Applications of Optimal Transport to Economics and Related Topics

The US has alarmingly high, and rising, gun violence and fatality rates. While it is generally believed that supply side policy is critical in addressing the problem, legislation has been relatively ineffective, for example the Gun Violence Prevention and Community Safety Act of 2020. Previous literature has identified hotspots and proximate determinants, particularly urban locations. Effective supply side policy would require application of optimal transport methods. We apply novel and current generation structural models to identify the spatial network for supply of guns and propagation of violence risks. This provides clean quantification of spatial supply chains and associated costs of transport between nodes, which are necessary for mitigation using optimal transport and logistics network management methods.

ET Jaynes work on probability theory, which he subtitled the logic of science, should be much better known. We cast some light on a small segment of his work, demonstrating how logical probability can be used to analyze people judge scientific and economic pronouncements and claims of cause. This has important consequences in economics, and any area in which people are asked to believe a cause has been discovered or verified in science, especially when they are asked to act on the discovery.

The a priori procedure (APP) provides minimum sample sizes for estimating parameters of the population distribution that ensure precision and confidence in sample statistics. In this paper, we extend the APP to include the family of elliptical distributions, which is a member of a broad family of probability distributions and is an extension of the family of normal distributions. Properties of the elliptical distribution are discussed. Under the uncorrelated assumption and with a given precision and a confidence level, the desired sample size for estimating the location parameter is obtained for generalized elliptically symmetric logistic, symmetric Kotz Type, and t distributions, respectively. The confidence interval for the location parameter is constructed based on the desired sample size using elliptical distribution. Three real data examples are given to illustrate our main results. In addition, the Shinyapp program links for some of the elliptical distributions are provided for researchers and practitioners to use. In the program, the desired sample size is calculated.

As the COVID-19 pandemic has evolved, it has become increasingly evident that the actual number of cases has likely been underestimated. In this study, we review an econometric method to estimate the true scale of COVID-19 cases for 40 countries spanning from January 1, 2020, to November 3, 2020. The method centers around the ‘structural’ model, which is an expansion of the SIR epidemiological model, and is designed to incorporate the notion of underreporting. The findings of our analysis reveal substantial underreporting, aligning with prior research and expert opinions within the field of public health.

Artificial intelligence (AI) has significantly impacted many different industries, including finance and economics. These technologies are increasingly being used to improve economic forecasting and analysis, providing more accurate predictions and better decision-making. The article delves into the expanding use of artificial intelligence (AI) in economic forecasting and analysis, including subjects such as big data, predictive analytics, and econometrics. It will also examine the problems of using AI in econometrics research, as well as the future of these technologies. Traditional forecasting approaches rely on econometric models for economic forecasting and analysis. These models evaluate correlations between economic indicators such as GDP, inflation, and unemployment using statistical approaches and mathematical equations. However, these classic models have limitations in that they may not be able to explain more complex interactions between economic variables. Furthermore, they require a lot of data as well as certain assumptions about the structure of the model, which can affect their ability to adapt to changing economic conditions. The use of AI and Machine Learning (ML) in economics can help overcome these problems and improve the accuracy of predictions about future trends.

Quantiles are a fundamental concept in probability and theoretical statistics and a daily tool in their applications. While the univariate concept of quantiles is quite clear and well understood, its multivariate extension is more problematic. After half a century of continued efforts and many proposals, two concepts, essentially, are emerging: the so-called (relabeled) geometric quantiles, extending the characterization of univariate quantiles as minimizers of an L $$_1$$ 1 loss function involving the check functions, and the more recent center-outward quantiles based on measure transportation ideas. These two concepts yield distinct families of quantile regions and quantile contours. Our objective here is to present a comparison of their main theoretical properties and a numerical investigation of their differences.

We survey the state of the art of AI applications to financial expectations and the role quantum logic can play in further advancements of AI technologies. We discuss financial applications of such machine learning techniques as reinforcement learning and deep neural networks to the analysis of financial statements, algorithmic trading, portfolio management, and robo-advising. Next, we elaborate on the emergence and advancement of QML (quantum machine learning) and advocate for the wider exploration of the advantages of quantum inspired neural networks, steaming from the use of quantum logic that is able to capture agents’ non- classical expectations and non expected utility decisions, also coined “bounded rationality”. We would like to motivate to use human—like AI techniques that are centered on quantum, rather than classical logic to (i) represent the human brain type information processing; (ii) speed up the work of the AI algorithms; (iii) better operate in complex and uncertain environments.

