Forecasting stock prices remains a fundamental yet complex challenge in financial economics due to the nonlinearity, volatility, and exogenous shocks characterizing market behavior. This paper proposes a hybrid deep learning framework that integrates Long Short-Term Memory (LSTM) networks for time-series modeling with Transformer-based architectures for textual sentiment extraction from financial news. The goal is to enhance predictive accuracy by combining structured historical data with unstructured semantic signals. Using three years of daily data from Apple Inc. (AAPL), the model captures endogenous price dynamics via LSTM and incorporates contemporaneous market sentiment through FinBERT, a Transformer model pretrained on financial text. Empirical results show that the hybrid model outperforms price-only baselines across multiple evaluation metrics, including mean squared error (MSE) and directional accuracy. The incorporation of sentiment features proves particularly valuable around earnings announcements and event-driven volatility regimes. This study contributes to the literature on machine learning in finance by demonstrating the complementary strengths of multimodal learning, offering a more interpretable and robust framework for stock price prediction. The findings also open avenues for future research in real-time forecasting, reinforcement learning integration, and the application of hybrid models across diverse asset classes.

Credit markets around the world are undergoing digital transformation which has led to the rise in FinTech and BigTech lending. FinTech and BigTech lending is the provision of credit by FinTech and BigTech providers who have more capital, cutting-edge IT systems, worldwide recognition, greater online presence and are able to handle more big data on computers and mobile phones than traditional banks. FinTech and BigTech lending is growing in importance, but the determinants of FinTech and BigTech lending have received little attention in the literature. This study investigates the determinants of FinTech and BigTech lending. The study focused on the effect of financial inclusion and financial development on FinTech and BigTech lending. Using data for 18 countries from 2013 to 2019 and employing the difference-GMM and 2SLS regression methods, the findings reveal that financial inclusion and financial development are significant determinants of FinTech and BigTech lending. Financial development is a positive determinant of FinTech and BigTech lending while financial inclusion has a significant effect on FinTech and BigTech lending. Also, FinTech and BigTech lending lead to greater banking sector stability and also poses the risk of rising nonperforming loans. There is also a significant positive correlation between financial development and FinTech and BigTech lending. These findings add to the emerging literature on the role of FinTech and BigTech in financial intermediation. This research is significant because it provides insights into the role of financial inclusion and financial development in the digital transformation of credit markets.

Financial literacy seems to be more important and focused than ever. Several recent studies have found that Portugal is at bottom of the table compared to the Eurozone countries regarding financial literacy. As it’s a key factor in the development of a country, it appears to be crucial to understand what people know about financial matters when they complete compulsory schooling. With a sample of 296 Portuguese students who enrolled in the polytechnic higher education system for the first time, we studied if they understand simple concepts related to financial issues (such as loans), as well as whether they are aware of the risk of not recovering the money invested that is embedded in some of the most talked-about and common financial products that are available in the market. This last objective seems to be relevant since a lot of fraudulent schemes involving teenagers, young adults, and financial markets have emerged in recent years. From the results, some disturbing conclusions can be drawn. For instance, more than two-thirds of the sample do not know what Euribor is (similar result regarding Spread). About a third of the simple do not understand inflation’s consequences. 16,9% do not know what term deposits are, and derivative products and saving certificates are seen as very alike regarding the risk they represent. Students who chose a business-related course as their first choice when applying showed a higher level of financial literacy, although it is still low compared to what one would expect.

This paper examines impacts of China’s financial liberalization policy on income inequality, through three channels: financial scale, financial structure and financial efficiency, an empirical analysis based on panel data of 30 provinces in China from 1996 to 2013 is conducted. The results confirm the Kuznets effect between financial scale, financial structure and income inequality. As the size of the financial sector expands, the financial structure is tilted toward direct financing, and the income gap among residents will experience a "reverse U-shaped" trend that rises first and then falls. Most of China has not yet passed the turning point, and is still in the upper bound of the "inverted U-shaped" curve. Financial liberalization policies will continue to exacerbate income inequality. The impact of financial efficiency on income distribution is quite different in different regions of China. After dividing the whole China into three regions according to the degree of economic development, it is found that the financial efficiency of the eastern and western regions has a Kuznets effect on the income gap, but compared with the eastern region, more provinces and cities in the western region have entered the stage of reducing the income inequality, and the financial development has a great impact on the western region. The effects of financial development on central China are weak, and income inequality increases with financial efficiency.

