• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.3
• /
• pp.1171-1180
• /
• 2021

This study aims to investigate the impact of the multimarket contract on risk-adjusted profitability. Risk-adjusted profitability is measured in terms of risk-adjusted return on assets. This study employs dynamic panel data of 27 commercial banks in Vietnam using the GMM estimator to test the multimarket contact hypothesis in the Vietnamese banking sector. The results show that there is a negative impact of multimarket contact on the profitability of banks. Multimarket contact, deposit to asset ratio, non-interest income to total income, GDP growth rate, Worldwide Governance Indicator (WGI), and operating cost to assets are the major determinants of risk-adjusted profitability of commercial banks. Our main findings show that Vietnamese banks' focus to increase the multimarket contact may lead to lower profitability and there is evidence that supports theory predictions, since the average number of contacts among banks, bank size, and capitalization are positively related to risk-adjusted profitability. The study has policy implications for commercial banks in that they should not only focus on interest as a source of income and diversify their income source from non-interest income as well since it helps to improve risk-adjusted profitability for them.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.3
• /
• pp.467-476
• /
• 2022

The Bank of Korea raised the benchmark interest rate by a quarter percentage point to 1.75 percent per year, and analysts predict that South Korea's policy rate will reach 2.00 percent by the end of calendar year 2022. Furthermore, because market volatility has been significantly increased by a variety of factors, including rising rates, inflation, and market volatility, many investors have struggled to meet their financial objectives or deliver returns. Banks and financial institutions are attempting to provide Robo-Advisors to manage client portfolios without human intervention in this situation. In this regard, determining the best hyper-parameter combination is becoming increasingly important. This study compares some activation functions of the Deep Deterministic Policy Gradient(DDPG) and Twin-delayed Deep Deterministic Policy Gradient (TD3) Algorithms to choose a sequence of actions that maximizes long-term reward. The DDPG and TD3 outperformed its benchmark index, according to the results. One reason for this is that we need to understand the action probabilities in order to choose an action and receive a reward, which we then compare to the state value to determine an advantage. As interest in machine learning has grown and research into deep reinforcement learning has become more active, finding an optimal hyper-parameter combination for DDPG and TD3 has become increasingly important.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.10
• /
• pp.1-8
• /
• 2022

Purpose: Support vector machines (SVMs) ensemble has been proposed to improve classification performance of Credit risk recently. However, currently used fusion strategies do not evaluate the importance degree of the output of individual component SVM classifier when combining the component predictions to the final decision. To deal with this problem, this paper designs a support vector machines (SVMs) ensemble method based on fuzzy integral, which aggregates the outputs of separate component SVMs with importance of each component SVM. Research design, data, and methodology: This paper designs a personal credit risk evaluation index system including 16 indicators and discusses a support vector machines (SVMs) ensemble method based on fuzzy integral for designing a credit risk assessment system to discriminate good creditors from bad ones. This paper randomly selects 1500 sample data of personal loan customers of a commercial bank in China 2015-2020 for simulation experiments. Results: By comparing the experimental result SVMs ensemble with the single SVM, the neural network ensemble, the proposed method outperforms the single SVM, and neural network ensemble in terms of classification accuracy. Conclusions: The results show that the method proposed in this paper has higher classification accuracy than other classification methods, which confirms the feasibility and effectiveness of this method.

• Asia-Pacific Journal of Business
• /
• v.12 no.4
• /
• pp.13-40
• /
• 2021

Purpose - The purpose of this study is to predict corporate corruption in emerging markets such as Brazil, Russia, India, and China (BRIC) using different machine learning techniques. Since corruption is a significant problem that can affect corporate performance, particularly in emerging markets, it is important to correctly identify whether a company engages in corrupt practices. Design/methodology/approach - In order to address the research question, we employ predictive analytic techniques (machine learning methods). Using the World Bank Enterprise Survey Data, this study evaluates various predictive models generated by seven supervised learning algorithms: k-Nearest Neighbour (k-NN), Naïve Bayes (NB), Decision Tree (DT), Decision Rules (DR), Logistic Regression (LR), Support Vector Machines (SVM), and Artificial Neural Network (ANN). Findings - We find that DT, DR, SVM and ANN create highly accurate models (over 90% of accuracy). Among various factors, firm age is the most significant, while several other determinants such as source of working capital, top manager experience, and the number of permanent full-time employees also contribute to company corruption. Research implications or Originality - This research successfully demonstrates how machine learning can be applied to predict corporate corruption and also identifies the major causes of corporate corruption.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.3
• /
• pp.23-31
• /
• 2022