Using the provincial panel data in China from 2014 to 2021, this paper examines the effects and paths of digital economy and labor mobility on industrial structure optimization, based on the construction of industrial structure upgrading index and digital economy comprehensive development level index. The mediation effect model and the panel threshold model are used in the analysis process. The empirical results show that: ① Digital economy can promote the optimization and upgrading of industrial structure by facilitating the mobility of labor. ② Adopting the threshold model, this paper finds that the effect of digital economy on the optimization of industrial structure presents non-linear characteristics. ③ Both digital economy and industrial structure are characterized by heterogeneity in terms of regional distribution. Therefore, we can conclude that in order to realize the goal of high-quality development, it is necessary to actively promote the balanced development of the digital economy. We are supposed to further improve the relevant labor market policies to promote the coordinated development of the industrial structure and the digital economy.

This research evaluates model selection within a class of integer-valued time series models that feature overdispersion and extends these models to their generalized forms. The newly introduced models include: (1) dispersed integer-valued GARCH models incorporating negative binomial, double Poisson, or generalized Poisson distributions, and (2) a Double Log-form integer-valued GARCH model. The latter model avoids over-restrictions in the parameter space. We estimate parameters and select models within the Bayesian framework using adaptive Markov chain Monte Carlo (MCMC) sampling schemes, and employ the deviance information criterion (DIC) for model selection. We also design simulation studies to examine estimation accuracy and potential model misspecification. Using monthly crime counts in Bankstown, New South Wales, Australia, for an empirical illustration, our findings highlight the ability to select the most promising models among the competing ones based on DIC.

We conducted an investigation into four econometric models designed to handle mixed-frequency data. Our primary objective is to leverage a vast array of monthly macroeconomic variables to enhance the accuracy of forecasting quarterly Gross Domestic Product (GDP). To achieve this, we compared the following models: (1) The Autoregressive (AR) model, (2) The Mixed Data Sampling (MIDAS) model, which enables the combination of data at different frequencies, (3) The Lasso-MIDAS model, as proposed by [27], aimed at addressing issues related to inconsistent data frequencies and the curse of dimensionality arising from high-dimensional data, (4) the Sparse-group LASSO model, introduced by [3], which accommodates for the mixing processes and recognizes that the financial and the macroeconomic data may have heavier than exponential tails. An empirical analysis of forecasting GDP growth reveals that the sparse-group LASSO model consistently outperforms other models when forecasting four steps ahead, both before and after COVID-19 episodes. For short-term forecasting, both the MIDAS and sparse-group LASSO models exhibit favorable performance compared to alternative approaches. When comparing our findings before and after the COVID-19 episodes, it becomes evident that the MIDAS model significantly outperforms other models when incorporating COVID-19 data. Utilizing high-frequency data without any form of regularization appears to play a substantial role in improving forecasting performance, particularly during abrupt economic downturns. In essence, these two models can serve as an alternative “benchmark” for forecasting when sudden economic fluctuations occur, rendering conventional models like the AR model quickly outdated.

As part of a prelude to the applications of optimal transport theory to econometrics and machine learning, this tutorial paper focus on the notion of disintegration in measure theory in the analysis of Wassersrein metrics which are useful, in particular, for machine learning and financial risks. An elementary exposition on using disintegration to prove that Waserstein divergence is a bona fide metric is provided.

On the one hand, in economics, there is a well-known and well-studied economy of scale: when two smaller companies merge, it lowers their costs and thus, makes them more effective and therefore more competitive. At first glance, this advantage of big size would make economy dominated by big companies—but in reality, small business remain a significant and important economic sector. Similarly, it is well known and well studied that research collaboration enhances researchers’ productivity—but still a significant portion of important results come from individual efforts. In several applications areas, there are area-specific explanations for this seemingly contradictory phenomenon. In this paper, we provide a general explanation based on first principles. Our reasoning also leads to a new explanation of the ubiquity of Zipf’s Law—a law that describes, e.g., the distribution of companies by size.

Most funding for science comes from taxpayers. So, it is very important to be able to convince taxpayers that this funding is potentially beneficial for them. This task is easier in Earth sciences, e.g., in meteorology, where there are clear local benefits. The problem is that while many people support local studies focused on their region, they do not always have a good understanding of the fact that effective local benefits require also studying surrounding areas—and what should be the optimal balance between local and (more) global studies. In this paper, on a (somewhat) simplified model of the situation, we explain what is the appropriate balance. We hope that the corresponding methodology can (and will) be applied to more realistic—and thus, more complex—local-global models as well.

