|
on Artificial Intelligence |
| By: | Damioli, Giacomo (ISER, University of Essex); Van Roy, Vincent (European Commission, Joint Research Centre); Vertesy, Daniel (European Commission, Joint Research Centre); Vivarelli, Marco (Università Cattolica del Sacro Cuore) |
| Abstract: | Artificial intelligence (AI) is emerging as a transformative innovation with the potential to drive significant economic growth and productivity gains. This study examines whether AI is initiating a technological revolution, signifying a new technological paradigm, using the perspective of evolutionary neo-Schumpeterian economics. Using a global dataset combining information on AI patenting activities and their applicants between 2000 and 2016, our analysis reveals that AI patenting has accelerated and substantially evolved in terms of its pervasiveness, with AI innovators shifting from the ICT core industries to non-ICT service industries over the investigated period. Moreover, there has been a decrease in concentration of innovation activities and a reshuffling in the innovative hierarchies, with innovative entries and young and smaller applicants driving this change. Finally, we find that AI technologies play a role in generating and accelerating further innovations (so revealing to be "enabling technologies", a distinctive feature of GPTs). All these features have characterised the emergence of major technological paradigms in the past and suggest that AI technologies may indeed generate a paradigmatic shift. |
| Keywords: | Artificial Intelligence, technological paradigm, structural change, patents |
| JEL: | O31 O33 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp17183 |
| By: | Tom Coupé (University of Canterbury) |
| Abstract: | In this paper, I analyse ChatGPT’s opinion on economic issues by repeatedly prompting ChatGPT with questions from different surveys that have been used to assess the opinion of the economics profession. I find that ChatGPT 3.5 is a one-handed economist with strong opinions, while ChatGPT4o is much more of an ‘average’ economist. I further find little evidence that the widespread use of ChatGPT4o could reduce the gap between what the general public thinks about economic issues and the economics’ profession views on those issues, that ChatGPT4o is about equally likely to prefer professors’ financial advice and the financial advice from popular books, and that ChatGPT4o is more likely to agree with less/nonmainstream views about the economics profession than the economics profession. |
| Keywords: | ChatGPT, Economic Opinion, Economists' Consensus, Public Policy, Artificial Intelligence |
| JEL: | C83 A11 D80 D83 |
| Date: | 2024–08–01 |
| URL: | https://d.repec.org/n?u=RePEc:cbt:econwp:24/13 |
| By: | Julia Schmidt; Graham Pilgrim; Annabelle Mourougane |
| Abstract: | This paper estimates the artificial intelligence-hiring intensity of occupations/industries (i.e. the share of job postings related to AI skills) in the United Kingdom during 2012-22. The analysis deploys a natural language processing algorithm (NLP) on online job postings, collected by Lightcast, which provides timely and detailed insights into labour demand for different professions. The key contribution of the study lies in the design of the classification rule identifying jobs as AI-related which, contrary to the existing literature, goes beyond the simple use of keywords. Moreover, the methodology allows for comparisons between data-hiring intensive jobs, defined as the share of jobs related to data production tasks, and AI-hiring intensive jobs. Estimates point to a rise in the economy-wide AI-hiring intensity in the United Kingdom over the past decade but to fairly small levels (reaching 0.6% on average over the 2017-22 period). Over time, the demand for AI-related jobs has spread outside the traditional Information, Communication and Telecommunications industries, with the Finance and Insurance industry increasingly demanding AI skills. At a regional level, the higher demand for AI-related jobs is found in London and research hubs. At the occupation level, marked changes in the demand for AI skills are also visible. Professions such as data scientist, computer scientist, hardware engineer and robotics engineer are estimated to be the most AI-hiring intense occupations in the United Kingdom. The data and methodology used allow for the exploration of cross-country estimates in the future. |
| Keywords: | AI-hiring intensity, artificial intelligence, job advertisements, natural language processing, united kingdom |
| JEL: | C80 C88 E01 J21 |
| Date: | 2024–09–05 |
| URL: | https://d.repec.org/n?u=RePEc:oec:comaaa:25-en |