The study investigates the effect of trade openness on the economic growth of agricultural countries. The information of export, import, gross domestic product (GDP), Gross Fixed Capital Formation (GFCF), and population of 72 agrarian nations generated by the World Bank from 2011 until 2020 is used for data examination. Then, before panel data analysis, a preferred model is chosen from among common-effects, fixed-effects, and random effects. The best model turns out to be a fixed-effect model. The result reports that from 2011 to 2020; 16 out of 72 nations have succeeded in experiencing positive economic growth, the value of GFCF was US$ 2,859.04 billion, and later grew by 19 percent to US$ 3,393.73 billion, the population tends to increase continuously year by year, and 2 out of 72 countries experienced export plus import exceed their GDP. Moreover, trade openness is positively associated with economic growth, with a coefficient of 3.81. Besides that, an increase in GFCF may boost economic growth by approximately 3.32 percent. On the contrary, one percent additional population significantly delivers around 25.46 percent negative economic growth. To sum up, the higher intensity of products or services sold and bought abroad may enhance the economic performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.551-569
• /
• 2024

With the rapid development of electric vehicles (EVs) industry, EV charging service becomes more and more important. Especially, in the case of suddenly drop of air temperature or open holidays that large-scale EVs seeking for charging devices (CDs) in a short time. In such scenario, inefficient EV charging scheduling algorithm might lead to a bad service quality, for example, long queueing times for EVs and unreasonable idling time for charging devices. To deal with this issue, this paper propose a Deep-Q-Network (DQN) based two-stage scheduling method for the large-scale EVs charging service. Fine-grained states with two delicate neural networks are proposed to optimize the sequencing of EVs and charging station (CS) arrangement. Two efficient algorithms are presented to obtain the optimal EVs charging scheduling scheme for large-scale EVs charging demand. Three case studies show the superiority of our proposal, in terms of a high service quality (minimized average queuing time of EVs and maximized charging performance at both EV and CS sides) and achieve greater scheduling efficiency. The code and data are available at THE CODE AND DATA.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.259-266
• /
• 2021

Recently, the financial industry has seen a dramatic change due to the development of innovative technologies such as FinTech, but there is a lack of research on the digital level of financial institution workers. This study analyzes factors that affect the willingness of financial institution workers to accept digital innovation and to examine the relationship between acceptance intention and business performance. Based on the theoretical basis of UTAUT, independent variables were divided into internal expectations, external influences, facilitation conditions, and employment risks. Survey data of 100 bankers at N bank were analyzed using SPSS and AMOS 18. Studies have shown that internal expectations and external influences have positive effects on the acceptance intention of financial institution workers, and that facilitation conditions, employment risks do not. This study found a significant relationship between acceptance intention and business performance and confirming that acceptance intention has a direct and indirect impact on business performance. Study findings could be a reference to enhancing the willingness to accept digital innovation technologies and developing ways to improve business performance by validating factors that affect the willingness of financial institution workers to accept digital innovation.

• Asia Marketing Journal
• /
• v.11 no.4
• /
• pp.21-48
• /
• 2010

This article analyzes film performances in the Korean movie market utilizing three-stage models that incorporate available information in three different stages of the movie life cycle, i.e., at the time of its release, at the end of the first week, and at the end of its life cycle. Based on the premise that the performance of a movie is affected principally by factors of scale, evaluation, and competition, we attempted to ascertain the effects on these factors on performances, and how they differ in different stages. Also, by analyzing domestic and foreign movies released in Korea separately, we were able to compare the different effects of the three factors on the performances of the two categories of movies. Additionally, our movie performance models incorporated herding behavior among the customers. Our results demonstrate that herding is prominently observed after the first week only for domestic movies. In general, the scale factor has been shown to be most important for movie performances in all stages. For foreign films, it is particularly critical for the first week and total performances. Whereas the evaluation factor influences domestic film performance more strongly at the screen choice stage, it affects the performance of foreign films more strongly in the later stages of the life cycle. As compared to foreign films, domestic film performance appears to be more sensitive to the competition factor. We also discuss the effects of covariates such as genre and symbolicity on movie performance.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.11-19
• /
• 2014

In recent SONAR (sound navigation and ranging) systems, wideband active SONAR systems has received more attention than narrowband SONAR systems due to the remarkable detection performance in terms of range resolution. However, the wideband SONAR systems usually requires a huge amount of computational burden in order to achieve their own superiority. To cope with this drawback of the wideband SONAR systems, this paper proposes a fast target detection and velocity estimation method using an extended replica in wideband hyperbolic frequency modulation active SONAR system. Computer simulation shows that the proposed method can be implemented by a highly reduced computational complexity with a little performance degradation in target detection and velocity estimation compared to the conventional filter bank method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.103-111
• /
• 2004

The method of speaker normalization has been known as the successful method for improving the accuracy of speech recognition at speaker independent speech recognition system. A frequency warping approach is widely used method based on maximum likelihood for speaker normalization. This paper propose a new power spectrum warping approach to making improvement of speaker normalization better than a frequency warping. Th power spectrum warping uses Mel-frequency cepstrum analysis(MFCC) and is a simple mechanism to performing speaker normalization by modifying the power spectrum of Mel filter bank in MFCC. Also, this paper propose the hybrid VTN combined the Power spectrum warping and a frequency warping. Experiment of this paper did a comparative analysis about the recognition performance of the SKKU PBW DB applied each speaker normalization approach on baseline system. The experiment results have shown that a frequency warping is 2.06%, the power spectrum is 3.06%, and hybrid VTN is 4.07% word error rate reduction as of word recognition performance of baseline system.