This study investigates the impact of financial inclusion on environmental sustainability in 178 emerging and developing countries from 1996 to 2022. Employing a composite index derived through Principal Component Analysis (PCA) as a measure of financial inclusion and covering four aspects (access, depth, efficiency, stability), our analysis reveals negative outcomes. The findings indicate that enhancing financial inclusion is associated with a notable increase in CO2 per capita emissions as well as in Total Greenhouse Gas emissions. We demonstrate that controlling corruption improves environmental quality, yet this measure alone is insufficient to fully mitigate the impact of financial inclusion, as indicated by our moderation analysis. The same analysis, however, shows that fostering globalization through trade openness is an efficient tool to alleviate the positive effect of financial inclusion on the quality of the environment. The study employs various policies targeting the control of development levels, energy consumption, natural resource utilization, industry, and urban population dynamics to contextualize the influence of financial inclusion on environmental sustainability. Through econometric methods and a comprehensive examination of the specified time frame, our results provide insights into the complex interplay between financial inclusion and environmental outcomes in diverse socio-economic contexts. The research contributes to the discourse on sustainable development by highlighting the potential of certain factors as a catalyst for environmental improvement. Understanding these dynamics is crucial for policymakers, as it underlines the trade-off between integrating inclusive financial strategies and achieving environmentally sustainable development trajectories in emerging and developing nations. Moreover, shedding light on the underlying mechanisms, such as trade-offs, fills a significant gap in the literature.

We present two approaches to forecasting parameters in the SABR model. The first approach is the vector autoregressive moving-average model (VARMA) for the time series of the in-sample calibrated parameters, and the second is based on machine learning techniques called epsilon-support vector regression (ε-SVR). Using daily data of S&P 500 ETF option prices from January 1, 2014, to December 31, 2018, we first calibrate the daily values of the model parameters from the training sample, then conduct out-of-sample forecasting of parameters and pricing of options. Both approaches produce good fits between the forecasted and calibrated parameters for out-of-sample dates. A comparison study shows that using forecasted parameters as inputs, the SABR model generates better pricing results than assuming constant parameters or using lag parameters. We also discuss the market conditions under which one approach outperforms the other.

This paper presents a model of bank runs and evaluates relevant policy tools. The model is founded on the historical pattern of banking panics, involving an economic boom, an adverse shock, prominent bank failures, and runs on both insolvent and solvent banks. The model analyzes various ways in which solvency information affects the likelihood of systemwide bank runs. An interesting result is that partial bank-specific information can be worse than no bank-specific information. The model can also explain runs driven by liquidity concern based on incomplete solvency information. The main policy implication derived from the model and the evaluation of policy tools is that policy actions to contain a financial crisis should incorporate weeding out insolvent institutions and assuring the solvency of remaining institutions.

This paper evaluates the fit-for-purpose of the monetary policy measures implemented by the Bank of Ghana in response to the COVID-19 pandemic. We examine the effectiveness of the BoG’s policy interventions in the context of vector autoregressions augmented with macroeconomic and financial indicators. We demonstrate that the BoG’s monetary policy measures have had nominal, real, and financial effects. The monetary interventions have been successful, as evidenced by the gradual reduction in the sovereign spread, improved financial stability, and increased real economic activity. Our findings suggest that balance sheet actions are less effective and should be moderated in the conduct of monetary policy in jurisdictions without zero lower bound constraints. However, the analysis indicates that in times of crisis, central banks should deploy both standard and non-standard tools to stabilize dysfunctional financial markets and avoid a deflationary spiral. The historical and variance decomposition of the data reveal that monetary policy shocks have historically made the largest contributions to the targeted macro-financial aggregates during the pandemic episodes.

Exiting literature and central banks have recently raised concerns about the ominous overlooked threat of growing global debt, and its fundamental role in financial crises and economic instability. This paper develops and models an alternative economic theory that calls for a paradigm shift from the prevailing debt-based financial economy. Through a structured literature review and conceptual analysis, the paper explores the relationship between the traditional interest-based financial economy and economic injustice and instability. The paper then through an econometric analysis of data collected from 189 countries tests its conceptualised theory advocating a gradual transition from the deb-based financial economy. The results provide three important contributions. Firstly, the results contribute to the field of economics and finance by providing a conceptual and theoretical framework for examining the interaction between the financial economy and economic equity. The paper introduces a conceptualisation of what it coins as the Equitable Optimality Economic Theory, which replaces interest rate with profit rate. Secondly, the paper extends the debate in the literature about debt theories and its impact on the financial economy by arguing that a shift towards debt-balanced and eventually debt-free financial economy provides a more equitable and stable economic system. Thirdly, the econometric modelling demonstrates that such a change would lead to improved economic growth, reduced debt levels, enhanced financial stability, and the inherent nature of profit rates provides a natural buffer against economic downturns. The study concludes by proposing a practical roadmap for this economic transition in gradual and steady approach.

