수요 패턴 별 최적 머신러닝 수요예측 모델 성능 비교
Optimal Machine Learning-Based Demand Prediction Model Performance Comparison by Demand Pattern
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
수요예측은 제품에 대한 수요량을 예측해 자원을 관리하기 위한 방법으로, 기업의 노동력과 예산 관리에 영향을 미친다. 이러한 이유로 수요예측 모델의 성능 향상을 위한 연구가 주목을 받고 있다. 본 연구에서는 수요예측 성능 향상을 위해 품목의 수요 패턴을 분석해 4가지 유형으로 구분하고, 각 유형에 적합한 모델을 제안한다. 성능 비교를 위해 사용한 데이터는 대한민국 공군 T-50 단일 기종의 수리 부속 품목의 분기 별 수요 데이터이다. 품목의 수요 패턴은 수요발생구간(average demand interval, ADI)과 변동 계수(coefficient of variation, CV)를 사용해 네 가지 smooth, lumpy, intermittent, erratic으로 구분하며 다양한 알고리즘으로 구현한 수요예측 모델의 성능을 비교하기 위해 5가지 기계학습 알고리즘과 2 가지 딥러닝 알고리즘을 사용해 수요예측 모델을 구현한다. 기계학습 알고리즘 중에는 앙상블 알고리즘인 random forest regression, adaboost, extra trees regression, bagging, gradient boosting regression 과 딥러닝 알고리즘인 long-short term memory(LSTM), deep neural network(DNN)을 사용한다. 수요 패턴에 따른 네 가지 유형에 적합한 모델을 선정해 수요예측 결과를 도출한 경우가 일관된 모델을 사용한 경우에 비해 품목 정확도가 0.61%, 수량 정확도가 0.09 우수한 것을 확인할 수 있다. 제안하는 모델을 적용한다면 전문가의 효율적인 수요 관리가 이루어질 수 있을 것으로 기대한다.
Abstract
Demand forecasting is a way to manage resources by forecasting demands for products, so it has direct impacts on corporate resources and budget management. Based on these reasons, research on improving forecasting performances of demand forecasting models. In this research, 4 demand patterns for items were analyzed to improve demand prediction performance, and the optimal model was proposed. The data used to compare the performance were the demand data from each quarter for maintenance items for a T-50 aircraft of Republic of Korea air force. First, the demand patterns for the items adopted average demand interval(ADI) and coefficient of variation(CV) and were categorized into smooth, lumpy, intermittent, and erratic items. In this research, to compare the performance of demand forecasting models derived from different algorithms, 5 types of machine learning algorithms and 2 types of deep learning algorithms were used to construct demand forecasting models. In machine learning algorithms, there are ensemble learning such as random forest regression, adaboost, extra trees regression, bagging, gradient boosting regression and deep learning algorithm such as long-short term memory(LSTM) and deep neural network(DNN). We can confirm that item accuracy is 0.61% and quantity accuracy is 0.09% better than that of consistent models when the demand forecast results are derived by selecting models suitable for four types according to demand patterns. We expect that efficient demand management by experts will be achieved if the application of the proposed model.
참고문헌 (44)
- Hua, Z. S., "A new approach of forecasting intermittent demand for spare parts inventories in the process industries", Journal of the Operational Research Society, 58(1), pp.52~61 (2007)
- Moon, S., "The development of a hierarchical forecasting method for predicting spare parts demand in the South Korean Navy —A case study", International Journal of Production Economics, 140(2), pp.794~802 (2012)
- Ghobbar, A. A., "Evaluation of forecasting methods for intermittent parts demand in the field of aviation: a predictive model", Computers & Operations Research, 30(14), pp.2097~2114 (2003)
- Esperon-Miguez, M., "A review of integrated vehicle health management tools for legacy platforms: challenges and opportunities", Progress in Aerospace Sciences, 56, pp.19~34 (2013)
- "Structural Integrity Management of German Combat and Mission Aircraft"[URL]
- Giaouris, D., "A systems approach for management of microgrids considering multiple energy carriers, stochastic loads, forecasting and demand side response", Applied Energy, 226, pp.546~559 (2018)
- 윤현민, "데이터마이닝을 활용한 해군함정 수리부속 수요예측", 한국산업경영시스템학회지, 40(4), pp.253~259 (2017), 한국산업경영시스템학회
- Wang, D., "DeepSD:supply-demand prediction for online car-hailing services using deep neural networks", IEEE 33rd International Conference on Data Engineering (ICDE). IEEE, pp.243~254 (2017)
- I. H. Witten, "Data Mining:Practical machine learning tools and techniques" (2005), Morgan Kaufmann
- Yeonghyeon Gu, "Designing a Machine Learning-based System for Predicting the Demand for Spare Parts and Maintenance of Military Equipment", International Conference on Big Data Applications and Services (2017)
- Won Hee Chung, "Demand prediction model for air force equipment", International Conference on Big Data Applications and Services (2018)
- 윤예진, "회귀 분석을 이용한 Intel SGX 상의 안전한 전력 수요 예측", 한국차세대컴퓨팅학회 논문지, 13(4), pp.7~18 (2017), 한국차세대컴퓨팅학회
- Ghobbar, Adel A., "Evaluation of forecasting methods for intermittent parts demand in the field of aviation: a predictive model", Computers & Operations Research, 30(14), pp.2097~2114 (2003)
- Da Woon Jeong, "Clustering for forecasting item demand of repair parts of military equipment by demand pattern", International Conference on Big Data Applications and Services (2018)
