|
|
Impact of European Central Bank and Federal Reserve System statements on cryptocurrency markets via sentiment analysis
Krejcar, Vilém ; Krištoufek, Ladislav (advisor) ; Čech, František (referee)
This study explores the impact of public statements from major central banks, specifically the FED and the ECB, on Bitcoin volatility from 2018 to 2021. Utilizing high-frequency data, we computed Bitcoin's volatility and extracted sentiment scores from the central banks' communications using two methods: the FinBERT language model and the state-of-the-art Generative AI GPT-4 model with tailored prompt. The GPT-4 model, capturing more nuanced senti- ment from text, was deemed superior. Our analysis involved comparing various models, with the HAR model emerging as the most e ective for this study. The research findings are particularly significant: negative sentiment from the ECB during the pandemic was associated with immediate and significant increases in Bitcoin volatility, indicating a market reaction of caution when faced with negative emission. These findings highlight the significant impact of central bank sentiment on Bitcoin volatility, confirming the initial hypothesis of this research. Additionally, the results provide a motivation to incorporate Genera- tive Artificial Intelligence into academic research as a tool for uncovering novel insights. JEL Classification C32, C55, C58, E58, G15 Keywords central banks, sentiment analysis, volatility, Bit- coin, GenAI, HAR, FED, ECB Title Impact of European...
|
|
|
xG Statistics in Football Matches: Predictions and Betting
Černý, Sebastian ; Hanus, Luboš (advisor) ; Šťastná, Lenka (referee)
The thesis studies the effectiveness of betting on the results of football matches using Expected Goals (xG) statistics from two sources Understat and FootyS- tats. It evaluates the performance of 6 different models in seasons 2021/2022 and 2022/2023 across the Ąve highest-ranked European leagues using binary logistic regression to predict two possible results, either the home team winning or away team not losing. For betting, several strategies are used based on ex- isting literature. The results are compared to the model containing traditional variables used commonly for predictions in football based on relevant litera- ture. Using both a combination of xG and traditional variables, and only xG variables the results suggest that xG variables are effective for predicting the outcome of football games. The model containing only Understat xG variables yielded 4.18% return on investment (ROI) when betting on every match in both seasons, which was 3.6% more than the model with traditional variables. For betting only on particular matches based on certain criteria, the combined models with both types of variables had the best results, reaching 10.87% ROI that again outperformed the model with traditional variables by approximately 4.5%. JEL ClassiĄcation C10, C53, L83, Z29 Keywords football, expected...
|
|
|
Methods of Biomedical Informatics in the study of inflammatory bowel disease in children
Čopová, Ivana ; Hradský, Ondřej (advisor) ; Ďuricová, Dana (referee) ; Krupička, Radim (referee)
METHODS OF BIOMEDICAL INFORMATICS IN THE STUDY OF INFLAMMATORY BOWEL DISEASE IN CHILDREN Abstract Inflammatory bowel diseases (IBD) are a group of chronic, polygenic diseases primarily affecting the gastrointestinal tract, with an increasing incidence in both adult and paediatric populations globally. These diseases include Crohn's disease (CD), ulcerative colitis (UC) and so-called IBD unclassified (IBD-U). Faecal calprotectin (FC) is a marker of inflammation in IBD and its levels correlate with disease activity as defined by clinical parameters, endoscopic findings and histology. Current medical practice is associated with the availability of a large amount of clinical data and the desire to apply it effectively in the medical decision-making process in such a way as to achieve the maximum possible reduction in the risk of adverse disease course and the occurrence of disease- and/or treatment-associated complications. The primary goal of this dissertation is to apply biomedical informatics methods to paediatric IBD in the process of validating FC in predicting disease activity and response to treatment, searching for additional potential predictive factors, and developing prediction models for specific clinical situations. We found that the development of FC levels in the early phase of induction therapy...