According to decision theory, in general, to recommend the best of possible actions, we need to know, for each possible action, the probabilities of different outcomes, and we also need to know the decision maker’s utility function—that describes his/her preferences. For some pairs of probability distributions, however, we can make such a recommendation without knowing the exact form of the utility function—e.g., in financial applications, we only need to know that a larger amount is preferable to a smaller one. Such situations, when we can make decisions based only on the information about probabilities, are known as stochastic dominance. The usual analysis of such situations is based in the idealized assumption that any difference in utility, no matter how small, is important. In reality, very small changes in utility value are irrelevant. From this viewpoint, if the utility corresponding to the distribution $$F_2(x)$$ F 2 ( x ) is always either larger or only slightly smaller than the utility corresponding to $$F_1(x)$$ F 1 ( x ) , then we can still conclude that the second action is better (or of the same quality) than the first action. In this paper, we show how to describe such approximate stochastic dominance in precise terms.

Using data from 18 border stations between 2018 and 2022, this paper analyzes the formal border exports between Myanmar and its neighbouring countries—Bangladesh, China, Laos, India, and Thailand. Firstly, it presents an overview of the export pattern that crosses international borders. Secondly, it applies a Bayesian gravity model to investigate the determinants of Myanmar’s border exports. The posterior mean estimates give a clear prediction that the border exports are positively related to the market size of the destination and adversely related to the distance, which is in line with standard gravity literature. It was further found that (i) border infrastructure plays a significant role in driving border exports as border stations having relatively better infrastructure are predicted to have higher levels of exports than those without, (ii) documentation cost is predicted to be a significant negative predictor of border exports, and (iii) border exports to destinations that have free trade agreements with Myanmar are predicted to be higher than destinations without such agreements.

Our research investigated the relationships among carbon emissions, crude oil prices, total factor productivity (TFP), research and development (R&D), and international trade balance in the US. Using the autoregressive distributed lag (ARDL) model, we analyzed annual data from 1970 to 2021. Our findings revealed a two-way relationship between carbon emissions and TFP, and identified oil prices as causes of carbon emissions, while carbon emissions influenced trade balance. In the long term, carbon emissions had minimal effects on TFP and R&D but significantly impacted trade balances. TFP negatively affected carbon emissions. Moreover, increasing TFP and investment in R&D are crucial for mitigating emissions. In the short term, the impact of these variables on carbon emissions was lower. Changes in TFP and R&D influenced by carbon emissions had persistent negative effects, while oil prices and trade balance had modest, long-term positive impacts on emission volatility. These findings emphasize that insufficient growth in TFP hampers efforts to reduce environmental degradation and highlight the importance of enhancing total factor productivity and investing in research and development to mitigate carbon emissions in the long run.

The governments of the Organization for Economic Cooperation and Development (OECD) countries have issued several strict policies to improve environmental quality. Thereby, analysis of factors that affect environmental matters in OECD members might provide helpful lessons for emerging countries. The study aims to investigate the role of tax and renewable energy consumption on environmental issues prevention in OECD countries from 1994 to 2018. By applying Monte Carlo simulations, the findings reveal that renewable energy consumption is a good policy, while tax regulation only has a medium negative impact on environmental quality. The study also finds that regulatory quality does not support environmental quality improvement in these countries. Based on findings, the study suggests some helpful implications for administrators in planning ecological protection policies and encouraging renewable energy consumption.

This paper aims to examine the capacity of the US Monetary Policy Uncertainty (MPU) Index in accurately forecasting the volatility of foreign exchange rates for the Dollar Index, Euro/US$, and Yen/US$. To achieve this, we introduce several hybrid Artificial Neural Networks (ANN)−GARCH models, namely GARCH, ANN−EGARCH, and ANN−GJR−GARCH, which incorporate MPU as the exogenous variable (X). In addition to that, a significant challenge in ANN modeling is choosing the appropriate activation function. Therefore, we consider and compare various forms of activation functions, including logistic, Gompertz, Tanh, ReLU, and leakyReLU. Our results demonstrate that incorporating MPU improves the forecasting performance of the benchmark ANN−GARCH−type models both in- and out-of-sample. In particular, we find that incorporating MPU into the ANN−EGARCH model yields the largest forecasting gains compared to all other variants of the ANN−GARCH−type models. Additionally, our findings reveal that ReLU is the best activation function for predicting Dollar and Yen volatility, while Gompertz performs the best for predicting Euro volatility.

