|
on Payment Systems and Financial Technology |
| By: | Ozili, Peterson K |
| Abstract: | Artificial intelligence (AI) is rapidly growing with new use cases emerging every day. AI has many applications in the financial sector. It has applications for risk management, fraud detection, efficiency, cost savings and improved customer experience. However, its applications for digital financial inclusion and development finance are yet to be explored in the literature. This study explores how artificial intelligence can be used to increase digital financial inclusion. Specifically, the study explores the potential for AI to streamline the operations of agents of digital financial inclusion; determine the communal areas in need of digital financial inclusion; automate the digital formal account opening process; offer customized experience for both banked and unbanked adults; ensure security and safety of customers’ funds; determine the credit worthiness of unbanked adults who have recently become banked; give banked adults full control of their financial lives; deepen digital financial inclusion; and promote equity and diversity for digital financial inclusion. The study also identifies the challenges of AI for digital financial inclusion. It further presents some insights on the possible AI governance frameworks for digital financial inclusion. The insights offered in this study are useful to guide countries and policymakers that want to use AI to accelerate digital financial inclusion. |
| Keywords: | Artificial intelligence, financial inclusion, digital financial inclusion, AI algorithm, digital technology, unbanked adults, machine learning. |
| JEL: | O30 O31 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:125033 |
| By: | Ozili, Peterson K |
| Abstract: | The objective of this article is to present some of the current thinking and arguments about central bank digital currency (CBDC) from the perspective of those who have vested interests in central bank digital currency (CBDC) and from those who are opposed to CBDC. The article gives the reader an opportunity to reflect deeply about CBDC and to make their own opinion about CBDC based on the informed insights of others. From the collection of quotes, it was found that the concept of a central bank digital currency has come to stay, and many central banks want to issue a CBDC in the distant future. It was also found that, despite the efforts of central banks and pro-CBDC enthusiasts to publicise the benefits of a CBDC for citizens, many people continue to raise daunting questions about the potential for government overreach and surveillance, loss of competitive advantages for deposit-taking financial institutions, loss of privacy for citizens, and concerns that CBDC development is an unwholesome distraction for central banks, among other concerns. There is also a perceived negative sentiment about CBDC, and this sentiment is unlikely to change anytime soon. |
| Keywords: | central bank, CBDC, central bank digital currency, wholesale CBDC, retail CBDC, financial stability, financial crisis, financial inclusion, payments. |
| JEL: | E52 E58 E59 O31 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:124263 |
| By: | Xie, Danyang |
| Abstract: | The United States and China exhibit markedly different development paths in digital assets and blockchain technology. The US relies on market-driven approaches, with the private sector promoting stablecoin innovation to strengthen the dollar’s global position, while China adopts a government-led approach, implementing centralized systems such as consortium chains and the digital yuan (e-CNY), emphasizing financial security and regulation. These divergent paths reflect fundamental institutional differences: American distrust of centralized institutions has fostered distributed ledger development, while China mitigates risks through government leadership. Currently, the digital yuan faces adoption challenges due to insufficient enthusiasm from commercial banks. We propose implementing a “dynamic reserve mechanism” to incentivize circulation and enhance privacy protection to address user concerns. The private sector should participate more actively in innovation, and we recommend establishing AI-supported “dynamic regulatory sandboxes” or “smart regulatory gateways” based on smart contracts to better balance innovation and regulatory needs. To address inflation and depegging risks of stablecoins, we recommend moving beyond fiat currency pegging to explore new models anchored to consumer goods, such as a “BigMac Coin.” |
| Keywords: | Central Bank Digital Currency; Stablecoins; Blockchain; Financial Regulation; Financial Innovation; Regulatory Sandbox |
| JEL: | E42 E58 F33 G28 |
| Date: | 2025–05–27 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:124989 |
| By: | Craig S. Wright (Department of Economics, University of Exeter) |