| By: | Jean-Charles Bricongne; Baptiste Meunier; Raquel Caldeira |
| Abstract: | As text mining has expanded in economics, central banks appear to also have ridden this wave, as we review use cases of text mining across central banks and supervisory institutions. Text mining is a polyvalent tool to gauge the economic outlook in which central banks operate, notably as an innovative way to measure inflation expectations. This is also a pivotal tool to assess risks to financial stability. Beyond financial markets, text mining can also help supervising individual financial institutions. As central banks increasingly consider issues such as the climate challenge, text mining also allows to assess the perception of climate-related risks and banks’ preparedness. Besides, the analysis of central banks’ communication provides a feedback tool on how to best convey decisions. Albeit powerful, text mining complements – rather than replaces – the usual indicators and procedures at central banks. Going forward, generative AI opens new frontiers for the use of textual data. |
| Keywords: | Text Mining, Sentiment Analysis, Central Banking, Generative AI, Language Models |
| JEL: | C38 C55 C82 E58 L82 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:bfr:banfra:950 |
| By: | CJ Finnegan; James F. McCann; Salissou Moutari |
| Abstract: | In this paper we introduce a multi-agent deep-learning method which trades in the Futures markets based on the US S&P 500 index. The method (referred to as Model A) is an innovation founded on existing well-established machine-learning models which sample market prices and associated derivatives in order to decide whether the investment should be long/short or closed (zero exposure), on a day-to-day decision. We compare the predictions with some conventional machine-learning methods namely, Long Short-Term Memory, Random Forest and Gradient-Boosted-Trees. Results are benchmarked against a passive model in which the Futures contracts are held (long) continuously with the same exposure (level of investment). Historical tests are based on daily daytime trading carried out over a period of 6 calendar years (2018-23). We find that Model A outperforms the passive investment in key performance metrics, placing it within the top quartile performance of US Large Cap active fund managers. Model A also outperforms the three machine-learning classification comparators over this period. We observe that Model A is extremely efficient (doing less and getting more) with an exposure to the market of only 41.95% compared to the 100% market exposure of the passive investment, and thus provides increased profitability with reduced risk. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.11740 |
| By: | Qianqian Xie; Dong Li; Mengxi Xiao; Zihao Jiang; Ruoyu Xiang; Xiao Zhang; Zhengyu Chen; Yueru He; Weiguang Han; Yuzhe Yang; Shunian Chen; Yifei Zhang; Lihang Shen; Daniel Kim; Zhiwei Liu; Zheheng Luo; Yangyang Yu; Yupeng Cao; Zhiyang Deng; Zhiyuan Yao; Haohang Li; Duanyu Feng; Yongfu Dai; VijayaSai Somasundaram; Peng Lu; Yilun Zhao; Yitao Long; Guojun Xiong; Kaleb Smith; Honghai Yu; Yanzhao Lai; Min Peng; Jianyun Nie; Jordan W. Suchow; Xiao-Yang Liu; Benyou Wang; Alejandro Lopez-Lira; Jimin Huang; Sophia Ananiadou |
| Abstract: | Large language models (LLMs) have advanced financial applications, yet they often lack sufficient financial knowledge and struggle with tasks involving multi-modal inputs like tables and time series data. To address these limitations, we introduce \textit{Open-FinLLMs}, a series of Financial LLMs. We begin with FinLLaMA, pre-trained on a 52 billion token financial corpus, incorporating text, tables, and time-series data to embed comprehensive financial knowledge. FinLLaMA is then instruction fine-tuned with 573K financial instructions, resulting in FinLLaMA-instruct, which enhances task performance. Finally, we present FinLLaVA, a multimodal LLM trained with 1.43M image-text instructions to handle complex financial data types. Extensive evaluations demonstrate FinLLaMA's superior performance over LLaMA3-8B, LLaMA3.1-8B, and BloombergGPT in both zero-shot and few-shot settings across 19 and 4 datasets, respectively. FinLLaMA-instruct outperforms GPT-4 and other Financial LLMs on 15 datasets. FinLLaVA excels in understanding tables and charts across 4 multimodal tasks. Additionally, FinLLaMA achieves impressive Sharpe Ratios in trading simulations, highlighting its robust financial application capabilities. We will continually maintain and improve our models and benchmarks to support ongoing innovation in academia and industry. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.11878 |