In this research, we analyze the factors that contribute to happiness and unhappiness in Thailand. We use linear and diminishing relationships with Gross Province Product per capita to determine these factors. To select model variables, we use Lasso regression, and Ordinary Least Square tests the Easterlin Paradox and hedonic treadmill. We base our study on data collected from 77 provinces in Thailand in the year 2020. Our findings confirm the Easterlin Paradox and indicate that happiness and unhappiness are influenced by an inherent force. Furthermore, our results reveal that the number of criminal suspects has a significant impact on happiness and reduces the risk of unhappiness.

This study analyses the effect of financial development on economic growth in 64 developing countries during the period 2003–2017 using a Bayesian model averaging approach. The results indicate that financial development has a significant U-shaped effect on economic growth, providing new insight concerning the relationship between financial development and economic growth. We also demonstrate that investment to gross domestic product ratio and foreign direct investment have significant positive effects on economic growth, whereas population growth has a significant negative impact on economic growth.

Highly right-skewed data can often be modeled by using the three-parameter lognormal distribution. Meanwhile, the performances of extant confidence interval estimates are poor when the variance is large. Herein, methods to estimate the confidence interval for the coefficient of variation of the three-parameter lognormal distribution using the likelihood-based, generalized confidence interval, and method of variance estimates recovery methods are presented. The results of a numerical simulation study reveal that the likelihood-based confidence interval estimate performed well in terms of the actual coverage percentage and average length, even with a large coefficient of variation. The methods’ applicability is demonstrated through their application to wind speed data from Chiang Mai, Thailand, aiming to indicate soil erosion effects.

The study uses the Bayesian model averaging (BMA) approach to identify the determinants of carbon dioxide emissions in selected ASEAN countries for the period 1990–2020. The environmental Kuznets curve (EKC) hypothesis is re-examined during the analysis. Applying both non-informative and informative priors, the results show that energy factors are the main causes affecting CO $$_2$$ 2 emission levels. Based on the obtained models, some recommendations are proposed for each group of countries to control the generation of CO $$_2$$ 2 outputs.

The paper seeks to evaluate the decision criteria in the returning intention to rural tourism destinations of tourists in Vietnam. This research sample comprises tourists. This chapter used the quantitative technique of PLS-SEM. The PLS Algorithm shows that the empirical model has a measurement of determination of 0.876, with 87.6% variation of intention, perceived value, attitude, travel motivation, subjective norm, and perceived behavior control. The factor that has the strongest influence on the intention to return to a rural tourist destination (INT) is the perceived value (PV) of tourists (0.367), followed by the second strongest factor on the returning intention to rural tourism destinations is the subjective norm factor (SN) of tourists (0.340). Finally, managers need suggestions to raise the returning intention to rural tourism destinations of tourists: evidence from Vietnam.

This article deals with determination weights for models with many criteria. The application part is on the evaluation of the quality of life in the regional cities of the Czech Republic. The criteria are divided into main criteria and sub-criteria. There are 7 main criteria and 33 sub-criteria in this article. Each main criterion has several sub-criteria. The criterion weights are determined using the DEMATEL—ANP method. The advantage of this method is that it can display complex relationships between criteria, which is certainly a desired benefit.

This study investigates the impact of abrupt changes in GDP growth and global commodity prices in six Southeast Asian countries: Indonesia, Malaysia, The Philippines, Singapore, Thailand, and Vietnam. Utilizing the Markov-switching model, we analyze the relationship between these variables and inflation, recognizing that each country has unique characteristics. The monthly data of each country is collected from January 2010 to May 2023, comprising 161 observations. Our findings reveal that global oil price fluctuations significantly influence inflation during higher inflation periods in most countries, while the impact diminishes during lower inflation periods, particularly in Singapore, Indonesia, and Vietnam. The effect of global wheat prices on inflation varies across countries, with a stronger impact observed in the higher inflation regime of the Philippines and the lower inflation regime of Indonesia. Global sugar prices play a substantial role in driving inflation dynamics in both higher and lower inflation periods in most countries, with exceptions in Thailand and the Philippines. Furthermore, GDP growth exhibits a significant positive relationship with inflation in both higher and lower regimes for most countries, with varying magnitudes of influence. Notably, negative GDP growth is associated with stagflation in the higher inflation regime. These insights have vital implications for policymakers, enabling tailored strategies to address specific challenges in each country. During high volatility periods, measures can mitigate inflationary effects from oil price shocks, while lower inflation periods require managing potential deflationary pressures from negative GDP shocks.