| Abstract: | BTC, diverging fundamentally from the original Bitcoin protocol, has attained outsized market capitalisation despite abandoning Bitcoin's primary function as a scalable, traceable system for electronic cash. The Lightning Network, frequently misrepresented as a Layer 2 solution, is demonstrably a separate payment routing structure that never requires final settlement on-chain. This paper deconstructs the economic, technical, and ideological divergence of BTC from Bitcoin, critiques the architectural and empirical failure of Lightning, and examines the speculative mispricing driven by false narratives, branding confusion, and structural ignorance. |
| Keywords: | BTC, Bitcoin, Lightning Network, digital cash, scalability, protocol divergence, Layer 2, micropayments, transaction finality, network economics |
| JEL: | E42 G18 L86 O33 |
| Date: | 2025–07–01 |
| URL: | https://d.repec.org/n?u=RePEc:exe:wpaper:2502 |
| By: | Song, Myungkoo (Korea Institute for Industrial Economics and Trade) |
| Abstract: | Roughly speaking, blockchain is a digital ledger that records transactions in a distributed database spread across multiple computers. Its decentralized nature enhances security, making blockchain-based platforms or applications highly resilient. In addition, by enabling a permanent, immutable, and transparent record of transactions, blockchain has the potential to foster trust without the need for intermediaries, especially in environments where trusted third parties are scarce. There is also growing interest in blockchain in the manufacturing sector. Manufacturers worldwide are currently navigating a complex landscape of challenges, including intense global competition, supply chain disruptions, and increasing demands for sustainability. South Korean manufacturers in particular are facing substantial headwinds due to the rise of Chinese manufacturers, global trade tensions, and a demographic crisis driven by low birth rates and an aging population. To address these challenges, firms are looking intensely at adopting emerging technologies such as blockchain, artificial intelligence (AI), and quantum computing. Manufacturing interest in blockchain owes to the technology’s ability to enhance data integrity and foster trust among parties. Firms also view the technology as a key to unlocking innovative solutions to the aforementioned industry challenges. In this paper, I explore the growth of the blockchain industry in South Korea and examine the potential of blockchain technology in the country’s manufacturing sector. First, I examine the current state of the country’s blockchain industry and its adoption in the manufacturing sector. Next, I analyze use cases and assess how blockchain can improve competitiveness in the sector. Finally, I discuss the role of government policy in facilitating blockchain integration to strengthen the competitiveness of the manufacturing sector further. |
| Keywords: | blockchain; ICT; digital technology; cryptocurrency; industrial blockchain; Bitcoin; manufacturing; decentralization; digital ledger; South Korea; Korean blockchain; advanced digital industry; Korea Institute for Industrial Economics and Trade; KIET |
| JEL: | L60 L63 L86 O25 O30 |
| Date: | 2025–04–30 |
| URL: | https://d.repec.org/n?u=RePEc:ris:kieter:2025_012 |
| By: | Jonathan Chiu; Cyril Monnet |
| Abstract: | Central bankers argue that programmable digital currencies may compromise the uniformity of money. We explore this in a stylized model where programmable money arises endogenously, and differently programmed monies have varying liquidity. Programmability provides private value by easing commitment frictions but imposes social costs under informational frictions. Preserving uniformity is not necessarily socially beneficial. Banning programmable money lowers welfare when informational frictions are mild but improves it when commitment frictions are low. These insights suggest programmable money could be more beneficial on permissionless blockchains. |
| Keywords: | Digital currencies and fintech; Payment clearing and settlement systems |
| JEL: | E50 E58 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocawp:25-18 |
| By: | Ozili, Peterson K |
| Abstract: | This study examines the effect of CO2 emissions from gaseous fuel consumption on financial inclusion through physical financial access points in non-crisis years. The findings reveal that higher CO2 emissions are associated with a high level of financial inclusion in European, Asian and developing countries, implying that CO2 emissions do not decrease the level of financial inclusion. CO2 emissions decrease the level of financial inclusion in African countries that have strong institutions and a high lending rate. CO2 emissions also decrease the level of financial inclusion in developing countries that have a high lending rate. The implication is that policymakers and banks in European, African and Asian countries should reduce their reliance on physical financial access points to increase financial inclusion. They should adopt digital financial inclusion strategies to mitigate the adverse effect of CO2 emissions on the physical financial access points provided by banks to increase financial inclusion. |
| Keywords: | climate change, CO2 emissions, financial inclusion, institutional quality, inflation, interest rate, financial access points, bank branch, ATM, Africa, Asia, Europe, developing countries. |
