In the context of the rapid development of digital finance, some financial technology companies exhibit the phenomenon of "AI washing," where they overstate their AI capabilities while underinvesting in actual AI resources. This paper constructs a corporate-level AI washing index based on CHFS2019 data and AI investment data from 15-20 financial technology companies, analyzing and testing its impact on farmers' digital financial behavior response. The study finds that AI washing significantly suppresses farmers' digital financial behavior; the higher the degree of AI washing, the lower the response level of farmers' digital financial behavior. Moreover, AI washing indirectly inhibits farmers' behavioral responses by exacerbating knowledge exclusion and risk exclusion. Social capital can positively moderate the negative impact of AI washing; among farmer groups with high social capital, the suppressive effect of AI washing on digital financial behavior is significantly weaker than that among groups with low social capital. In response, this paper suggests that regulatory authorities establish a strict information disclosure system for AI technology, conduct differentiated digital financial education to enhance the identification capabilities of vulnerable groups, promote digital financial mutual aid groups to leverage the protective effects of social capital, improve the consumer protection mechanism for farmers in digital finance, and set up pilot "Digital Inclusive Finance Demonstration Counties," etc.
Many problems can be formulated as high-dimensional integrals of discontinuous functions that exhibit significant boundary growth, challenging the error analysis and applications of randomized quasi-Monte Carlo (RQMC) methods. This paper studies RQMC methods for super-fast growing functions satisfying generalized exponential growth conditions, with a special focus on financial derivative pricing. The main contribution of this paper is threefold. First, by combining RQMC with importance sampling (IS), we derive a new error bound for a class of integrands, whose values and derivatives are bounded by the critical growth function $e^{A|\boldsymbol{x}|^2}$ with $A = 1/2$. This result extends the existing results in the literature, which are limited to the case $A < 1/2$. We demonstrate that by imposing a light-tailed condition on the proposal distribution of IS, RQMC can achieve an error rate of $O(n^{-1 + ε})$ with a sample size n and an arbitrarily small $ε>0$. Second, we verify that the Gaussian proposals used in Optimal Drift Importance Sampling (ODIS) satisfy the required light-tailed condition, providing a rigorous theoretical guarantees for RQMC-ODIS in critical growth scenarios. Third, for discontinuous integrands from finance, we prove that the integrands after preintegration satisfy the exponential growth condition. This ensures that the preintegrated functions can be seamlessly incorporated into our RQMC-IS framework. Numerical experiments on financial derivative pricing validate our theory, showing that the RQMC-IS with preintegration is effective in handling problems with discontinuous payoffs, successfully achieving the expected convergence rates.
Giovanni Ballarin, Jacopo Capra, Petros Dellaportas
Stock return prediction is a problem that has received much attention in the finance literature. In recent years, sophisticated machine learning methods have been shown to perform significantly better than ''classical'' prediction techniques. One downside of these approaches is that they are often very expensive to implement, for both training and inference, because of their high complexity. We propose a return prediction framework for intraday returns at multiple horizons based on Echo State Network (ESN) models, wherein a large portion of parameters are drawn at random and never trained. We show that this approach enjoys the benefits of recurrent neural network expressivity, inherently efficient implementation, and strong forecasting performance.
Saeid Ario Vaghefi, Aymane Hachcham, Veronica Grasso
et al.
Tracking financial investments in climate adaptation is a complex and expertise-intensive task, particularly for Early Warning Systems (EWS), which lack standardized financial reporting across multilateral development banks (MDBs) and funds. To address this challenge, we introduce an LLM-based agentic AI system that integrates contextual retrieval, fine-tuning, and multi-step reasoning to extract relevant financial data, classify investments, and ensure compliance with funding guidelines. Our study focuses on a real-world application: tracking EWS investments in the Climate Risk and Early Warning Systems (CREWS) Fund. We analyze 25 MDB project documents and evaluate multiple AI-driven classification methods, including zero-shot and few-shot learning, fine-tuned transformer-based classifiers, chain-of-thought (CoT) prompting, and an agent-based retrieval-augmented generation (RAG) approach. Our results show that the agent-based RAG approach significantly outperforms other methods, achieving 87\% accuracy, 89\% precision, and 83\% recall. Additionally, we contribute a benchmark dataset and expert-annotated corpus, providing a valuable resource for future research in AI-driven financial tracking and climate finance transparency.