This research paper utilized a conventional stochastic frontier approach, employing maximum likelihood estimation, to investigate empirical production data pertaining to agricultural products, namely tobacco, rice, and chilli. The application of this rigorous methodology focused on analyzing agricultural production data gathered from Wiengkuk Subdistrict in Muang Nong Khai, Thailand. The outcomes of this study yielded significant findings, unveiling a striking reality: a mere average of $$60\%$$ 60 % of the agricultural products under scrutiny were effectively produced. These findings serve as a testament to the pivotal role played by government policies, specifically agricultural promotion, in shaping the overall quantity of agricultural output.

This study investigates the individual characteristics associated with fertility constraints. Specifically, this study uses data from the China Labor Force Dynamic Survey (CLDS2018), which includes information on individuals’ number of children and their ideal number of children. This allows us to assess whether individuals’ fertility choices align with their actual number of children or if they are constrained by factors such as health, economic circumstances, and government policies. Employing Probit regression analysis, the research identifies factors contributing to the ideal-behavior gap, representing the overall constraint on fertility. The findings reveal that individuals with gender preferences, higher education levels, residing in developed regions, and employed in government are more likely to experience a substantial ideal-behavior gap, implying constraints on their fertility behaviors due to factors such as health, economics, or policies. In addition, the study identifies individual characteristics specifically associated with facing restrictions imposed by the two-child policy. Focusing on the policy constraint, the findings reveal that older females and individuals with agricultural hukou, particularly those who prefer daughters, are less likely to be constrained by the two-child policy.

This paper employs a fixed-effects Bayesian panel kink regression framework to examine the dynamics of the impact of economic freedom on economic growth in five selected Sub-Saharan African countries. Our novel findings have empirically established that economic freedom has a nonlinear impact on economic growth with a kink point value of approximately 59%. The results show that economic freedom positively impacts economic growth in the lower region, but negatively in the higher region. Specifically, with a 95% posterior probability, a 1% point rise in the total economic freedom score will lead to about 0.14% point increase in economic growth in the lower region, whilst it will be about 0.31% point decline in growth in the higher regime with a 95% posterior probability, ceteris paribus. This finding starkly highlights the fact that, in addition to the nonlinearity of the impact of economic freedom on growth, the impact in the high region is more than twice larger than it is in the lower region. This finding is very relevant for policy choices and implementations that focus on economic freedom and economic growth.

Due to the heterogeneous socio-economic backgrounds and multifaceted causes contributing to the phenomenon of NEETs (youths not in education, employment, or training), this study classifies youths into six groups by their status including in-school, employed, NEET due to job seeking, NEET due to family responsibility, NEET due to disability, and other NEETs. Subsequently, we analyze a comprehensive list of socio-economic factors associated with different groups of youths in Thailand. The empirical analysis employs the Generalized Maximum Entropy (GME) model for the multinomial choice to analyze Thailand’s socio-economic survey data. Consistent with prior research, the findings reveal that youths living in poverty or lower consumption expenditure households are more inclined to leave formal education to work or become NEETs, except in the case of NEETs due to disability. This highlights the necessity to extend support beyond education and employment opportunities to address family responsibilities, particularly for youths in households with high dependency ratios or infants. Moreover, the study underscores the diversity of NEET situations among youths from other different socio-economic backgrounds. Notably, there is evidence linking NEET status due to job-seeking with youths from higher socio-economic backgrounds, suggesting potential labor market challenges. Additionally, youths with disabilities encounter barriers not only due to their condition but also in job-seeking. While common policy measures exist, tailored interventions are crucial to facilitate their reintegration into formal education or the labor market.

This study employs a copula-based stochastic frontier modeling (copula-SFM) framework to empirically assess resource-rich countries’ efficiency in utilizing resource rent within Sub-Saharan Africa. The primary objective is to provide robust scientific evidence to aid these nations in maximizing their mineral resource utilization. Model selection criteria, specifically the Bayesian Information Criterion (BIC) and Akaike Information Criterion (AIC), identify the Normal copula-SFM as the superior choice. The findings emphasize the pivotal role of government effectiveness and population growth as strong, positive determinants of per capita income in the selected countries. In terms of average technical efficiency (TE) scores, Equatorial Guinea leads the rankings with an impressive score of 0.9907, while Tanzania trails with the lowest average TE score of 0.8177. These results underscore the potential for enhancing resource-rich countries’ economic performance through effective governance and managing population growth.