| JEL: | G21 Q01 Q50 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:125032 |
| By: | Gauci, Ian |
| Abstract: | Disclosure Statement: The author declares no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. ABSTRACT This article critiques the European Union’s regulatory approach to decentralised finance (DeFi), which transposes traditional institutional oversight frameworks onto systems with fundamentally different architectures. DeFi protocols are non-custodial, pseudonymous, composable, and autonomously executed, making classical regulatory approaches structurally incompatible. Legal systems assuming identity, hierarchy, and discretionary control prove inadequate for supervising systems designed to eliminate such centralisation. Drawing on EU constitutional principles, regulatory theory, and jurisprudence, this article develops a dual-layer oversight model using Malta as a case study. The framework proposes licensing fiduciary conduct under the Malta Financial Services Authority while providing infrastructure assurance through the Malta Digital Innovation Authority. This model anchors accountability to proximity rather than legal fiction, and to function rather than form, offering a scalable solution respecting EU subsidiarity principles. Keywords: Decentralised Finance, Financial Regulation, European Union, Malta, Blockchain, Smart Contracts |
| Date: | 2025–06–30 |
| URL: | https://d.repec.org/n?u=RePEc:osf:lawarc:8nkqg_v1 |
| By: | Erum Iftikhar; Wei Wei; John Cartlidge |
| Abstract: | Blockchain-based decentralised lending is a rapidly growing and evolving alternative to traditional lending, but it poses new risks. To mitigate these risks, lending protocols have integrated automated risk management tools into their smart contracts. However, the effectiveness of the latest risk management features introduced in the most recent versions of these lending protocols is understudied. To close this gap, we use a panel regression fixed effects model to empirically analyse the cross-version (v2 and v3) and cross-chain (L1 and L2) performance of the liquidation mechanisms of the two most popular lending protocols, Aave and Compound, during the period Jan 2021 to Dec 2024. Our analysis reveals that liquidation events in v3 of both protocols lead to an increase in total value locked and total revenue, with stronger impact on the L2 blockchain compared to L1. In contrast, liquidations in v2 have an insignificant impact, which indicates that the most recent v3 protocols have better risk management than the earlier v2 protocols. We also show that L1 blockchains are the preferred choice among large investors for their robust liquidity and ecosystem depth, while L2 blockchains are more popular among retail investors for their lower fees and faster execution. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.12855 |
| By: | Hjalte Fejerskov Boas (University of Copenhagen); Mona Barake (Skatteforsk, NMBU) |
| Abstract: | Cryptocurrencies pose substantial challenges to tax enforcement due to their anonymous and decentralized properties, undermining conventional regulatory practices. We study the impact of an ambitious new enforcement initiative aimed at addressing these challenges: domestic third-party reporting of crypto income. We estimate tax compliance and behavioral responses to this new policy by combining unique Danish microdata from domestic crypto platforms, administrative tax records, and cross-border bank transfers. Despite the introduction of domestic third-party reporting, over 90% of crypto investors do not declare crypto income. Moreover, we identify a significant and persistent evasion response to the policy as investors shift trading activity from domestic platforms, subject to third-party reporting, to foreign platforms outside regulatory reach. Our findings underscore the limits of domestic enforcement strategies in addressing tax evasion for decentralized, borderless assets like cryptocurrencies, highlighting the need for international coordination. |
| Keywords: | Cryptocurrencies, Tax compliance, Tax enforcement |
| JEL: | D31 H24 H26 H31 G5 |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:dbp:wpaper:029 |
| By: | Kenechukwu E. Anadu; Pablo D. Azar; Catherine Huang; Marco Cipriani; Thomas M. Eisenbach; Gabriele La Spada; Mattia Landoni; Marco Macchiavelli; Antoine Malfroy-Camine; J. Christina Wang |
| Abstract: | Similar to the more traditional money market funds (MMFs), stablecoins aim to provide investors with safe, money-like assets. We investigate similarities and differences between these two investment products. Our key finding is that, like MMFs, stablecoins also suffer from “flight-to-safety” dynamics. This is manifested in net flows from riskier to safer stablecoins on days of crypto-market stress. The same flight-to-safety dynamics also characterized flows during stablecoin runs, as exemplified by the two most severe episodes in 2022 and 2023. Furthermore, as flight-to-safety flows occur within MMF families, stablecoin flows tend to occur within blockchains. |
