• Information Systems Review
• /
• v.26 no.2
• /
• pp.45-57
• /
• 2024

This study develops a deep learning-based methodology for predicting Crude Palm Oil (CPO) prices. Palm oil is an essential resource across various industries due to its yield and economic efficiency, leading to increased industrial interest in its price volatility. While numerous studies have been conducted on palm oil price prediction, most rely on time series forecasting, which has inherent accuracy limitations. To address the main limitation of traditional methods-the absence of stationarity-this research introduces a novel model that uses the ratio of future prices to current prices as the dependent variable. This approach, inspired by return modeling in stock price predictions, demonstrates superior performance over simple price prediction. Additionally, the methodology incorporates the consideration of lag values of independent variables, a critical factor in multivariate time series forecasting, to eliminate unnecessary noise and enhance the stability of the prediction model. This research not only significantly improves the accuracy of palm oil price prediction but also offers an applicable approach for other economic forecasting issues where time series data is crucial, providing substantial value to the industry.

• Journal of Service Research and Studies
• /
• v.10 no.1
• /
• pp.55-67
• /
• 2020

Fine dust has recently become one of the greatest concerns of Korean people and has been a target of considerable efforts by governments and local governments. In the academic world, many researches have been carried out in relation to fine dust, but the research on the economic field has been relatively few. So we wanted to know how fine dust affects the economy. Big data of PM10 concentration for fine dust and fine dust theme stock price were collected for five years from 2013 to 2017. Regression analysis was performed using the linear regression model, the generalized least squares method. As a result, the change in the fine dust concentration was found to have a effect on the related theme stocks' price. When the fine dust concentration increased compared to the previous day, the fine dust theme stocks' price also showed a tendency to increase. Also, according to the analysis of stock price change from 2013 to 2017 based on fine dust theme stocks, companies with large regression coefficients were changed every year. Among them, the regression coefficients of Monalisa were repeatedly high in 2014, 2015, 2017, Samil Pharmaceutical in 2015, 2016 and 2017, and Welcron in 2016 and 2017, and the companies were judged to be sensitive to the concentration of fine dust. The companies that responded the most in the past 5 years were Wokong, Welcron, Dongsung Pharmaceutical, Samil Pharmaceutical, and Monalisa. If PM2.5 measurement data are accumulated enough, it would be meaningful to compare and analyze PM2.5 concentration with independent variables. In this study, only the fine dust concentration is used as an independent variable. However, it is expected that a more clear and well-explained result can be found by adding appropriate additional variables to increase the explanatory power.

• Journal of Information Technology Services
• /
• v.19 no.2
• /
• pp.109-124
• /
• 2020

Facing the 4^th Industrial Revolution era, researches on artificial intelligence have become active and attempts have been made to apply machine learning in various fields. In the field of finance, Robo Advisor service, which analyze the market, make investment decisions and allocate assets instead of people, are rapidly expanding. The stock price prediction using the machine learning that has been carried out to date is mainly based on the prediction of the market index such as KOSPI, and utilizes technical data that is fundamental index or price derivative index using financial statement. However, most researches have proceeded without any explicit verification of the prediction rate of the learning data. In this study, we conducted an experiment to determine the degree of market prediction ability of basic indicators, technical indicators, and system risk indicators (AR) used in stock price prediction. First, we set the core parameters for each financial indicator and define the objective function reflecting the return and volatility. Then, an experiment was performed to extract the sample from the distribution of each parameter by the Markov chain Monte Carlo (MCMC) method and to find the optimum value to maximize the objective function. Since Robo Advisor is a commodity that trades financial instruments such as stocks and funds, it can not be utilized only by forecasting the market index. The sample for this experiment is data of 17 years of 1,500 stocks that have been listed in Korea for more than 5 years after listing. As a result of the experiment, it was possible to establish a meaningful trading strategy that exceeds the market return. This study can be utilized as a basis for the development of Robo Advisor products in that it includes a large proportion of listed stocks in Korea, rather than an experiment on a single index, and verifies market predictability of various financial indicators.

• Asia-Pacific Journal of Business
• /
• v.11 no.2
• /
• pp.159-172
• /
• 2020

Purpose - The purpose of this study is to investigate economic variables which have impact on the prices and returns of preferred stocks and to provide investors, underwriters, and policy makers with information regarding correlations and causal relations between them. Design/methodology/approach - This study collected 98 monthly data from Korea Exchange and Bank of Korea. The Granger causal relation analysis, unit-root test and the multiple regression analysis were hired in order to analyze the data. Findings - First, our study derives the economic variables affecting the prices and returns of preferred stocks and their implications, while previous studies focused mainly on the differential characteristics and related economic factors between common and preferred stocks. Empirical results show that the significant variables influencing the prices and returns of preffered stocks are consumer sentiment index, consumer price index, industrial production index, KOSPI volatility index, and exchange rate between Korean won and US dollar. Second, consumer sentiment index, consumer price index, and industrial production index have significant casual relations with the returns of preferred stocks, providing market participants with important information regarding investment in preferred stocks. Research implications or Originality - This study is different from previous studies in that preferred stocks themselves are investigated rather than the gap between common stocks and preferred stocks. In addition, we derive the major macro variables affecting the prices and returns of preferred stocks and find some useful causal relations between the macro variables and returns of preferred stocks. These findings give important implications to market participants, including stock investors, underwriters, and policy makers.