Abstract The standard crow search algorithm suffers from low convergence accuracy, insufficient stability, and susceptibility to getting stuck in local optima. To tackle these formidable challenges, this paper proposes a novel multi-strategy improved crow search algorithm (MSICSA) specifically designed for multi-level image segmentation. The proposed approach incorporates three key enhancements: firstly, opposition-based learning (OBL) is utilized to improve the quality of initial solutions within MSICSA; secondly, an adaptive awareness probability mechanism is introduced to better balance the trade-off between exploration and exploitation; lastly, two differential mutation operators are developed to enhance global search capabilities, increase population diversity, and reduce the risk of converging on local optima. To validate the performance of the proposed algorithm, two sets of experiments are conducted. In the first set of experiments, CEC 2020 benchmark test functions are selected to compare the performance of MSICSA with other group intelligent optimization algorithms. In the second set of experiments, Otsu’s method and fuzzy entropy are employed as objective functions for performing multilevel threshold segmentation on twelve grayscale images. The experimental results demonstrate that MSICSA outperforms seven comparison algorithms in terms of both convergence speed and segmentation quality.
The housing markets in former Soviet Union countries have undergone substantial transformations since 1991, with mortgage lending emerging as a pivotal instrument driving housing demand and ownership. In Georgia, as in many other post-Soviet states, official data demonstrate a consistent rise in the number of individuals entering the mortgage market to purchase housing, particularly finished housing units. This trend underscores the necessity of understanding the socio-economic factors that influence mortgage uptake among urban residents, particularly in rapidly transforming transitional economies. This study investigates the determinants of mortgage loan acquisition for the purchase of finished housing, using primary survey data collected from a sample of 356 mortgage loan holders in Tbilisi, the capital and largest city of Georgia.
The empirical results indicate that individual income and employment status are the most significant predictors of a household’s decision to secure a mortgage. Higher income levels and stable, formal employment significantly increase the likelihood of mortgage loan approval and uptake. In contrast, demographic variables such as age, gender, and education level were found to have limited predictive power in the decision-making process. These findings highlight the critical role of economic security, labor market integration, and reliable income sources in shaping access to housing finance in transitional economies.
This study contributes to the existing literature in three main ways. First, it offers novel empirical insights into the socio-economic characteristics of mortgage borrowers in Georgia, addressing a substantial gap in the regional literature. Second, it provides a foundational assessment of the Georgian housing finance landscape, serving as a reference point for comparative studies in other former Soviet republics, including Armenia and Azerbaijan. Third, the study delivers practical implications for policymakers, financial institutions, and housing market stakeholders by offering data-driven evidence on the prerequisites for mortgage accessibility in post-socialist urban contexts. In doing so, it enhances the understanding of mortgage dynamics within the broader framework of economic transition, institutional development, and urban transformation.
In recent years, supply chain finance has developed rapidly in mainland China, and its “supply chain attributes” and “financial attributes” cannot be ignored in enhancing corporate dynamic capabilities. Drawing on the panel data of A-share-listed firms in Shanghai and Shenzhen over the period from 2010 to 2023, this study empirically investigates the influence of supply chain finance on corporate persistent innovation. The outcomes display that supply chain finance can significantly promote corporate persistent innovation. Mechanism analysis indicates that supply chain finance can enhance corporate dynamic capabilities, which is likely to be an important channel for the improvement of corporate persistent innovation levels. Heterogeneity analysis shows that in sample firms holding shares of financial institutions, with high customer concentration, high supplier concentration, and high ESG ratings, the promoting effect of supply chain finance on corporate persistent innovation is more evident. Extended analysis shows that supply chain disruptions can significantly inhibit corporate persistent innovation; persistent innovation can enhance corporate profitability and supply chain stability. The research findings of this paper enrich the studies on the economic consequences of supply chain finance and provide beneficial references and insights for enterprises to adopt supply chain finance, financial institutions to innovate financing models, and the government to formulate precise and effective corporate support policies.