| Keywords: | money market mutual funds; financial stability; runs; liquidity transformation; crypto assets; stablecoins |
| JEL: | G10 G20 G23 |
| Date: | 2025–06–01 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedbqu:101131 |
| By: | Julia Ko\'nczal |
| Abstract: | The cryptocurrency options market is notable for its high volatility and lower liquidity compared to traditional markets. These characteristics introduce significant challenges to traditional option pricing methodologies. Addressing these complexities requires advanced models that can effectively capture the dynamics of the market. We explore which option pricing models are most effective in valuing cryptocurrency options. Specifically, we calibrate and evaluate the performance of the Black-Scholes, Merton Jump Diffusion, Variance Gamma, Kou, Heston, and Bates models. Our analysis focuses on pricing vanilla options on futures contracts for Bitcoin (BTC) and Ether (ETH). We find that the Black-Scholes model exhibits the highest pricing errors. In contrast, the Kou and Bates models achieve the lowest errors, with the Kou model performing the best for the BTC options and the Bates model for ETH options. The results highlight the importance of incorporating jumps and stochastic volatility into pricing models to better reflect the behavior of these assets. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.14614 |
| By: | Maria Elena Filippin |
| Abstract: | This paper examines how household-targeted government policies influence financial market participation conditional on financial literacy, focusing on potential Central Bank Digital Currency (CBDC) adoption. Due to the lack of empirical CBDC data, I use the introduction of retail Treasury bonds in Italy as a proxy to investigate how financial literacy affects households' likelihood to engage with the new instrument. Using the Bank of Italy's Survey on Household Income and Wealth, I explore how financial literacy influenced households' participation in the Treasury bond market following the 2012 introduction of retail Treasury bonds, showing that households with some but low financial literacy are more likely to participate than other household groups. Based on these findings, I develop a theoretical model to explore the potential implications of financial literacy for CBDC adoption, showing that low-literate households with limited access to risky assets allocate more wealth to CBDC, while high-literate households use risky assets to safeguard against income risk. These results highlight the role of financial literacy in shaping portfolio choices and CBDC adoption. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.12575 |
| By: | Qiuyu Lu (Ph.D. in Economics, Graduate School of Economics, the University of Osaka); Noriaki Matsushima (Osaka School of International Public Policy, the University of Osaka); Shiva Shekhar (Tilburg School of Economics and Management, Tilburg University) |
| Abstract: | This study explores the welfare impact of personalized pricing for consumers in a duopolistic two-sided market, with consumers single-homing and developers affiliating with a platform according to their outside option. Personalized pricing, which is private in nature, cannot influence expectations regarding the network sizes, inducing the platforms to offer lower participation fees for developers. Those lower fees increase network benefits for consumers, allowing the platforms to exploit these benefits through personalized pricing. Personalized prices are higher when the network value for developers is high, benefiting competing platforms at the expense of consumers. These findings offer policy insights on personalized pricing. |
| Keywords: | Personalized pricing, Uniform prices, Two-sided market, Content developers |
| JEL: | L13 D43 M21 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:osp:wpaper:25e003 |
| By: | Ozili, Peterson K |
| Abstract: | Digital public infrastructure (DPI) is an emerging innovation that leverages digital technologies to increase access to public and social services towards improving people’s welfare and livelihoods in society. DPI is a set of digital systems that enable members of society to safely and efficiently connect to open-source digital networks to access social services and other economic opportunities that improve their welfare. The study explores the concept of digital public infrastructure, the global trends, opportunities and challenges. The study also highlights some DPI success and failure stories across countries, and it offers some insights into the challenges and risks of digital public infrastructure. It was shown that digital public infrastructure has many components, and it is enabling digital access to public goods and services for many individuals who lack access to essential goods and services. As a result, many individuals and firms are connecting with one another through a public digital networked infrastructure. However, DPI poses some risks or challenges such as difficulty in evaluating impact, cybersecurity risks, lack of interoperability between digital systems, digital exclusion, lack of private and public sector collaboration, lack of accountability mechanisms, ethical dilemmas and geopolitical concerns. The discussion in this article contributes to the digital society literature by showing that digital public infrastructure is an essential part of a digital society and the benefits of DPI to society are enormous if the risks can be mitigated. |
