• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.59-76
• /
• 2023

Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.

• Advanced Industrial SCIence
• /
• v.2 no.3
• /
• pp.22-28
• /
• 2023

In this study, we conducted research on the automated trading of U.S. stocks through a volatility strategy using the Fear and Greed index. Volatility in the stock market is a common phenomenon that can lead to fluctuations in stock prices. Investors can capitalize on this volatility by implementing a strategy based on it, involving the buying and selling of stocks based on their expected level of volatility. The goal of this thesis is to investigate the effectiveness of the volatility strategy in generating profits in the stock market.This study employs a quantitative research methodology using secondary data from the stock market. The dataset comprises daily stock prices and daily volatility measures for the S&P 500 index stocks. Over a five-year period spanning from 2016 to 2020, the stocks were listed on the New York Stock Exchange (NYSE). The strategy involves purchasing stocks from the low volatility group and selling stocks from the high volatility group. The results indicate that the volatility strategy yields positive returns, with an average annual return of 9.2%, compared to the benchmark return of 7.5% for the sample period. Furthermore, the findings demonstrate that the strategy outperforms the benchmark return in four out of the five years within the sample period. Particularly noteworthy is the strategy's performance during periods of high market volatility, such as the COVID-19 pandemic in 2020, where it generated a return of 14.6%, as opposed to the benchmark return of 5.5%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.419-430
• /
• 2023

Currently, NFTs have no dominant application except for the proof of ownership for digital content, and it also have small liquidity problem, which makes their price difficult to predict. Real estate usually has very high barriers to investment due to its high pricing. Real estate can be converted into NFTs and also divided into small value fungible tokens (FTs), and it can increase the the volume of the investor community due to more liquidity and better accessibility. In this document, we implement and design a system that allows ordinary users can invest on high priced real estate utilizing Black Litterman (BL) model-based Portfolio investment interface. To this end, we target a set of real estates pegged as collateral and issue NFT for the collateral using blockchain. We use oracle to get the current real estate information and to monitor varying real estate prices. After tokenizing real estate into NFTs, we divide the NFTs into easily accessible price FTs, thereby, we can lower prices and provide large liquidity with price volatility limited. In addition, we also implemented BL based asset portfolio interface for effective portfolio composition for investing in multiple of real estates with small investments. Using BL model, investors can fix the asset portfolio. We implemented the whole system using Solidity smart contracts on Flask web framework with public data portals as oracle interfaces.

• Economic Analysis
• /
• v.27 no.1
• /
• pp.67-90
• /
• 2021

This study found an interesting fact that the nonlinear relationship structure between volatility and trading volume changed before and after the COVID-19 pandemic according to empirical analysis using Bitcoin (BTC) market data that sensitively reflects investors' trading behavior. That is, their relationship appeared positive (+) in a stable market state before COVID-19 pandemic, as in theory based on the information flow paradigm. In a state under severe market stress due to COVID-19 pandemic, however, their dependence structure changed and even negative (-). This can be seen as a consequence of increased market stress caused by COVID-19 pandemics from a behavioral economics perspective, resulting in structural changes in the asset market and a significant impact on the nonlinear dependence of volatility and trading volume (in particular, their dependence at extreme quantiles). Hence, it should be recognized that in addition to information flows, psychological phenomena such as behavioral biases or herd behavior, which are closely related to market stress, can be a key in changing their dependence structure. For empirical analysis, this study performs a test of Ross (2015) for detecting a structural change, and proposes a Copula Regression Quantiles (CRQ) approach that can identify their nonlinear relationship structure and the asymmetric dependence in their distribution tails without the assumption of i.i.d. random variable. In addition, it was confirmed that when the relationship between their extreme values was analyzed by linear models, incorrect results could be derived due to model specification errors.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.251-264
• /
• 2022

