머신러닝과 시계열 기법 기반의 초단기 시간단위 수요예측방법론 개발 연구
Development of Short-term Time-unit Demand Forecasting Methodology based on Machine Learning and Time Series Model
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Demand forecasting is an important field and it is safe to say that forecasting is a key component of economic activity. An accurate forecasting is the key to determining the competitiveness of all economic players. Forecasting an uncertain future is a difficult task and radical change in the external environment are adding to the difficulty of forecasting. Amid the increasing demand for accurate demand forecasting, the emergence of Big data, AI, ML, and DL following the development of computing power is becoming a major turning point in the demand forecasting field as well. In addition to the traditional forecasting methodologies, the use of dataming techniques is also rapidly increasing. And various efforts have been continued to improve the forecasting accuracy. In this paper, a hybrid forecasting methodology which is combined time series model and data mining technique and a multistage methodology are presented for short-term forecasting. Specifically, we developed a hybrid forecasting model that combines SARIMA(Seasonal Autoregressive Integrated Moving Average) and Random Forest, and a multistage methodology that utilizing the forecasting result of the upper-category as a variable in the forecasting process of the sub-category. In order to verify the methodologies presented in this paper, we use the rental data of ‘Seoul bike’(shared bicycle in Seoul) as verification data. As a result of the forecasting ‘Seoul bike’ demand for the next 7 days(every 3 hours) of rental point clusters, the average forecasting accuracy was 81.5%. It is high accuracy level considering that the forecasting unit was 3hours, forecasting horizon was next 56 steps, and the average accuracy by Random forest was 65%. In addition, it was confirmed that high accuracy was maintained steadily regardless of the time difference from the forecasting point unlike the characteristics of general demand forecasting, And the high accuracy level was confirmed as a forecasting model not only a 3 hours forecasting, but also daily(90.1%) and weekly(91.7%) forecasting. The research shows the forecasting methodologies of this paper is worth to use as a short-term forecasting model. And we confirmed that the methodologies are very useful to forecasting daily and weekly demand as well. It is expected that the methodologies proposed in this paper will be widely used as an accurate forecasting model in more diverse fields.
Abstract
Demand forecasting is an important field and it is safe to say that forecasting is a key component of economic activity. An accurate forecasting is the key to determining the competitiveness of all economic players. Forecasting an uncertain future is a difficult task and radical change in the external environment are adding to the difficulty of forecasting. Amid the increasing demand for accurate demand forecasting, the emergence of Big data, AI, ML, and DL following the development of computing power is becoming a major turning point in the demand forecasting field as well. In addition to the traditional forecasting methodologies, the use of dataming techniques is also rapidly increasing. And various efforts have been continued to improve the forecasting accuracy. In this paper, a hybrid forecasting methodology which is combined time series model and data mining technique and a multistage methodology are presented for short-term forecasting. Specifically, we developed a hybrid forecasting model that combines SARIMA(Seasonal Autoregressive Integrated Moving Average) and Random Forest, and a multistage methodology that utilizing the forecasting result of the upper-category as a variable in the forecasting process of the sub-category. In order to verify the methodologies presented in this paper, we use the rental data of ‘Seoul bike’(shared bicycle in Seoul) as verification data. As a result of the forecasting ‘Seoul bike’ demand for the next 7 days(every 3 hours) of rental point clusters, the average forecasting accuracy was 81.5%. It is high accuracy level considering that the forecasting unit was 3hours, forecasting horizon was next 56 steps, and the average accuracy by Random forest was 65%. In addition, it was confirmed that high accuracy was maintained steadily regardless of the time difference from the forecasting point unlike the characteristics of general demand forecasting, And the high accuracy level was confirmed as a forecasting model not only a 3 hours forecasting, but also daily(90.1%) and weekly(91.7%) forecasting. The research shows the forecasting methodologies of this paper is worth to use as a short-term forecasting model. And we confirmed that the methodologies are very useful to forecasting daily and weekly demand as well. It is expected that the methodologies proposed in this paper will be widely used as an accurate forecasting model in more diverse fields.