Abstract To address the challenges of low efficiency, complex processes, low accuracy, and high costs in financial management, this paper proposes utilizing blockchain and IoT technologies, specifically Blockchain-based Smart Contract and Biometric Multifactor Authentication (BCSC-BMFA), to develop an intelligent financial management system for technical institutions. The proposed BMFA system aims to provide secure and transparent data management, real-time monitoring and reporting, and automation of financial processes to improve accuracy, efficiency, and transparency. Blockchain-based ledgers are used to store financial data securely, along with IoT sensors such as Point-of-Sale (POS) sensors and asset tracking sensors, to capture real-time financial data, and smart contracts to automate financial processes. This framework improves accuracy and efficiency, reduces costs, and increases transparency and accountability. The system’s efficiency is evaluated using a pilot study to demonstrate its performance and effectiveness in a real-world scenario.
This paper examines whether companies’ innovativeness affects the availability of capital and, therefore, whether this group is financially constrained. It uses an objective, indirect way of measuring financial constraints based on the assumption that financially restricted firms only invest when internal cash flow allows them to do so. Therefore, the research was based on the investment-cash flow equation, more precisely the adjusted ECM model adapted to the SME sector. The companies’ innovativeness was measured based on a proprietary synthetic indicator covering a broad range of information on innovation activity. The research was conducted on a sample of 403 firms, including large companies. The modified methodology for studying financial constraints confirmed that innovative small and medium-sized enterprises are financially constrained, contrary to non-innovative SMEs and large enterprises, both the innovators and those with low innovation potential. Based on the model analysis, it has been noticed that in innovative enterprises, there may be substitution between investing in tangible assets and human capital – personnel costs decrease a year before investment projects are implemented. Furthermore, innovative SMEs implement projects in response to a deteriorating situation, shrinking sales market, falling revenues and accompanying employment reduction.
Though there has been substantial progress in developing quantum algorithms to study classical datasets, the cost of simply \textit{loading} classical data is an obstacle to quantum advantage. When the amplitude encoding is used, loading an arbitrary classical vector requires up to exponential circuit depths with respect to the number of qubits. Here, we address this ``input problem'' with two contributions. First, we introduce a circuit compilation method based on tensor network (TN) theory. Our method -- AMLET (Automatic Multi-layer Loader Exploiting TNs) -- proceeds via careful construction of a specific TN topology and can be tailored to arbitrary circuit depths. Second, we perform numerical experiments on real-world classical data from four distinct areas: finance, images, fluid mechanics, and proteins. To the best of our knowledge, this is the broadest numerical analysis to date of loading classical data into a quantum computer. The required circuit depths are often several orders of magnitude lower than the exponentially-scaling general loading algorithm would require. Besides introducing a more efficient loading algorithm, this work demonstrates that many classical datasets are loadable in depths that are much shorter than previously expected, which has positive implications for speeding up classical workloads on quantum computers.
Large language models (LLMs) have shown the potential of revolutionizing natural language processing tasks in diverse domains, sparking great interest in finance. Accessing high-quality financial data is the first challenge for financial LLMs (FinLLMs). While proprietary models like BloombergGPT have taken advantage of their unique data accumulation, such privileged access calls for an open-source alternative to democratize Internet-scale financial data. In this paper, we present an open-source large language model, FinGPT, for the finance sector. Unlike proprietary models, FinGPT takes a data-centric approach, providing researchers and practitioners with accessible and transparent resources to develop their FinLLMs. We highlight the importance of an automatic data curation pipeline and the lightweight low-rank adaptation technique in building FinGPT. Furthermore, we showcase several potential applications as stepping stones for users, such as robo-advising, algorithmic trading, and low-code development. Through collaborative efforts within the open-source AI4Finance community, FinGPT aims to stimulate innovation, democratize FinLLMs, and unlock new opportunities in open finance. Two associated code repos are https://github.com/AI4Finance-Foundation/FinGPT and https://github.com/AI4Finance-Foundation/FinNLP
We study a novel automated market maker design: the function maximizing AMM (FM-AMM). Our central assumption is that trades are batched before execution. Because of competition between arbitrageurs, the FM-AMM eliminates arbitrage profits (or LVR) and sandwich attacks, currently the two main problems in decentralized finance and blockchain design more broadly. We then consider 11 token pairs and use Binance price data to simulate the lower bound to the return of providing liquidity to an FM-AMM. Such a lower bound is, for the most part, slightly higher than the empirical returns of providing liquidity on Uniswap v3 (currently the dominant AMM).
