• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.65-82
• /
• 2021

Stock market investors are generally split into foreign investors, institutional investors, and individual investors. Compared to individual investor groups, professional investor groups such as foreign investors have an advantage in information and financial power and, as a result, foreign investors are known to show good investment performance among market participants. The purpose of this study is to propose an investment strategy that combines investor-specific transaction information and machine learning, and to analyze the portfolio investment performance of the proposed model using actual stock price and investor-specific transaction data. The Korea Exchange offers daily information on the volume of purchase and sale of each investor to securities firms. We developed a data collection program in C# programming language using an API provided by Daishin Securities Cybosplus, and collected 151 out of 200 KOSPI stocks with daily opening price, closing price and investor-specific net purchase data from January 2, 2007 to July 31, 2017. The self-organizing map model is an artificial neural network that performs clustering by unsupervised learning and has been introduced by Teuvo Kohonen since 1984. We implement competition among intra-surface artificial neurons, and all connections are non-recursive artificial neural networks that go from bottom to top. It can also be expanded to multiple layers, although many fault layers are commonly used. Linear functions are used by active functions of artificial nerve cells, and learning rules use Instar rules as well as general competitive learning. The core of the backpropagation model is the model that performs classification by supervised learning as an artificial neural network. We grouped and transformed investor-specific transaction volume data to learn backpropagation models through the self-organizing map model of artificial neural networks. As a result of the estimation of verification data through training, the portfolios were rebalanced monthly. For performance analysis, a passive portfolio was designated and the KOSPI 200 and KOSPI index returns for proxies on market returns were also obtained. Performance analysis was conducted using the equally-weighted portfolio return, compound interest rate, annual return, Maximum Draw Down, standard deviation, and Sharpe Ratio. Buy and hold returns of the top 10 market capitalization stocks are designated as a benchmark. Buy and hold strategy is the best strategy under the efficient market hypothesis. The prediction rate of learning data using backpropagation model was significantly high at 96.61%, while the prediction rate of verification data was also relatively high in the results of the 57.1% verification data. The performance evaluation of self-organizing map grouping can be determined as a result of a backpropagation model. This is because if the grouping results of the self-organizing map model had been poor, the learning results of the backpropagation model would have been poor. In this way, the performance assessment of machine learning is judged to be better learned than previous studies. Our portfolio doubled the return on the benchmark and performed better than the market returns on the KOSPI and KOSPI 200 indexes. In contrast to the benchmark, the MDD and standard deviation for portfolio risk indicators also showed better results. The Sharpe Ratio performed higher than benchmarks and stock market indexes. Through this, we presented the direction of portfolio composition program using machine learning and investor-specific transaction information and showed that it can be used to develop programs for real stock investment. The return is the result of monthly portfolio composition and asset rebalancing to the same proportion. Better outcomes are predicted when forming a monthly portfolio if the system is enforced by rebalancing the suggested stocks continuously without selling and re-buying it. Therefore, real transactions appear to be relevant.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1049-1060
• /
• 2009

The expansion of volatility in Korean Stock Market made it more difficult for the individual to invest directly and increased the weight of indirect investment through a fund. The purpose of this study is to construct the EIF(enhanced index fund) model achieves an excessive return among several types of fund. For this purpose, this paper propose portfolio optimization model to manage an index fund by using GA(genetic algorithm), and apply the trading amount and the closing price of standard index to earn an excessive return add to index fund return. The result of the empirical analysis of this study suggested that the proposed model is well represented the trend of KOSPI 200 and the new investment strategies using this can make higher returns than Buy-and-Hold strategy by an index fund, if an appropriate number of stocks included.

• The Korean Journal of Financial Management
• /
• v.23 no.2
• /
• pp.85-107
• /
• 2006

This paper investigates whether the futures market responds to the news more sensitively and uses more diverse information than the spot market. The sensitivity to the news is measured by the coefficients of the model which regresses the daily changes in the futures prices to the daily changes in the theoretical prices computed from spot prices using the spot-futures parity. The diversity of news is measured by the mean range differences ($\overline{RD}$), mean hi-price differences($\overline{HD}$) and mean low-price differences. The data in this paper is the closing prices of the nearest-to-maturity and the second-nearest-to-maturity contracts of the KOSPI 200 index futures. As the estimates of the relative sensitivity of the futures prices($^{\beta}$) for the whole-period sample are not significantly different from 1, the sensitivity of two markets to the news are not different. However, $\hat{\beta}$ of the most recent period(Nov. 2002 to Dec. 2005) are strongly different from 1. And, in the most recent period, the futures price changes for the good news, which is defined as the price increase of KOSPI of more than 1.5% in a day, show additional sensitivity. Since the mean range different which measures the relative diversity of information used, are not significantly different from 0 for the whole-period and subperiod samples, and this can be interpreted that the futures market does not use more diverse information than the spot market. However, the mean high-price difference, which measures the relative diversity of good news, are significantly different from 0 for the nearest-maturity contracts in the whole-period and subperiod samples. This evidence supports that the futures prices reflects more diverse good news which brings price increase in the market.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.189-200
• /
• 2015

Stationary bootstrapping is applied to a Lagrangian multiplier (LM) test to test market microstructure noise (MMN) in financial asset prices. A Monte-Carlo experiment shows that the bootstrapping method improves the size of the original LM test which has some size distortion for conditional heteroscedastic models. The proposed test is illustrated for real data sets like KOSPI index and Won-Dollar exchange rate.