The purpose of this study is to present factors and strategies for successful rewarded-crowdfunding of companies. For this, rewarded-crowdfunding based on the extended theory of planned behavior(E-TPB) by adding individual innovation and risk preference as extended variables, in addition to the basic variables of the theory of planned behavior(TPB), including attitude, subjective norm, and perceived behavior control. In addition, the moderating effect of rewarded-crowdfunding experience was confirmed. In addition, the moderating effect of the rewarded-crowdfunding experience was confirmed, and exploratory factor analysis and multiple regression analysis were conducted for questionnaires who were aware of the concept of rewarded-crowdfunding. As a result of testing the hypothesis, it was found that attitude, subjective norm, perceived behavioral control, and risk preference affect the intention to invest in rewarded-crowdfunding. Also, we could find that perceived behavior control and risk preference were moderately influenced by investor who had experience in rewarded-crowdfunding. Based on the research results, it has academic and practical value by presenting the direction of enhancing the success of rewarded-crowdfunding that companies can use as a way to raise funds and boost sales.

• Korea Trade Review
• /
• v.41 no.1
• /
• pp.67-90
• /
• 2016

This study examines whether there is any significant relation between executive compensation and future firm performance for the Korean export manufacturing small and medium-sized firms. We sorted the whole sample firms into the sub-groups of 10 deciles by firm size and the KSIC standard. We found the following empirical results. First, Korean export manufacturing small and medium-sized firms typically showed lower or even negative profitability in terms of return on equity and operating profit ratio to sales. Foreign equity ownership is very low with an average of 3.77%. Second, for the firms with higher ratio of excess executive compensation to asset had lower future firm performance. It implies that the typical owner-manager in Korean export manufacturing SMEs earns excess pay, but do not contribute much to firm performance. Third, as for future cumulative abnormal returns for future one- and three-year periods, firms with higher owner-executive pay had lower returns compared with firms with lower pay. So the stock market investors set a lower value on them. Fourth, there is a positive relation between excess executive pay and executive overconfidence, and it implies that owner-CEOs with higher pay may become overconfident, thereby lowering future firm performance somehow.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.85-100
• /
• 2023

Corporate ESG performance (environmental, social, and corporate governance) reflecting a company's strategic sustainability has emerged as one of the main factors in today's investment decisions. The traditional ESG performance rating process is largely performed in a qualitative and subjective manner based on the institution-specific criteria, entailing limitations in reliability, predictability, and timeliness when making investment decisions. This study attempted to predict the corporate ESG rating through automated machine learning based on quantitative and disclosed corporate financial information. Using 12 types (21,360 cases) of market-disclosed financial information and 1,780 ESG measures available through the Korea Institute of Corporate Governance and Sustainability during 2019 to 2021, we suggested a deep neural network prediction model. Our model yielded about 86% of accurate classification performance in predicting ESG rating, showing better performance than other comparative models. This study contributed the literature in a way that the model achieved relatively accurate ESG rating predictions through an automated process using quantitative and publicly available corporate financial information. In terms of practical implications, the general investors can benefit from the prediction accuracy and time efficiency of our proposed model with nominal cost. In addition, this study can be expanded by accumulating more Korean and international data and by developing a more robust and complex model in the future.

• The Korean Journal of Franchise Management
• /
• v.2 no.1
• /
• pp.1-45
• /
• 2011

Franchising is one of the most effective strategies in promoting business establishment, creating jobs and accelerating economic growth. Thus, many countries in the world foster franchise business and support the franchise industry by enacting relevant regulations and making development policies. Vietnam deregulated franchise market through making franchise-related laws on June, 2005 and after joining WTO in 2009, Vietnamese government opened up the franchise market by letting foreign investors acquire 100% share on their investment in Vietnam. In addition, Vietnamese consumer's rapidly growing income and increasing liking for western life style make Vietnamese franchise market attractive and profitable. For this reason, many global franchise firms are competing to get the best seats. However, there has been no Korean attempt to profoundly study over Vietnamese franchise market. The purpose of this study would focus on analyzing and evaluating cases of Korean and international firms which successfully entered Vietnamese market and on proposing effective strategies and key success factors. The result of this study indicates that the companies successfully settled down to the Vietnamese market have developed marketing strategies which fit their strengths, and their common key success factors are 1) making the best of first mover advantage, 2) adapting themselves to local tastes and behaviors via systematic and scientific market research, 3) making thorough supervision on safety and hygiene, 4) doing strategy of firstly directly being operated and settled down by franchisor, later being managed by franchisees, 5) benchmarking both successful and failed cases in other countries.