Master's Thesis from the year 2022 in the subject Economics - Other, grade: 1,3, University of Frankfurt (Main), language: English, abstract: The Global Financial Crisis, starting in 2007, served as a reminder of the serious impact that imbalances originating in financial markets can have on economic growth. The aftermath of this economic shock with the ensuing recession continues to concern policymakers to this day. The subsequent period characterized by subdued growth and few but severe recessions gave rise to the importance of linkages between economic policy and risk management. The connection between this idea and the relevance of financial variables for analyzing growth risks is established by Adrian et al. (2019). They employ quantile regressions to examine the conditional distribution of future GDP growth and find that its left tail is exposed to substantially more volatility over time than the right tail. Moreover, they find that financial conditions for the US measured by the National Financial Conditions Index (NFCI) can serve as a relevant predictor of downside risk to conditional future economic growth. This thesis examines some machine-learning based variable selection methods that have been largely unexplored in the GaR context. The focus is on generating higher predictive power compared to the model by Adrian et al. (2019) rather than on analyzing economic relationships. The approaches described here are easy to apply and can help to automate the selection of variables for GaR estimation instead of having to manually choose relevant indicators. In detail, the LASSO method is used in the quantile regression context (Belloni and Chernozhukov 2011; Li and Zhu 2008), as well as the Adaptive (Wu and Liu 2009) and Relaxed LASSO (Meinshausen 2007), two of its modifications. In addition, the Elastic Net method is investigated as a compromise between Ridge and LASSO regression. To test the performance of these models, a backtesting exercise is conducted based on US data ranging from 1986 to 2019. The out-of-sample analysis is performed under the expanding and rolling window approach. For evaluation of the models, some of the backtesting tools used by Brownlees and Souza (2019) to perform a similar analysis for volatility models in the GaR context are utilized. In this regard, the following research question is formulated: Can the machine learning-based models improve the predictive power measured by the introduced backtesting tools for the investigated period compared to the quantile regression base model?

This study applies state-of-the-art machine learning (ML) techniques to forecast IMF-supported programs, analyzes the ML prediction results relative to traditional econometric approaches, explores non-linear relationships among predictors indicative of IMF-supported programs, and evaluates model robustness with regard to different feature sets and time periods. ML models consistently outperform traditional methods in out-of-sample prediction of new IMF-supported arrangements with key predictors that align well with the literature and show consensus across different algorithms. The analysis underscores the importance of incorporating a variety of external, fiscal, real, and financial features as well as institutional factors like membership in regional financing arrangements. The findings also highlight the varying influence of data processing choices such as feature selection, sampling techniques, and missing data imputation on the performance of different ML models and therefore indicate the usefulness of a flexible, algorithm-tailored approach. Additionally, the results reveal that models that are most effective in near and medium-term predictions may tend to underperform over the long term, thus illustrating the need for regular updates or more stable – albeit potentially near-term suboptimal – models when frequent updates are impractical.

Artificial Intelligence (AI) is an extensive concept that can be interpreted as a concentration on designing computer programs to train machines to accomplish functions like or better than hu-mans. An important subset of AI is Machine Learning (ML), in which a computer is provided with the capacity to learn its own patterns instead of the patterns and restrictions set by a human programmer, thus improving from experience. Deep Learning (DL), as a class of ML techniques, employs multilayered neural networks. The application of AI to plant science research is new and has grown significantly in recent years due to developments in calculation power, proficien-cies of hardware, and software progress. AI algorithms try to provide classifications and predic-tions. As applied to plant breeding, particularly omics data, ML as a given AI algorithm tries to translate omics data, which are intricate and include nonlinear interactions, into precise plant breeding. The applications of AI are extending rapidly and enhancing intensely in sophistication owing to the capability of rapid processing of huge and heterogeneous data. The conversion of AI techniques into accurate plant breeding is of great importance and will play a key role in the new era of plant breeding techniques in the coming years, particularly multi-omics data analysis. Advancements in plant breeding mainly depend upon developing statistical methods that harness the complicated data provided by analytical technologies identifying and quantifying genes, transcripts, proteins, metabolites, etc. The systems biology approach used in plant breeding, which integrates genomics, transcriptomics, proteomics, metabolomics, and other omics data, provides a massive amount of information. It is essential to perform accurate statistical analyses and AI methods such as ML and DL as well as optimization techniques to not only achieve an understanding of networks regulation and plant cell functions but develop high-precision models to predict the reaction of new Genetically Modified (GM) plants in special conditions. The constructed models will be of great economic importance, significantly reducing the time, labor, and instrument costs when finding optimized conditions for the bio-exploitation of plants. This Research Topic covers a wide range of studies on artificial intelligence-assisted plant breeding techniques, which contribute to plant biology and plant omics research. The relevant sub-topics include, but are not restricted to, the following: • AI-assisted plant breeding using omics and multi-omics approaches • Applying AI techniques along with multi-omics to recognize novel biomarkers associated with plant biological activities • Constructing up-to-date ML modeling and analyzing methods for dealing with omics data related to different plant growth processes • AI-assisted omics techniques in the plant defense process • Combining AI-assisted omics and multi-omics techniques using plant system biology approaches • Combining bioinformatics tools with AI approaches to analyze plant omics data • Designing cutting-edge workflow and developing innovative AI biology methods for omics data analysis