| Keywords: | digital public infrastructure, digital ID, digital payment, data exchange, interoperability, public-private partnerships, cybersecurity, digital society |
| JEL: | O31 O33 O38 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:125029 |
| By: | Samuel Kaplan (UNC/UDESA); Efstathios Polyzos (Zayed University/CAMA Australia); David Tercero-Lucas (ICADE/ICAI/Universidad Pontificia Comillas) |
| Abstract: | The growing influence of cryptocurrencies in global financial markets has raise questions about the impact of central bank communications on their price dynamics.This paper investigates how central bank communication affects the behaviour of cryptocurrency markets. Using a dataset of over 6, 000 central bank speeches anda broad panel of crypto assets, we quantify sentiment, uncertainty, and fear tone through natural language processing and assess their impact using local projectionmethods. Our results show that positive tone initially depresses returns while raising volatility, whereas uncertainty and fear produce mixed return responses and amplifyprice fluctuations in the short run. Heterogeneity across asset types reveals stronger responses among emerging, high-performing, and non-stablecoin cryptocurrencies.The findings highlight the informational role of central bank narratives in shaping outcomes in speculative and decentralised markets, with important implications forcommunication policy and financial stability monitoring. |
| Keywords: | Cryptocurrency, Central Bank Communication, Text Analysis, Sentiment Analysis, Monetary Policy |
| JEL: | D53 E52 E58 G15 O33 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:aoz:wpaper:365 |
| By: | Marc Deschamps (Université Marie et Louis Pasteur, CRESE, UR3190, F-25000 Besançon, France); Julie Le Gallo (CESAER UMR1041, INRAE, Institut Agro Dijon, France); Catherine Refait-Alexandre (Université Marie et Louis Pasteur, CRESE, UR3190, F-25000 Besançon, France) |
| Abstract: | Drawing on data from three specialized crowdfunding platforms and on semi-structured interviews conducted with project leaders located in the French Jura Arc region, we examine the role of this financing mechanism in the transition of the agri-food system. We draw in particular on proximity theory (Torre, 2018) to show that while so-called “social” proximity (ties of family, friendship, or networks) plays a decisive role in the success of crowdfunding campaigns, geographical proximity does not appear to be a determining factor in the decision to resort to crowdfunding or in the success of these campaigns. Our exploratory study also suggests that other forms of proximity (institutional or organizational) may influence the actors’ approaches. Finally, family and friendly support remains central, whereas the effect of any “geographical neighborhood” appears much more limited. |
| Keywords: | crowdfunding, transition, agri-food, proximity theory, social and geographical proximity. |
| JEL: | G29 Q14 Q20 R11 R12 |
| Date: | 2025–04 |
| URL: | https://d.repec.org/n?u=RePEc:crb:wpaper:2025-03-eng |
| By: | Gene Amromin; Kenechukwu E. Anadu; Falk Bräuning; Amy Chapel; Rebecca Chmielewski; Meeoak Cho; Patricia K. Cowperthwait; Lorenzo Garza; Cindy E. Hull; Siobhan Sanders; Sam Schulhofer-Wohl; Brett Solimine; Emma Weiss |
| Abstract: | Technology-focused Third-Party Service Providers (TPSPs) have become important players in the operations of financial institutions and the financial markets. This paper summarizes micro- and macro-prudential regulatory frameworks in place to address risks that TPSPs pose to the financial system. The key takeaways are as follows: First, in the U.S., TPSPs operate under limited comprehensive prudential regulatory oversight, aimed primarily at ensuring that their products are safe and resilient on an ongoing basis. Second, while banks rely on multiple TPSPs and hundreds of their services daily for their core banking businesses, U.S. banking supervisors have limited direct visibility into these activities and risks they may pose. Third, although the existing U.S. regulatory framework has some systemic risk considerations, there is no macroprudential structure in place for TPSP risks. Official bodies in other jurisdictions have developed macroprudential frameworks or high-level guidance to address TPSP risks, but their implementation in major economies is nascent at best. Finally, TPSPs are likely an important source of systemic vulnerability for financial institutions and financial markets, although vulnerabilities may be difficult to discern due to a need to assess the criticality of each activity performed by TPSPs and the concentration of TPSPs within that activity. |
| Keywords: | financial stability; third-party service providers; cyber risks |
| JEL: | G10 G23 G28 |
| Date: | 2025–07–01 |