In this study, I analyze the impact of the aggregate, income, corporate and social security tax revenues on both the U.S. output and the stock market return in a structural vector autoregression (SVAR) framework between 1960:Q1 and 2015:Q4. Unlike some of the other studies, I use aggregate and disaggregated tax revenue variables to examine the impact of scal policy. Results show that an increase in aggregate tax revenue reduces output and market return. In addition, an increase in income, corporate, and social security tax revenues reduces output and the market return signi cantly at varying degrees.

Part of the present inflation is caused by the breakdown of globalization, in particular supply chains, part is caused by the Corona Pandemic, in particular lockdowns, part is caused by the Ukrainian War, part is caused by European sanctions, and part – and not the smallest one – is caused by the European Central Bank’s printing money by hook or by crook in the past and in the presence. This paper attributes inflation decisively to the overwhelming money creation by the European Central Bank.

Investors are keenly interested in the risk of informed trading, as it can have an immediate impact on transaction costs imposed by liquidity providers. This paper examines microblogging-based informed trading as a systematic risk for liquidity at both market and firm levels. Assets at firm level were categorized into financial and non-financial perspective. In this context, the study constructed a bank index and non-financial firms (NFF) index within the broader market. In a relative market, the liquidity was priced pessimistically and a higher probability for appearance of spread was noted during pessimism environments. The bank index liquidity was significantly responsive towards systematic bearish and bullish sentiments. In addition, the posterior probability of systematic sentiment risk was considerably higher for bank assets’ liquidity. The NFF index liquidity was not exposed to the systematic bearish and bullish sentiments. Meantime, the posterior probability of systematic sentiment risk was considerably lower for non-financial assets’ liquidity. The relative market’s liquidity was not influenced by changes in past series of bearish and bullish sentiments. Similarly, the sentiments’ lags were not strong enough to impact the firm index liquidity in the short or long run.

The long-term extensive economic development has caused China's resource and environmental problems, especially the resource misallocation. The way China prioritises its limited resources is being significantly impacted by the rise of the digital economy and the interconnectedness of new technologies and the real economy. This paper quantitatively examines the linear and nonlinear impacts and mechanisms of digital development represented by internet development. With a series of empirical tests, we found that the internet development has significantly inhibited the resources misallocation, and the conclusion is still valid in the robustness test with internet popularization and internet infrastructure as the core explanatory variables. In addition to the marketization, internet development can further inhibit resource misallocation by promoting financial development, openness, urbanization and industrial structure. The findings of threshold regression suggest that the inhibitory effect of internet growth on resource misallocation becomes more visible as the degree of financial development and industrial structure increases; with the higher degree of urbanisation and marketization, although the internet development has always played an inhibitory role on resource mismatch, the inhibitory effect first increases and then decreases; with the improvement of openness, the hindering impact of internet growth on resource mismatch becomes more visible as the degree of financial development and industrial structure increases.

In this work we aim to identify potential determinants and seek to predict terrorism attack. Thus, to eliminate uncertainty linked to explanatory variables we used the BMA method. We show that, contrary to expectations terrorism in MENA region is no longer purely of economic origin but mainly due to political problems, education, financial development and countries’ demographic characteristics. Likewise, we find that national, international and global terrorism are not of same origins even they present many common roots. In the end, we show that it is possible to predict majority of attacks based on a small number of indicators measuring political risk, financial development and income inequalities.

With the development of information technology and its application in environmental governance, the role of the internet in improving energy efficiency and reducing energy-saving potential (ESP) has attracted more attention. In this study, the slack-based model (SBM) and the unexpected model, along with the entropy method, were applied to measure China's energy-saving potential and internet development. Further, we empirically analyzed the direct effect, mediating effect, threshold effect, and regional heterogeneity of the internet on ESP. Our conclusion shows that there is a significant spatial correlation between internet penetration and ESP. Internet penetration has become an important tool for reducing ESP, but this effect shows regional heterogeneity. Human capital accumulation, financial development, and industrial upgrading are important influencing mechanisms, but indirect effects are weaker than direct effects. The impact of internet penetration on ESP is non-linear, and for improving human capital accumulation, financial development, and industrial upgrading, the role of internet popularization in energy conservation is more obvious.

