• Proceedings of the KSR Conference
• /
• 2003.10b
• /
• pp.35-39
• /
• 2003

Effort has been given to improve demand forecast methodology of rail system since it can have great impact on project evaluation of rail system investment. However most of demand forecast softwares developed in western countries where concerns have been provided mostly to private transport and they should be updated in order to reflect our country's situation accurately. Therefore, this paper aims, especially focusing on rail system, to do comparison analysis of oversea's passenger demand forecast softwares and provide some ideas to develop the updated demand forecast system which enables to reflect our country's situation accurately. Main conclusions are that we will need to have well described model for real situation. So we will have to study for these aspects for travel demand forecasting system and develop the package architecture.

• Journal of the Korean Statistical Society
• /
• v.7 no.1
• /
• pp.11-16
• /
• 1978

Bayesian procedures are in vogue to revise the parameter estimates of the forecasting model in the light of actual time series data. In this paper, we study the Bayes forecast for demand and the risk when (a) 'noise' and (b) mean demand rate in a constant process model have moderately non-normal probability distributions.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1116-1123
• /
• 2006

The methodological framework proposed in this paper addresses the strength of the applied Bass model by Mahajan and Muller(1996) that it reflects the substitution of next generations among products. Also this paper is to estimate and analyze the forecast of demand for products that do not exist in the marketplace. We forecast the sales of digital TV using estimated market share and data obtained by the face to face Interview. In this research, we use two methods to analyze the demand for Digital TV that are the forecasting the Demand for the Substitution and binary logit analysis. The logit analysis is to estimate the decisive factor of purchasing digital TV. The decisive factors are composed of purchasing plan, region, gender, TV price, contents, coverage, income, age, and TV program. We apply the model to South Korea's market for digital TV. The results show that (1) Income, region and TV price play a prominent part which is the decisive factor of purchasing digital TV. (2) We forecaste the demand of digital TV that will be demanded about 18 millions TVs in 2015

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.11
• /
• pp.1608-1614
• /
• 2014

Power demand forecasting is an important factor of the peak management. This paper deals with the 15 minutes ahead load forecasting problem in a DC urban railway system. Since supplied power lines to trains are connected with parallel, the load characteristics are too complex and highly non-linear. The main idea of the proposed method for the 15 minutes ahead prediction is to use the daily load similarity accounting for the load nonlinearity. An Euclidean norm with weighted factors including loads of the neighbor substation is used for the similar load selection. The prediction value is determinated by the sum of the similar load and the correction value. The correction has applied the neural network model. The feasibility of the proposed method is exemplified through some simulations applied to the actual load data of Incheon subway system.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.161-171
• /
• 2019

Varied methods have been researched continuously because the past as the daily maximum electricity demand expectation has been a crucial task in the nation's electrical supply and demand. Forecasting the daily peak electricity demand accurately can prepare the daily operating program about the generating unit, and contribute the reduction of the consumption of the unnecessary energy source through efficient operating facilities. This method also has the advantage that can prepare anticipatively in the reserve margin reduced problem due to the power consumption superabundant by heating and air conditioning that can estimate the daily peak load. This paper researched a model that can forecast the next day's daily peak load when considering the influence of temperature and weekday, weekend, and holidays in the Seasonal ARIMA, TBATS, Seasonal Reg-ARIMA, and NNETAR model. The results of the forecasting performance test on the model of this paper for a Seasonal Reg-ARIMA model and NNETAR model that can consider the day of the week, and temperature showed better forecasting performance than a model that cannot consider these factors. The forecasting performance of the NNETAR model that utilized the artificial neural network was most outstanding.

• Journal of Korean Institute of Industrial Engineers
• /
• v.13 no.1
• /
• pp.25-29
• /
• 1987

When the historical data are available, the diffusion model, which describes the time pattern of the adoption process of a new product or technology or service, has been used as a reasonable predictor in the telecommunication demand forecasting area. This paper shows that the diffusion model is applicable when the historical data are not available. The model used is in the form of a "logistic" function. The parameters of the function are estimated using the questionnaire and the historical data of reference products. From the questionnaire, an initial and an upper limit long run value of the market share are estimated, and the diffusion time to the upper limit value is determined by the relation between the investment and the utility.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.17-27
• /
• 2020

District heating system supplies heat from low-cost high-efficiency heat production facilities to heat demand areas through a heat pipe network. For efficient heat supply system operation, it is important to accurately predict the heat demand within the region and optimize the heat production plan accordingly. In this study, a heat demand forecasting model is proposed considering real-time calorimeter information from local heat demands. Previous models considered ambient temperature and heat demand history data to predict future heat demands. To improve forecast accuracy, the proposed heat demand forecast model added big data from real-time calorimeters installed in the heat demands within the target region. By employing calorimeter information directly in the model, it is expected that the proposed forecast model is to reflect heat use pattern of each demand. Computational experiemtns based on the actual heat demand data shows that the forecast accuracy of the proposed model improved when the calorimeter big data is reflected.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.63 no.4
• /
• pp.307-311
• /
• 2014

Due to the increasing of power consumption, it is difficult to construct accurate prediction model for daily peak power demand. It is very important work to know power demand in next day for manager and control power system. In this research, we develop a daily peak power demand prediction method considering of characteristics of day of week. The proposed method is composed of liner model based on AR model and nonlinear model based on ELM to resolve the limitation of a single model. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.