Maryan Rizinski, Hristijan Peshov, Kostadin Mishev
et al.
Lexicon-based sentiment analysis (SA) in finance leverages specialized, manually annotated lexicons created by human experts to extract sentiment from financial texts. Although lexicon-based methods are simple to implement and fast to operate on textual data, they require considerable manual annotation efforts to create, maintain, and update the lexicons. These methods are also considered inferior to the deep learning-based approaches, such as transformer models, which have become dominant in various NLP tasks due to their remarkable performance. However, transformers require extensive data and computational resources for both training and testing. Additionally, they involve significant prediction times, making them unsuitable for real-time production environments or systems with limited processing capabilities. In this paper, we introduce a novel methodology named eXplainable Lexicons (XLex) that combines the advantages of both lexicon-based methods and transformer models. We propose an approach that utilizes transformers and SHapley Additive exPlanations (SHAP) for explainability to learn financial lexicons. Our study presents four main contributions. Firstly, we demonstrate that transformer-aided explainable lexicons can enhance the vocabulary coverage of the benchmark Loughran-McDonald (LM) lexicon, reducing the human involvement in annotating, maintaining, and updating the lexicons. Secondly, we show that the resulting lexicon outperforms the standard LM lexicon in SA of financial datasets. Thirdly, we illustrate that the lexicon-based approach is significantly more efficient in terms of model speed and size compared to transformers. Lastly, the XLex approach is inherently more interpretable than transformer models as lexicon models rely on predefined rules, allowing for better insights into the results of SA and making the XLex approach a viable tool for financial decision-making.
Mohammad Shahab Rezvani, Hannan Amoozad Mahdiraji, Ezatollah Abbasian
et al.
Based on the prospect theory, the current research evaluated the cooperation strategy in the financial services supply chain. This research was descriptive in data collection and quantitative in terms of method. The game theory approach in this research was modeled using the Stackelberg approach. Cooperation strategies in the supply chain included reducing sensitivity, expanding profits, avoiding losses, and relying on references. The 4-player game was used to achieve the best cooperation path. The statistical population of the research was specialists, experts, and managers of companies providing financial services, among which 135 participants were selected as the statistical sample. According to the results, some of the paths of the cooperation model in financing were eliminated, and 24 paths remained out of 81 available options. Then, using the Stackelberg competition, the weights of each route were determined. Finally, with Stackelberg's competition calculations, the best cooperation path was determined, which included the guidance of financing management, the flexibility of financing service providers, the attraction of partners' support policies, and the allocation of financial resources based on the profit expansion prospect. Unlike most empirical studies of supply chain management, which use partners' data at the business unit or strategic partner level, in this research, game theory based on prospect theory was used to evaluate the cooperation strategy. The supply chain of financing services is created to solve financial problems, and different companies, according to the characteristics of their industry, adopt different cooperation strategies based on maximizing their profit in this chain of cooperation.