The purpose of this paper is to evaluate the efficiency of agricultural production in China, analyze China's production function, and identify the primary factor affecting efficiency. Methodologically, we employ the stochastic frontier model, accounting for the interrelation between the two-sided error term (U) and the one-sided inefficiency factor (V). To address this complex relationship, we introduce a recent approach known as the Copula-based stochastic frontier model. After obtaining technical efficiency (TE) values, we classify the 31 provinces in China into three distinct groups using the K-means clustering method, each exhibiting unique characteristics. Subsequently, we conduct a LASSO regression analysis to examine the key factors influencing TE values. Our findings reveal that the most significant factor impacting TE values is the average household size, which refer to the average number of laborers per rural household in each province. Furthermore, we observe a negative correlation between the level of education among the labor force and TE values. We analyze that this negative correlation primarily results from the agricultural sector's limited appeal to individuals with higher levels of education.

The aims of this research are to analyze the four sectors of influences on China's fertility transition in terms of social development, economy, education, and policies by random forest algorithm, and combine them with the classical theory of demographic transition to compare the differences among the three stages of China's demographic transition periods, 1949–1977, 1978–2001, and 2002–2022. This paper collects annual data from different databases on 18 influential features including fertility. The data were preprocessed by data cleaning, data filling, and other methods to improve the accuracy of the model. According to the results of Gini important features ranking, the main reasons affecting the fertility transition in China have gone through three stages of evolution, from “satisfying basic survival needs” to “pursuing self-development and wealth accumulation in order to improve the standard of living” to “Self-value realization and improvement of the quality of life”. Based on these findings, several insights are provided in terms of government policy to current policies on fertility and social welfare systems.

The purpose of this paper is to introduce an approach to prediction quantile on Capital Asset Pricing Model (CAPM) using histogram-valued data. This study applies this purpose to predict the 5-min returns of two prominent stocks, namely Apple (AAPL) and Microsoft (MSFT), within the S&P500 market covering from January 1, 2019, to June 30, 2023. Moreover, we obtain data for the S&P500 index and US government bonds, representing the market return and risk-free rates, respectively. In this study we found that all quantiles of AAPL stock returns exhibit beta values greater than one, indicating that investing in AAPL will have a higher return than market return, while all quantiles of MSFT stock returns exhibit beta values less than one, indicating that investing in MSFT will have a less return than market return. Additionally, the results of the R-squared value of AAPL confirm the dynamic relationship between the asset and the market return at various levels of quantiles. On the other hand, the R-squared value for MSFT exhibits peaks in both the lower and upper quantile ranges of the U-shape curve which provides insights into the dynamics of MSFT stock returns in relation to the market returns at various quantile levels.

Foreign direct investments (FDIs) play a vital role in promoting an open and effective international economic system and are essential for economic development. However, the benefits of FDI are not equally distributed across countries, sectors, and locations. Theoretical approaches highlight the significance of complex integration strategies of FDI inflows and the interdependence between locations. Yet, little attention has been paid to incorporating the potential cross-country dependencies into the empirical analysis of the determinants of foreign direct investment. Therefore, this paper aims to ex-amine the relationship between foreign direct investment and economic development, utilizing a spatial panel data technique. The empirical analysis uses panel data for 166 countries from 2001 to 2017. Our findings suggest a weak spatial dependence on foreign direct investment and economic development at the international level.

This study explores exchange rate forecasting using a hybrid model with equal weight, alongside traditional models like ARIMA(p, d, q), ETS(A, N, N), TBATS, and the NNAR(p, k) model. We evaluate and compare their performance using RMSE, MAE, and MAPE measures on data spanning from January 2018 to July 2023. Our findings highlight the hybrid model with equal weight as an effective choice for USD/JPY and USD/CAD exchange rate prediction, outperforming other models in terms of lower RMSE, MAE, and MAPE values. In contrast, the ARIMA(p, d, q) model excels in forecasting EUR/USD and USD/CHF, aligning closely with true values. The hybrid model, while not always the best, consistently offers competitive performance, providing a versatile tool for Forex rate prediction. Future research can extend this hybrid model to forecast other financial instruments, including stock indices, digital assets, or commodity markets, offering valuable insights for investors and policymakers.

This study aims to investigate the mechanisms governing international oil price fluctuations and their dynamic repercussions on China's macroeconomy. To achieve this, we employ the BEKK-GARCH model to examine whether fluctuations in international oil prices exert an influence on China's oil prices. Furthermore, we utilize the nonlinear Markov Regime Vector Autoregression (MS-VAR) model to analyze the evolving effects of international oil price fluctuations on China's macroeconomy under varying regimes. Our findings reveal a significant two-way volatility spillover effect between international and domestic crude oil markets. Moreover, the impact of international crude oil price movements on China's macroeconomy is tempered by China's unique economic conditions. It's noteworthy that the Chinese economy tends to exhibit stability after achieving equilibrium rather than undergoing rapid shifts.

