|
on Computational Economics |
| By: | Shuozhe Li; Zachery B Schulwol; Risto Miikkulainen |
| Abstract: | To the naked eye, stock prices are considered chaotic, dynamic, and unpredictable. Indeed, it is one of the most difficult forecasting tasks that hundreds of millions of retail traders and professional traders around the world try to do every second even before the market opens. With recent advances in the development of machine learning and the amount of data the market generated over years, applying machine learning techniques such as deep learning neural networks is unavoidable. In this work, we modeled the task as a multivariate forecasting problem, instead of a naive autoregression problem. The multivariate analysis is done using the attention mechanism via applying a mutated version of the Transformer, "Stockformer", which we created. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.09625 |
| By: | Zhang, Luyao |
| Abstract: | In this research, we explore the nexus between artificial intelligence (AI) and blockchain, two paramount forces steering the contemporary digital era. AI, replicating human cognitive functions, encompasses capabilities from visual discernment to complex decision-making, with significant applicability in sectors such as healthcare and finance. Its influence during the web2 epoch not only enhanced the prowess of user-oriented platforms but also prompted debates on centralization. Conversely, blockchain provides a foundational structure advocating for decentralized and transparent transactional archiving. Yet, the foundational principle of "code is law" in blockchain underscores an imperative need for the fluid adaptability that AI brings. Our analysis methodically navigates the corpus of literature on the fusion of blockchain with machine learning, emphasizing AI's potential to elevate blockchain's utility. Additionally, we chart prospective research trajectories, weaving together blockchain and machine learning in niche domains like causal machine learning, reinforcement mechanism design, and cooperative AI. These intersections aim to cultivate interdisciplinary pursuits in AI for Science, catering to a broad spectrum of stakeholders. |
| Date: | 2023–11–02 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:g2q5t_v1 |
| By: | Britz, Wolfgang; Storm, Hugo |
| Abstract: | We design, detail and test an approach to optimize a social welfare function over a surrogate model of a global multi-regional Computable General Equilibrium (CGE) model. Latin-Hypercube sampling generates random observations of policy instruments considered in the later optimization. The observations are individually solved in the CGE model and jointly define the data set on which a Multi-Layer Perceptron Neural Network is trained and validated in Python packages. The trained parameters of the Neural Network are passed to GAMS as an Algebraic Modelling language to optimize a welfare function over policy instruments, subject to the surrogate model and further topical constraints. The set-up and its implementation are to a large degree generic such that application to differently structured and detailed CGE models and considered policy instruments is straightforward. The main dis-advantage is that the generation of the observation sample is computing time intensive, on a modern laptop it required about 30 hours. The trained Neural Network replicates the simulation behavior of the CGE model quite accurately with all outputs predicted with a R2 > 99.998%. The representation as a Neural Network provides a set of relatively simple equations which can be solved very fast and implemented easily in different software packages. Besides optimization, such a surrogate model representing key input-output relations of a CGE model could hence also be integrated easily in some other modelling framework. |
| Keywords: | Agricultural and Food Policy, Public Economics, Research Research Methods/Statistical Methods |
| Date: | 2025–03–27 |
| URL: | https://d.repec.org/n?u=RePEc:ags:ubfred:355478 |
| By: | Yu, Chen |
| Abstract: | In the epoch where artificial intelligence (AI) has become the harbinger of civilization's progress, the integration of cultural inheritance and identity into AI development emerges as a pivotal concern, especially for non-Western societies. "The Garden of Forking Paths: Options for Non-Western Societies in the Age of AI" explores the nuanced landscape that these societies navigate in the age of AI, juxtaposing the risks of cultural homogenization against the potential for cultural reinforcement through AI. The article delves into the metaphor of forking paths to depict the complex decisions and strategies that non-Western countries face in preserving their cultural uniqueness amidst the global AI revolution. It outlines a series of strategic interventions, including the formulation of culturally-rooted AI ethics guidelines, leveraging AI to promote heritage and languages, fostering participatory AI development, creating indigenized AI solutions, and encouraging cross-cultural AI dialogue and collaboration. These strategies are proposed as avenues to ensure that AI development not only respects but also enriches the cultural diversity of the global community. The article concludes with a call to action for stakeholders across the globe to engage in the co-creation of an AI future that is inclusive, respectful, and reflective of the rich tapestry of human cultures, thereby shaping an AI legacy that complements and enhances cultural inheritance. |
| Date: | 2024–02–22 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:bk8q2_v1 |
| By: | Fujio KAWASHIMA |
| Abstract: | Starting with the release of the Chat GPT in November 2022, the current remarkable development of Generative Artificial Intelligence (AI) has led to active discussions at both the national and international levels on how AI should be regulated. In parallel, generative AI has rapidly been developed and deployed in practical settings. In April 2023, the Cyberspace Administration of China (CAC) took the initiative in releasing the “Interim Measures for the Administration of Generated Artificial Intelligence Services, " which covers the entire process from the development stage to the provision of services, and which is highly controlling and interventive in nature. In July of the same year, however, the Interim Measures for the Administration of Generated Artificial Intelligence was enacted and announced jointly by the CAC, the National Development and Reform Commission, the Ministry of Education, the Ministry of Science and Technology, the Ministry of Industry and Information Technology, the Ministry of Public Security, and the State Administration of Radio and Television, and a stark shift was made towards a more innovation-oriented focus. In the fall of 2023, the U.S. withdrew its proposals in the Indo-Pacific Economic Framework (IPEF) and World Trade Organization (WTO) e-commerce negotiations due to the need to secure domestic policy space for AI and other regulatory issues. As shown by such a development, domestic discussion and interest conflicts surrounding AI governance may significantly affect negotiations of rules on e-commerce at the international level. Against this backdrop, this paper offers a detailed analysis of trends in AI regulations in China in order to understand domestic interests and contribute to an understanding of China's current stance in international negotiations, and to provide a foundation for interpreting future changes and predicting the future impact on international AI governance. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:eti:rdpsjp:25005 |
