• 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.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.2
• /
• pp.67-75
• /
• 2012

Different from other natural hazards including floods, drought advances slowly and spreads widely, so that the preparedness is quite important and effective to mitigate the impacts from drought. Evaluation and forecast the status of drought for the present and future utilizing the meteorological scenario for agricultural drought can be useful to set a plan for agricultural drought mitigation in agriculture water resource management. In this study, drought climate scenario model on the basis of historical drought records for preparing agricultural drought mitigation was developed. To consider dependency and correlation between various climate variables, this model was utilized the historical climate pattern using reference year setting of four drought levels. The reference year for drought level was determined based on the frequency analysis result of monthly effective rainfall. On the basis of this model, drought climate scenarios at Suwon and Icheon station were set up and these scenarios were applied on the water balance simulation of reservoir water storage for Madun reservoir as well as the soil moisture model for Gosam reservoir watershed. The results showed that drought climate scenarios in this study could be more useful for long-term forecast of longer than 2~3 months period rather than short-term forecast of below one month.

• Atmosphere
• /
• v.31 no.1
• /
• pp.73-83
• /
• 2021

Numerical weather prediction (NWP) models play an essential role in predicting weather factors, but using them is challenging due to various factors. To overcome the difficulties of NWP models, deep learning models have been deployed in weather forecasting by several recent studies. This study adapts long short-term memory (LSTM), which demonstrates remarkable performance in time-series prediction. The combination of LSTM model input of meteorological features and activation functions have a significant impact on the performance therefore, the results from 5 combinations of input features and 4 activation functions are analyzed in 9 Automated Surface Observing System (ASOS) stations corresponding to cities/islands/mountains. The optimized LSTM model produces better performance within eight forecast hours than Local Data Assimilation and Prediction System (LDAPS) operated by Korean meteorological administration. Therefore, this study illustrates that this LSTM model can be usefully applied to very short-term weather forecasting, and further studies about CNN-LSTM model with 2-D spatial convolution neural network (CNN) coupled in LSTM are required for improvement.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.453-459
• /
• 2021

The system marginal price of electricity is the amount paid to all the generating units, which is an important decision-making factor for the construction and maintenance of an electrical power unit. In this paper, we suggest a long-term forecasting model for calculating the system marginal price based on prices of natural gas and oil. As most variables used in the analysis are nonstationary time series, the long run relationship among the variables should be examined by cointegration tests. The forecasting model is similar to an error correction model which consists of a long run cointegrating equation and another equation for short run dynamics. To mitigate the robustness issue arising from the relatively small data sample, this study employs various testing and estimating methods. Compared to previous studies, this paper considers multiple fuel prices in the forecasting model of system marginal price, and provides greater emphasis on the robustness of analysis. As none of the cointegrating relations associated with system marginal price, natural gas price and oil price are excluded, three error correction models are estimated. Considering the root mean squared error and mean absolute error, the model based on the cointegrating relation between system marginal price and natural gas price performs best in the out-of-sample forecast.

• Journal of Korean Society of Forest Science
• /
• v.50 no.1
• /
• pp.29-35
• /
• 1980

The purpose of this study is to analyze and to forecast the long-term domestic demand and export demand for timber in Korea by regression models with time series data during 1962~1978. The method applied in this study was econometric analysis using Time Series Processor. The most important explanatory variables of timber demand were found to be the production activities of wood products industries to the prices of substitute goods. On the basis of the long-term forecast made according to the guidelines of the Fifth Five-Year Plan. According to the projection, domestic timber demand is projected at 8 million cubic meters in 1987 and 10.6 million cubic meters in 1991. On the other hand, the total demand (domestic demand plus export demand) for timber is projected 21.4 million cubic meters in 1987 and 27.2 million cubic meters in 1991.

• Journal of Energy Engineering
• /
• v.18 no.2
• /
• pp.114-124
• /
• 2009

The Ministry of Knowledge and Economy (MKE) establishes the Basic Plan for Long-Term Electricity Supply and Demand(BPE) biannually, a governmental plan for the stable electricity supply. This study investigated the effects of the electric demand forecast on the energy mix. A simplified simulation model was developed, which replaces the WASP program developed by the KPX and verified by comparing both results. Three different electric demand scenarios were devised based upon the 2005 electric demand forecast: Proper, 5 % higher, and 5% lower. The simplified model calculates the energy mix for each scenario of the year 2005. Then it calculates the energy mix for the proper electric demand forecast of the year 2007 using the energy mixes of the three scenarios as the initial conditions, so that it reveals the effect of electric demand forecast of the previous BPE on the energy mix of the next BPE. As the proper electric demand forecasts of the year 2005 and 2007 are the same, there is no change in the previous and the next BPEs. However when the electric demand forecasts were 5% higher in the previous BPE and proper in the next BPE, some of the planned power plant construction in the previous BPE had to be canceled. Similarly, when the electric demand forecasts were 5% lower in the previous BPE and proper in the next BPE, power plant construction should be urgently increased to meet the increased electric demand. As expected the LNG power plants were affected as their construction periods are shorter than coal fired or nuclear power plants. This study concludes that the electric demand forecast is very important and that it has the risk of long term energy mix.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.311-324
• /
• 2021

