil, František (referee) ; Hříbek, David (advisor)
This thesis focuses on the use of machine learning in fake news detection. For this purpose, four models have been selected – Bayesian, Decision Tree, Support Vector Machine and a Neural Network. In five experiments on various datasets, these models were trained, tested, evaluated and compared with state-of-the-art methods. Final implementation is in the form of a Python package, which allows it’s users to replicate this procedure with their own data. Beyond the assignment, Slovak dataset Dezinfo SK was created.
|
|
|
Measuring the Thickness of Material Layers Removed from a Sample in an Electron Microscope
Kutálek, Jiří ; Hříbek, David (referee) ; Čadík, Martin (advisor)
Motivace pro tuto práci vyvstává ze zájmu firmy Thermo Fisher Scientific o vyvinutí metody pro měření tloušťky vrstev odprášeného materiálu ze vzorku v elektronovém mikroskopu. Hlavním cílem práce je navržení meřicí metody, jež bude z praktického hlediska efektivnější než metody stávající. Mimo to, druhotným cílem je nalezení způsobu pro získání ground truth pro měření, která by umožnila navrženou metodu vyhodnotit. Tato práce představuje dvě nové meřicí metody detekující pozici hrany vzorku v obraze a způsob pro získání ground truth, spočívající ve vypálení drobných jamek (teček) do povrchu vzorku a následné detekce a počítání teček v obrázcích vzorku. Pro účely vyhodnocení všech metod jsem nasbíral tři sady obrázků. Výsledky experimentů ukazují, že jedna z navržených metod, Top-Down FIB, měří konzistentní hodnoty blízké očekávanému průměru a z porovnání vůču ground truth vychází o něco lépe, než state-of-the-art metoda. Navíc, algortimus počítající tečky v obraze se ukazál býti použitelnou metodou pro získání ground truth, neboť dosáhl stabilnějších výsledků, než alternativní ground truth vygenerovaná manuální anotací dat.
|
|
|
Active Learning for Work with Archive Materials
Štajerová, Alžbeta ; Hříbek, David (referee) ; Rozman, Jaroslav (advisor)
The aim of this Master's thesis is to design and implement an OCR system for archival historical documents containing handwriting text. The first part of the thesis deals with the study of optical character recognition, the process of OCR pipepline. Then the topic of active learning and its methods is described. The thesis reviews the available solutions for recognition of handwritten historical documents. I further describe the neural network architectures used for text detection. The thesis results in the design and subsequent implementation of system for text recognition of historical documents, enabling user annotation, full-text search in annotation records.
|
guest ::