| By: | Yu, Chen |
| Abstract: | The advent of artificial intelligence (AI) has ushered in a new epoch in the realm of economic governance, challenging the traditional balance between government intervention (the visible hand) and market forces (the invisible hand). This article delves into the transformative potential of AI in reshaping economic policy and market dynamics. It begins by elucidating the historical roles of the visible and invisible hands in economic theory, setting the stage for an exploration of AI's burgeoning influence. The potential impacts of AI on central planning and resource allocation are examined, highlighting the opportunities for enhanced decision-making and the challenges posed by privacy concerns and automation bias. In the market sphere, AI's effect on consumer behavior, competition, and price mechanisms is scrutinized, alongside ethical considerations and the need for robust regulatory frameworks. The article then navigates the convergence of AI with economic governance, advocating for a balanced approach to government intervention and market freedom. Policy implications are discussed, proposing strategies for governments to leverage AI while upholding economic principles. The future outlook section anticipates AI's trajectory in economic decision-making and offers recommendations for stakeholders. The article concludes by emphasizing the importance of a responsible and informed engagement with AI in economic policymaking, calling for collaborative efforts to ensure AI's ethical integration into economic systems. |
| Date: | 2024–01–03 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:tvchw_v1 |
| By: | Yu, Chen |
| Abstract: | The article "AI Revolution: Reshaping Global Value Chains for the Future" explores the transformative impact of artificial intelligence (AI) on global value chains (GVCs). It provides an in-depth analysis of the current landscape of traditional GVCs, the role of AI in reshaping value chains, implications and challenges arising from AI adoption, and future outlook and predictions. The article emphasizes the importance of adaptability, innovation, and responsible AI adoption in navigating the evolving landscape of AI-driven value chains. |
| Date: | 2023–12–29 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:n6hb2_v1 |
| By: | Nico Knuth; Andreas Nastansky (Hochschule für Wirtschaft und Recht (HWR) Berlin) |
| Abstract: | Die Fähigkeit Volatilität präzise vorherzusagen, ist von zentraler Bedeutung für das Risikomanagement in Banken und für das Treffen fundierter Anlageentscheidungen. In diesem Beitrag wird der Einsatz von Deep-Learning-Methoden − speziell des Long Short-Term Memory (LSTM)-Netzwerkes − zur Prognose der Volatilität des Deutschen Aktienindex analysiert. Hierbei wird die Prognosegüte des LSTMs mit der von gängigen zeitreihenökonometrischen Ansätzen, wie den Generalized Autoregressive Conditional Heteroscedaticity (GARCH)- Modellen, verglichen. Obwohl LSTMs in vielen Bereichen zunehmend Anwendung finden, ist ihr Einsatz in der Vorhersage von Finanzmarktzeitreihen im Vergleich zu etablierten ökonometrischen Modellen noch wenig untersucht. Die empirischen Ergebnisse zeigen, dass das LSTM verschiedene symmetrische und asymmetrische GARCH-Modelle in Bezug auf die Vorhersagegenauigkeit sowohl im Trainings- als auch im Testdatensatz deutlich übertrifft. Künstliche Neuronale Netze bieten eine bessere Generalisierungsfähigkeit und niedrigere Prognosefehler. Gleichzeitig werden Herausforderungen des Einsatzes neuronaler Netze im stark regulierten Bankensektor diskutiert. |
| Keywords: | asymmetrische Volatilität, GARCH, LSTM, Künstliche Neuronale Netze, Volatilitätsprognosen |
| JEL: | C45 C58 G17 |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:pot:statdp:59 |
| By: | Yeshineh, Alekaw Kebede; Woldeyes, Firew Bekele |
| Abstract: | This study uses a Computable General Equilibrium (CGE) model to analyse the impact of skilled and semi-skilled labour supply shocks on the overall Ethiopian economy and sectoral outputs. The study considers three policy scenarios: a 10% increase, a 15% increase, and a 20% increase in skilled and semi-skilled labour supply compared to a business-as-usual (BAU) scenario. The results of the study show that all the three scenarios lead to higher economic growth, investment, and exports. The impact on sectoral outputs is also positive, with the industry and services sectors performing better than the agriculture sector. Specifically, the results of a 20% increase scenario show that real annual Gross Domestic Product (GDP) growth rate will be 0.79 percentage points higher than the business-as-usual scenario. It also shows that annual growth rates of investments and exports will be 2.69 and 2.31 percentage points higher, respectively, than the business-as-usual scenario counterparts. Furthermore, annual production of the agriculture sector grows marginally by 0.16 percentage points, higher than the business-as-usual scenario. Output in the industry sector also increases by 1.61 percentage points higher than the business-as-usual scenario, while outputs in the services sector improve significantly as well. Overall, the study finds that increasing the supply of skilled and semi-skilled labour has a positive impact on the economy. This is because skilled and semi-skilled workers are more productive and can contribute to higher economic growth. The findings of this study have important implications for policy makers. Governments could implement policies to increase the supply of skilled and semi-skilled labour, for example by investing in education and training programmes. This would boost economic growth and improve the living standards of the population. |
| Date: | 2024–08–05 |
| URL: | https://d.repec.org/n?u=RePEc:aer:wpaper:64185c50-ae6b-47fe-b9d5-c0b124cb098c |