Browse > Article
http://dx.doi.org/10.17661/jkiiect.2018.11.5.543

Analysis Standardization Layout for Efficient Prediction Model  

Kim, Hyo-Kwan (Department of Fintech Korea Polytechnics)
Hwang, Won-Yong (Department of Fintech Korea Polytechnics)
Publication Information
The Journal of Korea Institute of Information, Electronics, and Communication Technology / v.11, no.5, 2018 , pp. 543-549 More about this Journal
Abstract
The importance of prediction is becoming more emphasized, due to the uncertain business environment. In order to implement the predictive model, a number of data engineers and scientists are involved in the project and various prediction ideas are suggested to enhance the model. it takes a long time to validate the model's accuracy. Also It's hard to redesign and develop the code. In this study, development method such as Lego is suggested to find the most efficient idea to integrate various prediction methodologies into one model. This development methodology is possible by setting the same data layout for the development code for each idea. Therefore, it can be validated by each idea and it is easy to add and delete ideas as it is developed in Lego form, which can shorten the entire development process time. Finally, result of test is shown to confirm whether the proposed method is easy to add and delete ideas.
Keywords
prediction; data engineer; data scientist; data layout; development method;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Taylor, James W, "Triple seasonal methods for short-term electricity demand forecasting," European Journal of Operational Research, vol.204, no.1, pp.139-152, 2010.   DOI
2 SongGyungBin, "An Algorithm of Short-Term Load Forecasting, vol.10, no.53A, pp.529-535, 2004.
3 HyoKwanKim, "A study on the advanced demand forecasting system using big data technique", 2017
4 SeoMyungYul, "A Study on the Seasonal Adjustment of Time Series and Demand Forecasting for Electronic Product Sales," koras, vol.3, no.1, pp13-39, 2003.
5 NamGyunHeo, "A Study on Air Demand Forecasting Using Multivariate Time Series Models" Communications for Statistical Applications and Methods, vol.22, no.5, pp1007-1017, 2009.
6 Berkeley, http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/
7 Taylor, James W, "An evaluation of methods for very short-term load forecasting using minute-by-minute British data," international Journal of Forecasting, vol.24, no.4, pp.645-658, 2008.   DOI