Investors have increasingly become interested in macroeconomic antecedents in order to better understand the investment environment and estimate the scope of profitable investment in equity markets. This study endeavors to examine the interdependency between the macroeconomic antecedents (international oil price (COP), Domestic gold price (GP), Rupee-dollar exchange rates (ER), Real interest rates (RIR), consumer price indices (CPI)), and the BSE Sensex and Nifty 50 index return. The data is converted into a natural logarithm for keeping it normal as well as for reducing the problem of heteroscedasticity. Monthly time series data from January 1992 to July 2019 is extracted from the Reserve Bank of India database with the application of financial Econometrics. Breusch-Godfrey serial correlation LM test for removal of autocorrelation, Breusch-Pagan-Godfrey test for removal of heteroscedasticity, Cointegration test and VECM test for testing cointegration between macroeconomic factors and market returns,] are employed to fit regression model. The Indian market returns are stable and positive but show intense volatility. When the series is stationary after the first difference, heteroskedasticity and serial correlation are not present. Different forecast accuracy measures point out macroeconomics can forecast future market returns of the Indian stock market. The step-by-step econometric tests show the long-run affiliation among macroeconomic antecedents.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.42 no.1
• /
• pp.29-41
• /
• 2017

Korea is expected to become a super-aged society by 2050. Given an aging population and the increasing pressure for the early retirement, a sufficient social safety net for elderly population becomes important. The Korean government introduced public reverse mortgage program in 2007, which is a product for aging seniors and the elderly, The number of reverse mortgage subscribers has also steadily grown. The demand continues to grow, but the reverse mortgage over a long period of time is a highly uncertain and risky product in the position of guarantee or lending institution. Thus, suitable demand prediction of the reverse mortgage subscribers is necessary for stable and sustainable operation. This study uses a Bass diffusion model to forecast the long-term demand for reverse mortgage and provides insight into reverse mortgage by forecasting demand for stability and substantiality of the loan product. We represent the projections of new subscribers on the basis of the data obtained from Korea Housing Finance Corporation. Results show that potential market size of Korean reverse mortgage reaches approximately 760,000-1,160,000 households by 2020. We validate the results by comparing the estimate of the cumulative number of subscribers with that found in literature.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.25-30
• /
• 2016

It is critical to forecast the maximum daily and monthly demand for power with as little error as possible for our industry and national economy. In general, long-term forecasting of power demand has been studied from both the consumer's perspective and an econometrics model in the form of a generalized linear model with predictors. Time series techniques are used for short-term forecasting with no predictors as predictors must be predicted prior to forecasting response variables and containing estimation errors during this process is inevitable. In previous researches, seasonal exponential smoothing method, SARMA (Seasonal Auto Regressive Moving Average) with consideration to weekly pattern Neuron-Fuzzy model, SVR (Support Vector Regression) model with predictors explored through machine learning, and K-means clustering technique in the various approaches have been applied to short-term power supply forecasting. In this paper, SARMA and intervention model are fitted to forecast the maximum power load daily, weekly, and monthly by using the empirical data from 2011 through 2013. $ARMA(2,\;1,\;2)(1,\;1,\;1)_7$ and $ARMA(0,\;1,\;1)(1,\;1,\;0)_{12}$ are fitted respectively to the daily and monthly power demand, but the weekly power demand is not fitted by AREA because of unit root series. In our fitted intervention model, the factors of long holidays, summer and winter are significant in the form of indicator function. The SARMA with MAPE (Mean Absolute Percentage Error) of 2.45% and intervention model with MAPE of 2.44% are more efficient than the present seasonal exponential smoothing with MAPE of about 4%. Although the dynamic repression model with the predictors of humidity, temperature, and seasonal dummies was applied to foretaste the daily power demand, it lead to a high MAPE of 3.5% even though it has estimation error of predictors.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.7
• /
• pp.297-306
• /
• 2017

Citizens want more accurate forecast information using Bus Information System. However, most bus information systems that use an average based short-term prediction algorithm include many errors because they do not consider the effects of the traffic flow, signal period, and halting time. In this paper, we try to improve the precision of forecast information by analyzing the influencing factors of the error, thereby making the convenience of the citizens. We analyzed the influence factors of the error using BIS data. It is shown in the analyzed data that the effects of the time characteristics and geographical conditions are mixed, and that effects on halting time and passes speed is different. Therefore, the halt time is constructed using Generalized Additive Model with explanatory variable such as hour, GPS coordinate and number of routes, and we used Hidden Markov Model to construct a pattern considering the influence of traffic flow on the unit section. As a result of the pattern construction, accurate real-time forecasting and long-term prediction of route travel time were possible. Finally, it is shown that this model is suitable for travel time prediction through statistical test between observed data and predicted data. As a result of this paper, we can provide more precise forecast information to the citizens, and we think that long-term forecasting can play an important role in decision making such as route scheduling.