|
|
|
Prediction of effects of single point mutations on protein-nucleic acids interactions
Štěpánková, Věra Tereza ; Novotný, Marian (advisor) ; Neuwirthová, Tereza (referee)
Single point mutations are the most common type of mutations and many of them can have pathogenic effects, it is therefore useful to be able to correctly and effectively predict their impact on a given protein. Proteins interacting with nucleic acids are essential for most cellular processes. Progress in computational methods and machine learning enables the development of increasingly high-quality tools for predicting the effect of mutations on proteins. An important category of these predictors are tools for predicting the effect of single point mutations on protein interactions with nucleic acids. This thesis focuses on currently available tools for prediction of missense mutation effect on protein-NA interactions, which predict quantitative changes in protein and nucleic acid affinity and estimate the severity of the mutation based on this change. Attention is also paid to methods for evaluating the quality of predictions of individual tools. Keywords: point mutation, prediction, interaction, mechanism
|
|
|
Assessing Economic Situation of a Company and Proposals for Its Improvement
Rybár, Tomáš ; Novotná, Veronika (referee) ; Doubravský, Karel (advisor)
The diploma thesis focuses on the assessment of the economic situation of Prefa Brno a.s. and possible suggestions for improving its performance. The theoretical part of the thesis is devoted to the explanation of the concepts of financial and statistical analysis. These concepts are then applied in the analytical part. From the financial analysis, the difference and ratio indicators are evaluated, supplemented by a set of indicators. Regression analysis is performed on selected ratios with a forecast for the following period and correlation analysis is used to identify the interrelationships between them. Conclusions are drawn from the results, which are used to formulate possible measures to improve the current economic situation of the entity under study.
|
|
|
Models for Predicting Business Financial Performance
Vakhrushev, Dmitrii ; Oulehla, Jiří (referee) ; Luňáček, Jiří (advisor)
The thesis focuses on models for predicting the financial performance of the ALZA company, where it focused on emphasizing the strong financial performance and stability of the company. Key factors contributing to ALZA's success will be mentioned, such as consistent revenues, profits, effective cost management and investment in innovation. In addition, the work would also focus on potential strategies for further growth, such as exploring new markets, strengthening online sales, diversifying product offerings, and strengthening relationships with customers and suppliers. Emphasizing the importance of continuous innovation, market monitoring and strategic investment will demonstrate ALZA's readiness for future success and market expansion.Using financial data for the period 2017 to 2022, market trends and industry benchmarks, accurate predictions can be made regarding ALZA's future financial results. Implementing advanced modelling techniques and incorporating different scenarios can provide valuable insights for strategic decision-making.
|
|
|
Prediction of future air quality
Roháček, Adam ; Sekora, Jiří (referee) ; Čmiel, Vratislav (advisor)
This thesis explores the prediction of future air quality as a critical aspect of environmental health and sustainable development. With the increasing concerns over air pollution and its detrimental effects on human health and the environment, there is a growing need for accurate forecasting techniques to anticipate and mitigate potential air quality issues. This thesis introduces the reader to the topic of air pollution, describes the usage of prediction algorithms and evaluates quality of the own algorithm.
|
|
|
Predicting the success of football players using machine learning methods
Janeček, Jan ; Filipenská, Marina (referee) ; Ředina, Richard (advisor)
This bachelor thesis focuses on the implementation of an artificial neural network in the Python programming language using the Keras library. The aim of the work is the numerical prediction of a football player’s match readiness on a scale from 0 to 1. The prediction is based on five physiological-kinematic data obtained from three training sessions preceding a given match. The reference data for training the artificial neural network includes technical data on the number of successful and total actions during the match. The data used in this work was collected from Sigma Olomouc U19 football club players using Polar Team Pro and Wyscout software. The lowest recorded model error, which was 0.1046, was achieved using a single hidden layer containing 15 perceptrons.
|
|
|
Air quality measurement with prediction
Sadriyeva, Kamilya ; Janoušek, Oto (referee) ; Čmiel, Vratislav (advisor)
This work focuses on the issue of measuring and predicting indoor air quality using the Python programming language. It includes an analysis of existing methods for air quality monitoring, the design of a data collection model, the creation of a predictive model, and the application of computational algorithms to address this issue.
|
|
|
Health assessment using smart devices
Vargová, Enikö ; Filipenská, Marina (referee) ; Němcová, Andrea (advisor)
This thesis deals with the possibilities of non-invasive determination of blood glucose from photoplethysmographic signals. Elevated blood sugar is often associated with disease called diabetes mellitus. Diabetes is one of the world’s major chronic diseases. Untreated diabetes is often a cause of death. The aim of the work is to propose methods for glycemic classification and prediction. Two datasets have been created by recording the PPG signals using two smart devices (a smart wristband and a smartphone), along with their blood glucose levels measured in an invasive way. The PPG signals were preprocessed, and suitable features were extracted from them. Various machine-learning models for glycemic classification and prediction were created.
|
guest ::