| URL: | https://d.repec.org/n?u=RePEc:fip:feddwp:101200 |
| By: | Joseph Abadi; Jesús Fernández-Villaverde; Daniel R. Sanches |
| Abstract: | We present a micro-founded monetary model of the world economy to study international currency competition. Our model features both “unipolar” equilibria, with a single dominant international currency, and “multipolar” equilibria, in which multiple currencies circulate internationally. Governments can compete to internationalize their currencies by offering attractive interest rates on their sovereign debt. A large economy has a natural advantage in ensuring its currency becomes dominant, but if it lacks the fiscal capacity to absorb the global demand for liquid assets, the multipolar equilibrium emerges. |
| Keywords: | Dominant Currency; International Monetary System; Interest-Rate Policy; Fiscal Capacity |
| JEL: | E42 E58 G21 |
| Date: | 2025–06–26 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedpwp:101163 |
| By: | Timofei Belenko; Georgii Vosorov |
| Abstract: | In this paper, we propose an analytical method to compute the collateral liquidation probability in decentralized finance (DeFi) stablecoin single-collateral lending. Our approach models the collateral exchange rate as a zero-drift geometric Brownian motion, converts it into a regular zero-drift Brownian motion, and employs the reflection principle to derive the liquidation probability. Unlike most existing methods that rely on computationally intensive simulations such as Monte Carlo, our formula provides a lightweight, exact solution. This advancement offers a more efficient alternative for risk assessment in DeFi platforms. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.08100 |
| By: | Benguria, Felipe (Gatton College of Business and Economics, University of Kentucky); Novy, Dennis (University of Warwick, CAGE, CEP/LSE, CEPR, CESifo) |
| Abstract: | How can a currency achieve more widespread international use? We study the internationalization of the Chinese renminbi (RMB) through the lens of a unique policy experiment in Argentina. In 2023, amid a severe dollar shortage, Argentina expanded a currency swap line with the People's Bank of China. Within the next few months, the share of imports from China invoiced in RMB surged rapidly to nearly 50% - displacing the US dollar, which had previously accounted for virtually all invoicing. Following the presidential election of late 2023, as macroeconomic policies changed and the dollar shortage eased, invoicing in RMB declined. We explore the mechanisms behind this aggregate pattern, using rich firm-level data on imports, bank-firm loan relationships, and bank balance sheets. Our results indicate that banks played a key role, in line with the dollar shortage narrative. First, firms with pre-existing relationships to banks with limited US dollar loans were more likely to switch to RMB. Second, firms borrowing from a Chinese state-owned bank were significantly more likely to use RMB. We also document firm-level spillovers, with RMB use for imports from China increasing the likelihood of RMB use for imports from other countries. Finally, we observe an effect on trade volumes. Firms switching to RMB saw increased total imports. |
| Keywords: | Banking, Central Bank, China, Geoeconomics, Invoicing, Lending, Renminbi, Swap, Trade, US Dollar JEL Classification: E58, F14, F31, F33, G21 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:cge:wacage:758 |
| By: | José Manuel Carbó (BANCO DE ESPAÑA); Claudia Toledo (BANCO CENTRAL DE CHILE); Ángel Iván Moreno (BANCO DE ESPAÑA) |
| Abstract: | Los diccionarios de sentimiento son una herramienta fundamental en el análisis automatizado de textos. Mientras que en inglés existen múltiples opciones para analizar textos económicos y financieros, en español las alternativas son más escasas. Dos de las más destacadas son los diccionarios desarrollados por el Banco de España y el Banco Central de Chile, diseñados para medir el sentimiento en los informes de estabilidad financiera. Este documento detalla el proceso para la obtención de un primer diccionario de consenso panhispánico, combinando ambos enfoques, que pueda ser utilizado en distintos países de habla hispana. Los resultados muestran que el diccionario resultante de la unión de ambos (diccionario «Unión») es una herramienta eficaz y equilibrada, capaz de captar el sentimiento de los textos en ambos países. Para validar su robustez, demostramos que el Unión es resistente a la eliminación de términos y que sus resultados son similares a los obtenidos con los modelos de lenguaje avanzado (LLM, por sus siglas en inglés). En general, mostramos que los diccionarios, y particularmente el mencionado diccionario Unión, pueden obtener resultados parecidos a los de los LLM en términos de sentimiento en los textos de estabilidad financiera, debido a la naturaleza estructurada y específica de estos documentos. |
| Keywords: | minería de textos, análisis de sentimiento, procesado de lenguaje natural, comunicaciones de bancos centrales, estabilidad financiera |
| JEL: | C82 G28 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:bde:opaper:2514 |