In a complex and changeable stock market, algorithmic stock trading has firmly established itself as a fundamental aspect of the present-day financial market, where most transactions are now fully automated. Additionally, Deep Reinforcement Learning (DRL) agents, renowned for their exceptional performance in intricate games such as chess and Go, are increasingly impacting the stock market. In this paper, we examine the potential of deep reinforcement learning to optimize the portfolio returns of 15 Asian stocks. We model stock trading as a Markov decision process problem because of its stochastic and interactive nature. Furthermore, we train a deep reinforcement learning agent using three actor-critic-based algorithms: proximal policy optimization (PPO), advantage actor-critic (A2C), and deep deterministic policy gradient (DDPG). We tested the algorithm on Asian stocks to see how well it performed pre-COVID, during COVID, and post-COVID. The trading agent’s performance using various reinforcement learning algorithms is assessed and compared to the traditional min-variance portfolio allocation strategy. The proposed three individual algorithms are above the minimum variance in risk-adjusted return as evaluated by the Sharpe ratio.

This study aims to assess the influence of soft skill learning programs on worker efficiency in Thailand. We examine several soft skills essential for enhancing workplace capabilities, including Planning and Ways of Working, Communication, Critical Thinking, and Mental Flexibility. Employing a Structural Equation Model and utilizing data from 220 training workers, we investigate the relationship between these soft skills and job efficiency. Our findings provide evidence that for every one-point increase in soft skills performance score, there is a corresponding 0.24% increase in job efficiency. Notably, Mental Flexibility has a more pronounced impact on worker learning performance, leading to higher working efficiency, while Critical Thinking exhibits weaker support for improved learning performance. Further-more, our study underscores the variations in the impact of learning skills across different worker generations, such as Generation X, Millennials, and Generation Z, highlighting their unique contributions to learning performance.

This study aims to verify the effectiveness of carbon emissions reduction through investments in Green finance, focusing on the S&P Global Clean Energy Index as a representative of the global Green finance sector. Specifically, the research identifies constituent stocks within this index that hold the potential to serve as prototypes for carbon emissions reduction initiatives. Utilizing monthly data for 99 stocks, the S&P Global Clean Energy Index, and industrial carbon emissions, this study employs the BART machine model, a novel approach combining Bayesian additive regression trees (BART) and machine learning. The findings of the study reveal a significant relationship between the log prices of AVANGRID Inc.’s stocks and carbon emissions. Notably, as the log prices of these stocks increase, carbon emissions demonstrate a corresponding increase. This effect is particularly pronounced when their price ranges from 44.70 to 46.99 US dollars. This suggests a substantial impact of AVANGRID Inc.’s stock prices on the rise in carbon emissions. Furthermore, the company's significant investments in cutting-edge technology to boost grid capacity in New York for renewable energy adoption in 2023 may result in short-term cost increases, potentially impacting profits, and investor outlook. However, these initiatives are expected to yield long-term environmental benefits and sustainable returns, positively influencing both the company's stock price and shareholder value in the future.

This paper uses a dynamic linear model (DLM) to find the relationship between greenhouse gas emissions and its determinants in Thailand. From the Bayesian model averaging (BMA) analysis was found that only forest, GDP, and industrial are sufficient for further investigation and can explain best the GHG emission. To explain the correlation, the time-varying coefficients of forest and GDP strongly explain and change in the same direction with GHG emission. In contrast, intercept term and industrial variables significantly explain and change in the opposite direction with GHG emission. There are some significant events that affect time-varying coefficients such as climate policy and the economic crisis in 2009. Moreover, The DLM used to be a forecasting tool for the next 10 years. The time-varying coefficients from intercept, GDP, and industrial can have a potential effect on GHG emissions. Forest will potentially explain GHG emissions in a better direction. On the contrary, the coefficients from the intercept term are in opposite directions.

This paper uses Bayesian estimation of the Seemingly Unrelated Time Series Equations (BSUTSE) model to present the relationships of explanatory variables on economic growth. From the Bayesian model average (BMA) analysis, the total considered independent variables is eleven. It was found that there are three variables that can explain the best model of yield curves and real GDP that consists of gold price, and stock from industrial, resource, financials, property and construction, and technology. The BSUTSE presents time-varying coefficients estimation on each economic growth variable. For the yield curve, most variables can explain economic growth more than ever. For real GDP, the return from property construction, industry, and resources significantly explains economic growth and changes in the opposite direction with real GDP. Gold price and the financial industry can explain changes in the same direction with real GDP. Only coefficients from technology parameters have more explain real GDP in the same direction. The BSUTSE is the model that allows coefficients to vary in time in an equation system. The advantage of The BSUTSE model, it can estimate time-varying coefficients.