Green credit policy (GCP) relies on financial means to promote environmental governance. Whether it can achieve the goals of economic development and environmental protection, especially in the context of different institutional supplies, remains to be scientifically tested. Based on the implementation of China’s Green Credit Guidelines in 2012, this study uses panel data of Chinese companies from 2009 to 2019 to explore the influence of GCP on green technology innovation and the role of institutional supply in it. The results show that GCP is instrumental in promoting green innovation in heavily polluting enterprises, and the promotion effect is heterogeneous based on green patent types, firms’ ownership, and regional financial development levels. Further analysis finds that the supply of environmental protection systems by local governments can strengthen the green innovation effect of GCP. However, the institutional supply of innovation has not yet released a promotional effect. This paper finds that green credit can be used as an environmental governance tool and provides inspiration for local governments to issue environmental protection policies scientifically.

This paper examines the information content of selected US industries focusing on the dynamic linkages among these industries, the stock market and a number of fundamental variables. The period of investigation spans from January 1960 to December 2021. The empirical strategy includes several methodologies such as regressions, vector autoregressions and volatility models. The idea is to investigate the dynamic linkages among these series at both the mean and the volatility levels. The results point to significant industry returns’ explanatory power for many predictors of economic activity including the stock market. Further, time-varying analysis of the linkages among the industries and the stock market’s returns reveal that certain industries such as Oil and Financials provide consistent information leadership over other industries and across decades. Further, upon assessing the industry–market return volatility spillovers, it was found that a market risk–return profile may not always be economically significant and timely for investors. Finally, crises, financial or otherwise, affect industries but to differing degrees.

Credit scoring remains one of the most important subjects in financial risk management. Although the methods in this field have grown in sophistication, further improvements are necessary. These advances could translate in major gains for financial institutions and other companies that extend credit by diminishing the potential for losses in this process. This research seeks to compare statistical and artificial intelligence (AI) predictors in a credit risk analysis setting, namely the discriminant analysis, the logistic regression (LR), the artificial neural networks (ANNs), and the random forests. In order to perform this comparison, these methods are used to predict the default risk for a sample of companies that engage in trade credit. Pre-processing procedures are established, namely in the form of a proper sampling technique to assure the balance of the sample. Additionally, multicollinearity in the dataset is assessed via an analysis of the variance inflation factors (VIFs), and the presence of multivariate outliers is investigated with an algorithm based on robust Mahalanobis distances (MDs). After seeking the most beneficial architectures and/or settings for each predictor category, the final models are then compared in terms of several relevant key performance indicators (KPIs). The benchmarking analysis revealed that the artificial intelligence methods outperformed the statistical approaches.

We explore the connectedness and portfolio implications between Islamic and conventional bonds in global and GCC regions. We also compare which bonds performed better during our sample period. Unlike previous studies, we focus on Islamic bond markets compared to their conventional counterparts and highlight the GCC bonds (Islamic and conventional) in respect of global bonds. We apply the DCC-GJR-GARCH (1,1) method, the Sharpe ratio, and the portfolio implications strategy over the period from September 1, 2013, to February 23, 2022. Our time-varying results suggest that the relationship among all variables varies over time, but most of them are positive, suggesting that there are fewer diversification opportunities between Islamic and conventional bonds. Hedging and diversification benefits are found only in the limited period among these variables, especially between GCC bonds and global bonds, and global Sukuk and GCC Sukuk. The findings of risk-adjusted returns reveal that Islamic bonds outperform their conventional counterparts. Moreover, mixed results are found in the case of hedging costs, and the majority of the fund, based on optimal weights, should be invested in Islamic bonds. Our study endows investors and regulators in the global and GCC markets with new insights on how to shield their investments and the financial system from financial crises through a hedging strategy with Islamic finance.

Regulation of financial institutions has two key purposes: Solvency (prudential regulation) and consumer protection. Prudential regulation is implemented mainly by capital requirements, but governments also provide insurance for customer deposits, as a backup tool. In this article, we discuss the critical conditions for deposit insurance and capitalization to act as substitutes for each other, under cyclical economic environment. We make two assumptions. The first one is that deposit insurance is fairly priced and there is no moral hazard. The second one is that insurance creates incentives for moral hazard among insured banks, resulting in increased risk taking. We also discuss the critical conditions for deposit insurance and capitalization to be complementary under different proportions of deposit insurance.