• Korean Journal of Construction Engineering and Management
• /
• v.10 no.3
• /
• pp.42-52
• /
• 2009

From the beginning of 2000, Korean housing market has experienced cyclical volatility because of the global economic fluctuation such as steady decline in the interest rate and the house price bubble. In response to these state Korean Government announced policies about housing sales system kinds of Sales Unit Price Restraint and Post-Sales System to stabilize housing market. But such policies has brought unprecedented arguments both for and against, most of whom still seem to stick to self-centered judgement ahead of impact on housing market. In an integrated point of view, applying the system dynamics modeling, the paper aims at proposing basic Korean housing market dynamics models based on basis principles of housing market determined by supply and demand. And then, after research policies about housing sales system, analyze Impact on Korean Housing Market by change of Sales Systems applying policies to basic Korean housing market dynamics models.

• Korean Journal of Mathematics
• /
• v.22 no.3
• /
• pp.529-552
• /
• 2014

As we know, some indices and data are strong influence to the price movement of some assets now, but not to another assets and in future. Thus we define some asset models for several time intervals; intraday, weekly, monthly, and yearly asset models. We define these asset models by using Brownian motion with volatility and Poisson process, and several deterministic functions(index function, twitter data function and big-jump simple function etc). In our asset models, these deterministic functions are the positive or negative levels of auxiliary indices, of analyzed data, and for imminent and extreme state(for example, financial shock or the highest popularity in the market). These functions determined by indices, twitter data and shocking news are a kind of one of speciality of our asset models. For reasonableness of our asset models, we introduce several real data, figurers and tables, and simulations. Perhaps from our asset models, for short-term or long-term investment, we can classify and reference many kinds of usual auxiliary indices, information and data.

• Korea Trade Review
• /
• v.47 no.5
• /
• pp.21-37
• /
• 2022

Baltic Dry Index (BDI) is difficult to forecast because of the high volatility and complexity. To improve the BDI forecasting ability, this study apply Bayesian variable selection method with a large number of predictors. Our estimation results based on the BDI and all predictors from January 2000 to September 2021 indicate that the out-of-sample prediction ability of the ADL model with the variable selection is superior to that of the AR model in terms of point and density forecasting. We also find that critical predictors for the BDI change over forecasts horizon. The lagged BDI are being selected as an key predictor at all forecasts horizon, but commodity price, the clarksea index, and interest rates have additional information to predict BDI at mid-term horizon. This implies that time variations of predictors should be considered to predict the BDI.

• Korean Management Science Review
• /
• v.25 no.3
• /
• pp.1-12
• /
• 2008

The Swaption is one of the popular Interest rates derivatives. In spite of such a popularity, the swaption pricing formula is hard to derived within the theoretical consistency. Most of swaption pricing model are heavily depending on the simulation technique. We present a new class of swaption model based on the multi-factor HJM levy-mixture model. A key contribution of this paper is to provide a generalized swaption pricing formula encompassing many market stylize facts. We provide an approximated closed form solution of the swaption price using the Gram-Charlier expansion. Specifically, the solution form is similar to the market models, since our approximation is based on the Lognormal distribution. It can be directly compared with the traditional Black's formula when the size of third and fourth moments are not so large. The proposed extended levy model is also expected to be capable of producing the volatility smiles and skewness.

• Environmental and Resource Economics Review
• /
• v.21 no.3
• /
• pp.441-464
• /
• 2012

As prices of energy resources such as oil and gas started to rise steadily in 2000, energy security has been one of the most important topics in the world. To secure more energy, most of countries which are highly dependent on imported energy resources try to occupy oversea oil or gas reserves, thereby intensifying competition for energy resources around world. Under this circumstance, we focus on independent E&P companies since they are relatively small size companies which are suitable for M&A. We analyze investment option values for these E&P companies using a real option model for depletable resources. Based on analytical model, empirical study is provided to examine rationality of investment for energy companies. The result shows sufficient profitability for independent E&P companies in both oil and gas projects in the North America during 2004 to 2008. In Particular, oil projects were more feasible than gas project due to lower price of gas and high volatility of gas price at that time.

• Management Science and Financial Engineering
• /
• v.19 no.1
• /
• pp.11-16
• /
• 2013

This paper derives an equilibrium asset price when there exist three kinds of traders in financial market: a risk-averse informed trader, noise traders, and risk neutral market makers. This paper is an extended version of Kyle's (1985, Econometrica) continuous time model by introducing insider's risk aversion. We obtain not only the equilibrium asset pricing and market depth parameter but also insider's value function and optimal insider's trading strategy explicitly. The comparative static shows that the market depth (the reciprocal of market pressure) increases with time and volatility of noise traders' trading.