• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.172.6-172
• /
• 2001

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock, or other economic markets. Most previous experiments used multilayer perceptrons(MLP) for stock market forecasting, The Kospi 200 Index is modeled using different neural networks and fuzzy system predictions. In this paper, a multilayer perceptron architecture, a dynamic polynomial neural network(DPNN) and a fuzzy system are used to predict the Kospi 200 index. The results of prediction is compared with the root mean squared error(RMSE) and the scatter plot. The results show that the fuzzy system is performing slightly better than DPNN and MLP. We can develop the desired fuzzy system by learning methods ...

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.37
• /
• pp.31-40
• /
• 1996

The amount of safety stock is decided from various information such as the forecasted demand, the lead time, the size of the order quantity and the desired service level. There are two cases to consider the problem of setting safety stock when both the demand in a period and the lead time are characterized as random variables: the first case is the parameters of the demand and lead time distributions are known, the second case is they are unknown and must be estimated. The objective of this study is to present the procedure for setting safety stocks in the case the parameters of the demand and lead time distributions are unknown and must be estimated. In this study, a simple exponential smoothing model is used. to generate the estimates of demand in each period and a discrete distribution of the lead time is developed from historical data, and the optimal service level is used which determined to consider both of a backorder and lost sale.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.7-12
• /
• 2003

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock or other economic markets. Most previous experiments used the neural network models for the stock market forecasting. The KOSPI 200 (Korea Composite Stock Price Index 200) is modeled by using different neural networks and fuzzy logic. In this paper, the neural network, the dynamic polynomial neural network (DPNN) and the fuzzy logic employed for the prediction of the KOSPI 200. The prediction results are compared by the root mean squared error (RMSE) and scatter plot, respectively. The results show that the performance of the fuzzy system is little bit worse than that of the DPNN but better than that of the neural network. We can develop the desired fuzzy system by optimization methods.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2030-2032
• /
• 2001

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock, or other economic markets. Most previous experiments used multilayer perceptrons(MLP) for stock market forecasting. The Kospi 200 Index is modeled using different neural networks and fuzzy system predictions. In this paper, a multilayer perceptron architecture, a dynamic polynomial neural network(DPNN) and a fuzzy system are used to predict the Kospi 200 index. The results of prediction is compared with the root mean squared error(RMSE) and the scatter plot. Results show that both networks can be trained to predict the index. And the fuzzy system is performing slightly better than DPNN and MLP.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.31-39
• /
• 2022

Stock prices are influenced by a number of external factors, such as laws and trends, as well as number-based internal factors such as trading volume and closing prices. Since many factors affect stock prices, it is very difficult to accurately predict stock prices using only fragmentary stock data. In particular, since the value of a company is greatly affected by the perception of people who actually trade stocks, emotional information about a specific company is considered an important factor. In this paper, we propose a deep learning-based stock price prediction model using sentiment analysis with news data considering temporal characteristics. Stock and news data, two heterogeneous data with different characteristics, are integrated according to time scale and used as input to the model, and the effect of time scale and sentiment index on stock price prediction is finally compared and analyzed. Also, we verify that the accuracy of the proposed model is improved through comparative experiments with existing models.

• Management Science and Financial Engineering
• /
• v.21 no.2
• /
• pp.13-23
• /
• 2015

This study addresses the question as to whether the option prices have useful predictive information on the direction of stock markets by investigating a forecasting power of volatility curvatures and skewness premiums implicit in S&P 500 index option prices traded in Chicago Board Options Exchange. We begin by estimating implied volatility functions and risk neutral price densities every minute based on non-parametric method and then calculate volatility curvature and skewness premium using them. The rationale is that high volatility curvature or high skewness premium often leads to strong bullish sentiment among market participants. We found that the rate of return on the signal following trading strategy was significantly higher than that on the intraday buy-and-hold strategy, which indicates that the S&P500 index option prices have a strong forecasting power on the direction of stock index market. Another major finding is that the information contents of S&P 500 index option prices disappear within one minute, and so one minute-delayed signal following trading strategy would not lead to any excess return compared to a simple buy-and-hold strategy.

• Korean System Dynamics Review
• /
• v.3 no.1
• /
• pp.79-104
• /
• 2002

A system dynamics project is going on for forecasting automobile market in Korea. The project is made up of three stages, and the first stage has been wrapped up. As the first attempt, most efforts have been focused on the sound foundation rather than the exact forecast. The model consists of three sectors; the supply sector, the demand sector, and the population sector. The supply sector is a simple stock and flow diagrams representing the supply capacities of all automobile types. The major effort is made on the demand sector and the population sector. The demands are divided into three categories; replacement demands, new demands, and additional demands. The model applies “one car per person" concept, and assumes there will be no additional demands for a while. The replacement demands are calculated based on a simple stock and flow diagram. The new demands are calculated via Bass models; each bass model represents a diffusion for each age group. The population is divided into 101 age groups (age 0 to age 100). The model has been calibrated with past 10 year data (1990 - 1999), and tested for the next two years (2000-2001). The results ware acceptable, although a fine tuning is required. Now the second stage is going on, and most of efforts are made how to incorporate the economic and cultural factors.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.30 no.4
• /
• pp.65-75
• /
• 2022

This study aims to forecast of Air Passenger Demand between South Korea and North Korea using the system dynamics analysis methodology that is based on the system thinking. System dynamics is not only a tool that makes the systematic thought to a model but also a computer program-based analysis methodology that mathematically models the system varying according to time variation. This study analyzed the causal relationship based on the interrelation among variables and structured them by considering various variables that affect aviation cooperation from the perspective of Air passenger demand forecasting. In addition, based on the causal relationship between variables, this study also completed the causal loop diagram that forms a feedback loop, constructed the stock-flow diagram of Inter-Korean model using Vensim program. In this study, Air passenger demand was using by the simulation variable value into System Dynamics. This study was difficult to reflect the various variables constituting the North Korea environment, and there is a limit to the occurrence of events in North Korea.

• Asia pacific journal of information systems
• /
• v.7 no.1
• /
• pp.67-83
• /
• 1997

The utility of learning techniques in investment analysis has been demonstrated in many areas, ranging from forecasting individual stocks to entire market indexes. To date, however, the application of artificial intelligence to financial forecasting has focused largely on short predictive horizons. Usually the forecast window is a single period ahead; if the input data involve daily observations, the forecast is for one day ahead; if monthly observations, then a month ahead; and so on. Thus far little work has been conducted on the efficacy of long-term prediction involving multiperiod forecasting. This paper examines the impact of alternative procedures for extended prediction using knowledge discovery techniques. One dimension in the study involves temporal granularity: a single jump from the present period to the end of the forecast window versus a web of short-term forecasts involving a sequence of single-period predictions. Another parameter relates to the numerosity of input variables: a technical approach involving only lagged observations of the target variable versus a fundamental approach involving multiple variables. The dual possibilities along each of the granularity and numerosity dimensions entail a total of 4 models. These models are first evaluated using neural networks, then compared against a multi-input jump model using case based reasoning. The computational models are examined in the context of forecasting the S&P 500 index.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.