In this study of 411 university students in the Chiang Mai region, the focus was on assessing their awareness and understanding of computer related offenses under the Computer Crime Act of 2017. Utilizing the Quantile regression model, the research identified influential factors. Age was found to positively correlate with increased awareness and comprehension of computer related offenses, attributed to life experiences and extended exposure to digital technologies. Additionally, higher GPAs were associated with greater awareness, suggesting academic institutions’ role in shaping digital ethics understanding. In addition, the greater the experience seen in the EXPERIAN variable, the greater the level of awareness and understanding of computer crimes. This study offers valuable insights into the nuanced dynamics of digital ethics awareness and understanding, with age, academic performance, and internet experience as pivotal factors.

Tail dependence is the tool to measure dependence in the extremes of a bivariate distribution. Copula is the function used to describe the dependence between the variables. Therefore, copula is used in order to determine the tail dependence. In this work, we focus on dealing with the case of an extreme weight of mixture copula. We provide the transformed Bayesian model averaging to estimate the tail dependence comparing with the conventional ways to estimate the mixture copula by simulation study.

In this investigation spanning the period from 2019 to 2023, we delve into the dynamic relationship between the energy and agriculture markets, placing a specific emphasis on the disruptive energy price crisis emanating from the Ukraine war. The article conducts a thorough analysis of volatility spillovers between these two crucial sectors, elucidating directional volatility transmission and pinpointing key sectors that serve as primary contributors to volatility shocks. Notably, the Total Spillover Index (TSI), a pivotal metric in this context, consistently records at approximately 13% throughout the study period, indicating noteworthy spillover effects and a robust inter-sector connectedness. This study not only brings to light intricate patterns of spillover effects but also provides valuable insights into their implications for financial stability.

This study aims to investigate the relationship between online media usage and the risk of being subjected to internet harassment among undergraduate students at Chiang Mai Rajabhat University. The sample consists of 417 undergraduate students from Chiang Mai Rajabhat University, selected using accidental sampling. Data was collected through questionnaires. The independent variables involved in the research are age, gender, faculty of the respondents, time periods for using online media, the number of hours spent online per day, the number of devices assessing online media, and the number of activities engaged in on online media. Structural Equation Modeling (SEM) was employed to examine the associations among these variables. The results showed that the statistically significant factors that influence the risk of online cyberbully are different in each variable. Specifically, in the gender variable provided strong evidence, and very strong evidence was observed for the number of devices used to access online media. These were identified as significant factors affecting the risk of internet harassment among students.

This study delves into the factors that influence consumers’ decisions to purchase OTOP products through electronic commerce marketplaces (E-Marketplace) in Chiang Mai Province. It explores four key sets of factors: demographics, Consumer buying behavior through e-marketplaces, the online marketing mix (6Ps), and 5A marketing strategies that impact consumer behavior. The online marketing mix (6Ps) comprises Product, Price, Place, Promotion, Personalization, and Privacy, while the 5A marketing strategies include Awareness, Appeal, Ask, Act, and Advocate. The binary logistic regression model is used to analyze these factors’ influence on consumer decisions regarding OTOP product purchases through electronic marketplaces. Our results, show the importance of personalization in marketing strategies and the role of frequency in purchases emerged as key influencers on consumer behavior. These insights can guide OTOP businesses in adapting their marketing strategies and product offerings to cater to changing consumer demands in an increasingly digital landscape.

The learning outcome of each student depends on a lot of factors: learning spirit, level of interest in learning, training, and taking part in activities to create the best environment for developing skills, improving their academic achievement, and the influence of the learning environment, work, teamwork, etc. The paper uses Bayesian Information Criteria in Learning Outcome: Evidence from Vietnam. The learning outcome is used to discover a research model comprising 06 factors: Facilities (FAC), Lecturer (LEC), University (UNI), Learning Motivation (MOT), Learning Method (LM), and Friend (FR). We collected a sample of 98 responses in the analysis. The results show that Lecturer (LEC), University (UNI), and Friend (FR) influence learning outcome (LO). From the research results, the author has given some implications to help managers improve learning outcomes. Previous studies revealed that using linear regression. This study uses the optimal choice of Bayesian Information Criteria.