- Chawla, Aditya, "Applications of Artificial Intelligence Techniques in Engineering", pp.79~89 (2019), Springer
- Kumar, Prasanna, D. M., "Demand forecasting Using Artificial Neural Network Based on Different Learning Methods:Comparative Analysis", International journal for research in applied science and engineering technology (2014)
- AlFuhaid, A. S., "Cascaded artificial neural networks for short-term load forecasting", IEEE Transactions on Power Systems, 12(4), pp.1524~1529 (1997)
- Gan, Min, "Seasonal and trend time series forecasting based on a quasi-linear autoregressive model", Applied Soft Computing, 24, pp.13~18 (2014)
- Yan, Xing, "A comparison between SVM and LSSVM in mid-term electricity market clearing price forecasting", 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering(CCECE). IEEE (2013)
- Yan, Xing, "Mid-term electricity market clearing price forecasting utilizing hybrid support vector machine and auto-regressive moving average with external input", International Journal of Electrical Power & Energy Systems, 63, pp.64~70 (2014)
- Zhang, G. Peter, "Neural network forecasting for seasonal and trend time series", European journal of operational research, 160(2), pp.501~514 (2005)
- Hamzaçebi, Coşkun, "Improving artificial neural networks’ performance in seasonal time series forecasting", Information Sciences, 178(23), pp.4550~4559 (2008)
- Taskaya-Temizel, Tugba, "A comparative study of autoregressive neural network hybrids", Neural Networks, 18(5-6), pp.781~789 (2005)
- Cai, QiSen, "A novel stock forecasting model based on fuzzy time series and genetic algorithm", Procedia Computer Science, 18, pp.1155~1162 (2013)
- Qiu, Xueheng, "Ensemble deep learning for regression and time series forecasting", Computational Intelligence in Ensemble Learning (CIEL), 2014 IEEE Symposium on. IEEE (2014)
- Che, Zhengping, "Recurrent neural networks for multivariate time series with missing values", Scientific reports (2018)
- Chen, Thao-Tsen, "A weighted LS-SVM based learning system for time series forecasting", Information Sciences, 299, pp.99~116 (2015)
- Patel, Jigar, "Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques", Expert Systems with Applications, 42(1), pp.259~268 (2015)
- Günay, M. Erdem, "Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey", Energy Policy, 90, pp.92~101 (2016)
- Laptev, Nikolay, "Time-series extreme event forecasting with neural networks at uber", International Conference on Machine Learning (2017)
- Moon, S., "The development of a hierarchical forecasting method for predicting spare parts demand in the South Korean Navy—A case study", International Journal of Production Economics, 140(2), pp.794~802 (2012)
- Giaouris, D., "A systems approach for management of microgrids considering multiple energy carriers, stochastic loads, forecasting and demand side response", Applied Energy, 226, pp.546~559 (2018)
- Wang, D., "DeepSD:supply-demand prediction for online carhailing services using deep neural networks", IEEE 33rd International Conference on Data Engineering (ICDE). IEEE, pp.243~254 (2017)
- Albiński, Szymon, "Performance analysis of a hybrid bike sharing system: A service-level-based approach under censored demand observations", Transportation Research Part E: Logistics and Transportation Review, 116, pp.59~69 (2018)
- Chen, Mu-Chen, "An associationbased clustering approach to order batching considering customer demand patterns", Omega, 33(4), pp.333~343 (2005)
- Padulano, R., "Identification of Annual Water Demand Patterns in the City of Naples", Multidisciplinary Digital Publishing Institute Proceedings (2018)
- Oliveira, Paulo José A., "Do Time Series Models Contribute to Water Demand Clustering?", WDSA, 2018, ~
- Hernández, L., "Classification and clustering of electricity demand patterns in industrial parks", Energies, pp.5215~5228 (2012)
- Oh, Byung-Hoon, "A Study on Spare Parts Demand Forecasting Using Artificial Neural Network", Proceedings of the Korea Information Processing Society Conference (2017), Korea Information Processing Society
- Taegyu Kim, ""A Data Mining Approach for Intermittent Demand Forecasting of Aircraft Spare Parts" Focusing on the E-737(AEW&C: Airborne Early Warning &Control) Spare Parts", ~ (2018)
- Bandara, Kasun, "Sales demand forecast in e-commerce using a long short-term memory neural network methodology", International Conference on Neural Information Processing (2019), Springer
- Syntetos, Aris A., "Service Parts Management", pp.31~52 (2011), Springer
- 최장호, "데이터 센터 전력 관리를 위한 부하 기반 전력 분석 모델 및 저비용 전력 예측 방법", 한국차세대컴퓨팅학회 논문지, 10(2), pp.48~55 (2014), 한국차세대컴퓨팅학회
- 손남례, "SVR 기반 다변수 단기풍력발전예측 모델 연구", 한국차세대컴퓨팅학회 논문지, 13(1), pp.54~64 (2017), 한국차세대컴퓨팅학회