Artificial Intelligence and Machine Learning for Predictive and Analytical Rendering in Edge Computing focuses on the role of AI and machine learning as it impacts and works alongside Edge Computing. Sections cover the growing number of devices and applications in diversified domains of industry, including gaming, speech recognition, medical diagnostics, robotics and computer vision and how they are being driven by Big Data, Artificial Intelligence, Machine Learning and distributed computing, may it be Cloud Computing or the evolving Fog and Edge Computing paradigms. Challenges covered include remote storage and computing, bandwidth overload due to transportation of data from End nodes to Cloud leading in latency issues, security issues in transporting sensitive medical and financial information across larger gaps in points of data generation and computing, as well as design features of Edge nodes to store and run AI/ML algorithms for effective rendering. - Provides a reference handbook on the evolution of distributed systems, including Cloud, Fog and Edge Computing - Integrates the various Artificial Intelligence and Machine Learning techniques for effective predictions at Edge rather than Cloud or remote Data Centers - Provides insight into the features and constraints in Edge Computing and storage, including hardware constraints and the technological/architectural developments that shall overcome those constraints

Explores text mining and IoT applications for monitoring and controlling smart industrial systems Describes the key principles and techniques for Big-data analytics, security, and optimization for industrial applications. Provides context-aware insights, human-centric industry, smart computing for next-generation industry

This book (vol. 1) presents the proceedings of the IUPESM World Congress on Biomedical Engineering and Medical Physics, a triennially organized joint meeting of medical physicists, biomedical engineers and adjoining health care professionals. Besides the purely scientific and technological topics, the 2018 Congress will also focus on other aspects of professional involvement in health care, such as education and training, accreditation and certification, health technology assessment and patient safety. The IUPESM meeting is an important forum for medical physicists and biomedical engineers in medicine and healthcare learn and share knowledge, and discuss the latest research outcomes and technological advancements as well as new ideas in both medical physics and biomedical engineering field.

The Era of Artificial Intelligence, Machine Learning and Data Science in the Pharmaceutical Industry examines the drug discovery process, assessing how new technologies have improved effectiveness. Artificial intelligence and machine learning are considered the future for a wide range of disciplines and industries, including the pharmaceutical industry. In an environment where producing a single approved drug costs millions and takes many years of rigorous testing prior to its approval, reducing costs and time is of high interest. This book follows the journey that a drug company takes when producing a therapeutic, from the very beginning to ultimately benefitting a patient's life. This comprehensive resource will be useful to those working in the pharmaceutical industry, but will also be of interest to anyone doing research in chemical biology, computational chemistry, medicinal chemistry and bioinformatics. - Demonstrates how the prediction of toxic effects is performed, how to reduce costs in testing compounds, and its use in animal research - Written by the industrial teams who are conducting the work, showcasing how the technology has improved and where it should be further improved - Targets materials for a better understanding of techniques from different disciplines, thus creating a complete guide

The Financial Crisis was a cross-sector crisis that fundamentally affected modern society. Regulation, as a concept, was both blamed for allowing the crisis to happen, but also tasked with developing and implementing solutions in the wake of the crash. In this book, a number of specialists from a range of fields have contributed their insights into the effect of the Financial Crisis upon the regulatory frameworks affecting their fields, how regulators have responded to the Crisis, and then what this may mean for the future of regulation within those industries. These analyses are joined by a picture of past financial crises – which reveals interesting patterns – and then analyses of architectural regulatory models that were fundamentally affected by the Crisis. The book aims to allow sector specialists the freedom to share their insights so that, potentially, a broader picture can be identified. Providing an interesting and thought-provoking account of this societally impactful era, this book will help the reader develop a more informed understanding of the potential future of financial regulation. The book will be of value to researchers, students, advanced level students, regulators, and policymakers.