시계열 분석 모델을 이용한 조선 산업 주요물가의 예측에 관한 연구
A Study on the Prediction of Major Prices in the Shipbuilding Industry Using Time Series Analysis Model
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Oil and steel prices, which are major pricescosts in the shipbuilding industry, were predicted. Firstly, the error of the moving average line (N=3–5) was examined, and in all three error analyses, the moving average line (N=3) was small. Secondly, in the linear prediction of data through existing theory, oil prices rise slightly, and steel prices rise sharply, but in reality, linear prediction using existing data was not satisfactory. Thirdly, we identified the limitations of linear prediction methods and confirmed that oil and steel price prediction was somewhat similar to actual moving average line prediction methods. Due to the high volatility of major price flows, large errors were inevitable in the forecast section. Through the time series analysis method at the end of this paper, we were able to achieve not bad results in all analysis items relative to artificial intelligence (Prophet). Predictive data through predictive analysis using eight predictive models are expected to serve as a good research foundation for developing unique tools or establishing evaluation systems in the future. This study compares the basic settings of artificial intelligence programs with the results of core price prediction in the shipbuilding industry through time series prediction theory, and further studies the various hyper-parameters and event effects of Prophet in the future, leaving room for improvement of predictability.
Abstract
Oil and steel prices, which are major pricescosts in the shipbuilding industry, were predicted. Firstly, the error of the moving average line (N=3–5) was examined, and in all three error analyses, the moving average line (N=3) was small. Secondly, in the linear prediction of data through existing theory, oil prices rise slightly, and steel prices rise sharply, but in reality, linear prediction using existing data was not satisfactory. Thirdly, we identified the limitations of linear prediction methods and confirmed that oil and steel price prediction was somewhat similar to actual moving average line prediction methods. Due to the high volatility of major price flows, large errors were inevitable in the forecast section. Through the time series analysis method at the end of this paper, we were able to achieve not bad results in all analysis items relative to artificial intelligence (Prophet). Predictive data through predictive analysis using eight predictive models are expected to serve as a good research foundation for developing unique tools or establishing evaluation systems in the future. This study compares the basic settings of artificial intelligence programs with the results of core price prediction in the shipbuilding industry through time series prediction theory, and further studies the various hyper-parameters and event effects of Prophet in the future, leaving room for improvement of predictability.
참고문헌 (13)
- ndreas, M, "Introductory to Machine Learning with Python" (2017), Hanbit Media
- 함주혁, "각종 면내 및 면외 하중을 받는 선박판부재의 이중판 설계시스템 구축", 대한조선학회 논문집, 55(6), pp.521~526 (2018), 대한조선학회[DOI]
- Ham, J. H, "A study on the prediction of major prices in the shipbuilding industry using artificial intelligence", Autumn Conference of the Society of Naval Architects of Korea, pp.167~171 (2019)
- Ham, J.H, "A study on the prediction of stock price of large shipyards using deep learning", Autumn Conference of the Society of Naval Architects of Korea, pp.172~176 (2019)
- Ham, J.H, "Development of hybrid prototype dual loadcell structure", Journal of the Society of Naval Architects of Korea, 57(6), pp.373~380 (2021)
- Ham, J.H, "A study on the prediction of major prices in the shipbuilding industry using artificial intelligence -Comparison analysis with existing prediction methods", Spring Conference of the Society of Naval Architects of Korea (2021)
- Ham, J.H, "A study on the prediction of stock preice of large shipyards using deep learning-Comparison analysis with existing prediction methods", Spring Conference of the Society of Naval Architects of Korea (2021)
- Harvey, A, "Estimation procedures for structural time series models", Journal of Forecasting, 9, pp.89~108 (1990)
- Harvey, A. C, "Handbook of Statistics’, Vol. 11", pp.261~302 (1993), Elsevier
- Hutchinson, G. E, "An introduction to population ecology" (1978), Yale university press
- "Introducing the time series prediction package prophet" (2020)[URL]
- Kujira, H, "Introduction to machine running, deep learning practical development using python" (2017), Wikibooks
- "Forecasting at Scale" (2019)[URL]