• Journal of Service Research and Studies
• /
• v.9 no.1
• /
• pp.51-71
• /
• 2019

The purpose of this research is to analyze the ETF market, which has a large increase in the number of listed shares and the market capitalization, and to identify the investment effects of ETFs. The study procedure and method used to calculate the return and change trend of ETFs for the sample of the transaction information, the transaction amount, and the market capitalization for the period from 2010 to 2018, and performed correlation and regression analysis. As a result, the ETF's total return was 2.11%, the domestic underwriting market ETF yield was 2.39%, and the stock ETF yield was 2.59%, which was lower than the KOSPI 200 index and the KOSPI 200 index. Index ETF was 2.63%, followed by stock ETF and oversea underwriting market ETF. The problem with ETF investment is that the annual return of ETFs and domestic ETFs is as low as 2%, which is not enough for investors to expect more than 5%. The study contributes to the realization of the ETF by analyzing the actual effect of the investment and to establishing considerations when buying ETFs from the viewpoint of investors. The direction of the research is to accumulate more ETF data and present the investment direction precisely.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.4
• /
• pp.202-211
• /
• 2014

Pairs trading is a type of arbitrage investment strategy that buys an underpriced security and simultaneously sells an overpriced security. Since the 1980s, investors have recognized pairs trading as a promising arbitrage strategy that pursues absolute returns rather than relative profits. Thus, individual and institutional traders, as well as hedge fund traders in the financial markets, have an interest in developing a pairs trading strategy. This study proposes pairs trading rules (PTRs) created from a price ratio between securities (i.e., stock index futures) using rough set analysis. The price ratio involves calculating the closing price of one security and dividing it by the closing price of another security and generating Buy or Sell signals according to whether the ratio is increasing or decreasing. In this empirical study, we generate PTRs through rough set analysis applied to various technical indicators derived from the price ratio between KOSPI 200 and S&P 500 index futures. The proposed trading rules for pairs trading indicate high profits in the futures market.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.281-291
• /
• 2020

This study used Gauss-Poisson jump diffusion process on standard assets to estimate the statutory reserves of Variable Annuity (VA) guarantees specified in Korean bylaw of insurance supervision and calculated guarantee fees and risks based on the model to see the effect of considering the jumps. Financial assets, except KOSPI 200, have fat-tailed return distributions, which is an indirect evidence of discontinuous jumps. In the case of a domestic stock index and foreign stock indexes(Korean Won), guarantee fees and risks decrease when jumps are considered in models of underlying assets. This is explained by decreases in standard deviations after the jump diffusion is considered. On the other hand, in the case of domestic bond indexes and a foreign bond index(Korean Won), guarantee fees and risks tend to increase when jumps are considered. Results from a foreign stock index(US Dollar) and a foreign bond index(US Dollar) were opposite to those from the same kinds of Korean Won indexes. We conclude that VA guarantee fees and risks may be under or over estimated when jumps are not considered in models of underlying assets.

• Journal of Intelligence and Information Systems
• /
• v.16 no.1
• /
• pp.71-92
• /
• 2010

As the use of trading systems increases recently, many researchers are interested in developing intelligent trading systems using artificial intelligence techniques. However, most prior studies on trading systems have common limitations. First, they just adopted several technical indicators based on stock indices as independent variables although there are a variety of variables that can be used as independent variables for predicting the market. In addition, most of them focus on developing a model that predicts the direction of the stock market indices rather than one that can generate trading signals for maximizing returns. Thus, in this study, we propose a novel intelligent trading system that mitigates these limitations. It is designed to use both the technical indicators and the other non-price variables on the market. Also, it adopts 'two-threshold mechanism' so that it can transform the outcome of the stock market prediction model based on support vector machines to the trading decision signals like buy, sell or hold. To validate the usefulness of the proposed system, we applied it to the real world data-the KOSPI200 index from May 2004 to December 2009. As a result, we found that the proposed system outperformed other comparative models from the perspective of 'rate of return'.

• The Korean Journal of Applied Statistics
• /
• v.23 no.5
• /
• pp.823-834
• /
• 2010

Stock markets perpetually accumulate information. During trading hours the price instantaneously reacts to new information, but accumulated overnight information reacts simultaneously on the opening price. This can create opening price uctuations. This study explores the overnight information e ects on intra-da stock market volatility. GARCH models and the VKOSPI model are provided. Empirical data includes daily opening and closing prices of the KOSPI 200 index and the VKOSPI from March $3^{rd}$ 2008 to June $22^{th}$ 2010. Empirical results show that the VKOSPI signi cantly decrease during trading time when positiv overnight information moves the Korean stock upward. This study provides useful information to investors since the Korea Exchange plans to introduce a futures market for the VKOSPI soon.