PURPOSE: By bridging the funding gap between funding surplus units and deficit units, financial institutions like banks play a crucial role in fostering economic development in a nation. Banks provide the crucial task of organizing individual and institutional resources and directing them to those prepared to engage in business ventures or other productive uses. The aim of this paper is to evaluate the relation between funding liquidity and bank lending growth (BLG). An empirical analysis between bank capital and the funding liquidity ratio on bank lending growth (BLG) using the generalized method of moments (GMM) approach for the sustainable business has been not identified before. Therefore, this study tries to fill this gap. METHODOLOGY: The data was collected from 59 commercial banks in India from 2010 to 2022 which comprises of 21 public sector banks, 18 private sector banks, and 20 foreign banks. The GMM approach was what we employed. This strategy is typically utilized in situations in which the distribution of the data is uncertain and there is a concern with over identification. GMM offers a consistent, asymptotically normal, and efficient estimator in comparison to all of the other estimators that merely use the information presented by the moment conditions. FINDINGS: Findings suggests that there is a significantly negative influence of bank capital and funding liquidity on bank lending. This indicates that higher capital can limit the effect of funding liquidity on the growth of the banks’ loans, therefore the findings are consistent with the hypothesis that higher capital can lower the effect of funding liquidity. This study’s model also reveals the significantly favorable impact that funding liquidity has on the expansion of banks’ loan portfolios, which ultimately results in a more sophisticated increase in the growth rate of bank lending. IMPLICATIONS: This can be an importance piece of information for policy makers in taking accurate decisions to induce the BLG in the presence of an interactive association of funding liquidity and the lending growth rate at different capital levels. We found that the banks’ lending growth rate is significantly influenced by its past values with a significant p-value of less than 1%. The findings imply that capital funds and liquidity funds support the BLG rate in India by strengthening and neutralising the risk involved and absorbing the losses generated by stressed assets. ORIGINALITY AND VALUE: This study makes a significant contribution to the creation of a more in-depth understanding of the potential relationship between banks’ funding liquidity, capital funds, and bankers’ lending behavior, in particular with reference to developing market nations like India.
Abstract This study examines whether and how Sharia compliance and national governance affect the value of corporate cash holding (cash) in Organization of Islamic Cooperation (OIC) countries. Study results indicate that cash can enhance firm value and such cash value is higher for Sharia-compliant firms than for Sharia non-compliant firms. In addition, cash is particularly valuable when national governance is strong. Furthermore, the positive effect of Sharia compliance on cash value is more pronounced when national governance is strong. Results suggest that internal governance (i.e., Sharia compliance) and external governance (i.e., national governance) should be in sync to maximize cash value.
History of scholarship and learning. The humanities, Social Sciences
Christopher Boyle, Chris Barrell, Kelly-Ann Allen
et al.
The practice of inclusive education in schools has led to changes in policy and pedagogy, hence teacher acceptance and attitude are important components of its success. The aim of this study is to identify the differences in attitudes of primary and secondary pre-service teachers on inclusion and the potential relationship between demographic variables such as definitions of inclusion, previous experience working in a school, completion of a module on inclusive schools, and other variables. The study included 548 Australian university students studying primary (n = 348) or secondary (n = 193) professional teaching. All participants completed the Teacher Attitudes to Inclusion Scale (TAISA). Principle components analysis was performed to transform the TAISA questionnaire into smaller set of components and two-way between-groups analysis of variance was used to analyse data. Results showed that primary pre-service teachers have more positive attitudes towards inclusion than secondary pre-service teachers. Primary pre-service teachers were also more responsive to training on inclusive education. Implications for practice and future research are discussed.
MohammadAmin Fazli, Mahdi Lashkari, Hamed Taherkhani
et al.
Solving portfolio management problems using deep reinforcement learning has been getting much attention in finance for a few years. We have proposed a new method using experts signals and historical price data to feed into our reinforcement learning framework. Although experts signals have been used in previous works in the field of finance, as far as we know, it is the first time this method, in tandem with deep RL, is used to solve the financial portfolio management problem. Our proposed framework consists of a convolutional network for aggregating signals, another convolutional network for historical price data, and a vanilla network. We used the Proximal Policy Optimization algorithm as the agent to process the reward and take action in the environment. The results suggested that, on average, our framework could gain 90 percent of the profit earned by the best expert.