참고문헌 (34)
- 남승엽, "전시 피격 및 고장을 고려한 전투기 추가 소요 예측 모델 연구", 로지스틱스연구, 24(1), pp.81~94 (2016), 한국로지스틱스학회[DOI]
- 문현지, "파렛트 이동량에 대한 시간 단위 군집화 예측 모델", 로지스틱스연구, 27(4), pp.1~10 (2019), 한국로지스틱스학회[DOI]
- 장기왕, "전투기 수리부속 수요예측 프로세스 개선을 위한 실증적 연구", 로지스틱스연구, 25(4), pp.195~212 (2017), 한국로지스틱스학회[DOI]
- Baldigara T., "Modelling international tourism demand using seasonal ARIMA models", Tourism and Hospitality Management, 21 (2015)
- Chang W., "A SARIMA Model of Tourism Forecasting: The Case of Taiwan", Asia Pacific Journal of Tourism Research, 16 (2010)
- Chen C. F., "SARIMA forecasting of inbound air travel arrivals to Taiwan", Transportmetrica, 5 (2019)
- Chen G., "Multiple random forests modelling for urban water consumption forecasting", Water Resources Management, 31 (2017)
- Chen P., "Time Series Forecasting of Temperatures using SARIMA:An Example from Nanjing", IOP Conference Series:Materials Science and Engineering, pp.394~ (2018)
- Chiba Z., "Intelligent approach to build a Deep Neural Network based IDS for cloud environment using combination of machine learning algorithms", Computers & Security, 86 (2019)
- Dickey D. A., "Distribution of the estimators for autoregressive time series with a unit root", Journal of the American Statistical Association, 74 (1979)
- Dikshit A., "Short-term spatio-temporal drought forecasting using random forests model at New South Wales, Australia", Applied Sciences, 10 (2020)
- Dimri T., "Time series analysis of climate variables using seasonal ARIMA approach", Journal of Earth System Science, 129 (2020)
- Dudek G., "Short-Term Load Forecasting Using Random Forests", Intelligent Systems’ 2014 (2014)
- Jin F., "Forecasting air passenger demand with a new hybrid ensemble approach", Journal of Air Transport Management, 83 (2020)
- Ghosha P., "Forecasting directional movements of stock prices for intraday trading using LSTM and random forests", Finance Research Letters (2021)
- Kane M. J., "Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1outbreaks", BMC Bioinformatics, 15 (2014)
- Kumar R., "Time Series Data Prediction using IoT and Machine Learning Technique", Procedia Computer Science, 167 (2020)
- Kumar S. V., "Short-term traffic flow prediction using seasonal ARIMA model with limited input data", Europian Transport Research Review (2015)
- Liu H., "Improved pollution forecasting hybrid algorithms based on the ensemble method", Applied Mathematical Modelling, 73 (2019)
- Liu X., "Short-term offshore wind speed forecast by seasonal ARIMA - A comparison against GRU and LSTM", Energy, 227 (2021)
- Lui H., "A new hybrid ensemble deep reinforecement learning model for wind speed short term forecasting", Energy, 202 (2020)
- Luong C., "Forecasting of Realised Volatility with the Random Forests Algorithm", Journal of Risk and Financial Management, 11 (2018)
- Ma T., "Forecasting of monthly temperature variations using random forests", ARPN Journal of Engineering and Applied Sciences, 10 (2015)
- Ma T., "Hybrid machine learning algorithm and statistical time series model for network-wide traffic forecast", Transportation Research Part C : Emerging Technologies, 111 (2020)
- Mohamed N., "Short Term Load Forecasting Using Double SARIMA Model", Proceedings of the Regional Conference on Statistical Sciences (2010)
- Nielsen R. F., "Hybrid machine learning assisted modeling framework for particle processes", Computers &Chemical Engineering, 140 (2020)
- Papacharalampous G. A., "Evaluation of random forests and Prophet for daily streamflow forecasting", Advances in Geosciences, 45 (2018)
- Phan T. T. H., "Combining Statistical Machine Learning Models with ARIMA for Water Level Forecasting: The Case of the Red River", Advances in Water Resources, 142 (2020)
- Punia S., "Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail", International Journal of Production Research, 58 (2020)
- Tyralis H., "Variable Selection in Time Series Forecasting Using Random Forests", Algorithm, 10 (2017)
- Wang Y., "Application of residual modification approach in seasonal ARIMA for electricity demand forecasting:A case study of China", Energy Policy, 48 (2012)
- Williams B. M., "Modeling and Forecasting Vehicular Traffic Flowas a SARIMA Process: Theoretical Basis and Empirical Results", Journal OF Transportation Engineering, 129 (2003)
- Yang H. F., "Hybrid deep learning and empirical mode decomposition model for time series applications", Expert Systems with Applications, 120 (2019)
- Yu P. S., "Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting", Journal of Hydrology, 552 (2017)