인공지능 기반 수요예측 기법의 리뷰 = A review of artificial intelligence based demand forecasting techniques

다국어 초록 (Multilingual Abstract)

Big data has been generated in various fields. Many companies have now tried to make profits by building a system capable of analyzing big data based on artificial intelligence (AI) techniques. Integrating AI technology has made analyzing and utilizing vast amounts of data increasingly valuable. In particular, demand forecasting with maximum accuracy is critical to government and business management in various fields such as finance, procurement, production and marketing. In this case, it is important to apply an appropriate model that considers the demand pattern for each field. It is possible to analyze complex patterns of real data that can also be enlarged by a traditional time series model or regression model.
However, choosing the right model among the various models is difficult without prior knowledge. Many studies based on AI techniques such as machine learning and deep learning have been proven to overcome these problems. In addition, demand forecasting through the analysis of stereotyped data and unstructured data of images or texts has also shown high accuracy. This paper introduces important areas where demand forecasts are relatively active as well as introduces machine learning and deep learning techniques that consider the characteristics of each field.

국문 초록 (Abstract)

최근 다양한 분야에서 ‘빅데이터’가 생성되었다. 많은 기업들은 인공지능(AI)을 기반으로 빅데이터 분석이 가능한 시스템을 구축하여 이익 창출을 시도하고 있다. 인공지능 기술을 접목함으로써 방대한 양의 데이터를 효율적으로 분석하고 효과적으로 활용하는 것은 점점 더 중요해지고 있다. 특히 재무, 조달, 생산 및 마케팅과 같은 다양한 분야에서 국가 및 기업 경영 관리에있어 최소의 오차와 최대의 정확도를 갖춘 수요예측은 절대적으로 중요한 요소이다. 이 때 각 분야의 수요패턴을 고려한 적절한 모델을 적용하는 것이 중요하다. 전통적으로 쓰이는 시계열모델이나 회귀모델로도 비대해진 실제 데이터의 복잡한 비선형적인 패턴을 분석할 수 있다.
그러나 다양한 비선형 모델들 중에서 적절한 모델을 선택하는 것은 사전 지식 없이는 어려운 일이다. 최근에는 인공지능 기반의 기법들인 머신러닝이나 딥러닝 기법을 중심으로 이루어진 연구들이 이를 극복할 수 있음을 증명하고 있다. 뿐만 아니라 정형데이터와 이미지나 텍스트의 비정형 데이터 분석을 통한 수요예측도 높은 정확도를 갖춘 결과를 보이고 있다. 따라서 본 연구에서는 수요예측이 비교적 활발하게 일어나는 중요한 분야들을 나누어 설명하였다. 그리고 각 분야별로 갖는 특징적인 성격을 고려한 인공지능 기반의 수요예측 기법에 대해 머신러닝과 딥러닝 기법으로 나누어 소개하였다.

참고문헌 (Reference)

1 신동하, "하계 전력수요 예측을 위한 딥 러닝 입력 패턴에 관한 연구" 한국정보기술학회 14 (14): 127-134, 2016

2 박준호, "특수일 분리와 예측요소 확장을 이용한 전력수요 예측 딥 러닝 모델" 한국항행학회 21 (21): 365-370, 2017

3 임준엽, "트위터를 이용한 기계학습 기반의 영화흥행 예측" 한국정보처리학회 3 (3): 263-270, 2014

4 이상훈, "텍스트 마이닝을 활용한 영화흥행 예측 연구" 한국데이터정보과학회 26 (26): 1259-1269, 2015

5 박수지, "텍스트 마이닝을 통한 관광지 수요예측 -온라인 검색 엔진을 중심으로-" 한국관광학회 41 (41): 13-27, 2017

6 김항석, "준지도 학습 및 신경망 알고리즘을 이용한 전기가격 예측" 대한산업공학회 39 (39): 30-45, 2013

7 최석재, "온라인 뉴스 제목 분석을 통한 특정 장소 이벤트 성과 예측을 위한 형태소 분석 방법" 한국전자거래학회 21 (21): 15-32, 2016

8 정호철, "에너지인터넷에서 1D-CNN과 양방향 LSTM을이용한 에너지 수요예측" 한국전기전자학회 23 (23): 134-142, 2019

9 이오준, "소셜 빅데이터를 이용한 영화 흥행 요인 분석" 한국콘텐츠학회 14 (14): 527-538, 2014

10 신광섭, "딥러닝을 이용한 열 수요예측 모델 개발" 사)한국빅데이터학회 3 (3): 59-70, 2018

11 김인중, "딥러닝과 통계 모델을 이용한 T-커머스 매출 예측" 한국정보과학회 44 (44): 803-812, 2017

12 안준영, "동계 전력수요예측을 위한 신경망 모델에 관한 연구" 한국정보기술학회 15 (15): 1-9, 2017

13 윤현민, "데이터마이닝을 활용한 해군함정 수리부속 수요예측" 한국산업경영시스템학회 40 (40): 253-259, 2017

14 전성현, "데이터마이닝을 이용한 박스오피스 예측" 한국통계학회 29 (29): 1257-1270, 2016

15 Liu, Y., "Word of mouth for movies : its dynamics and impact on box office revenue" 70 : 74-89, 2006

16 Setiawan, A., "Very short-term electricity load demand forecasting using support vector regression" 2888-2894, 2009

17 Simoncini, M., "Vehicle classification from low-frequency GPS data with recurrent neural networks" 91 : 176-191, 2018

18 Sun, X., "Using a Grey-Markov model optimized by Cuckoo search algorithm to forecast the annual foreign tourist arrivals to China" 52 : 369-379, 2016

19 Ji, G., "Urban water demand forecasting by LS-SVM with tuning based on elitist teaching-learning-based optimization" 3997-4002, 2014

20 Tiwari, M. K., "Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models" 49 : 6486-6507, 2013

21 Abrahart, R. J., "Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting" 36 : 480-512, 2012

22 Kim, J., "Trends and Success Cases of Big Data in Korea and abroad" 23 : 47-52, 2016

23 Hinton, G. E., "Training products of experts by minimizing contrastive divergence" 14 : 1771-1800, 2002

24 Schapire, R. E., "The strength of weak learnability" 5 : 197-227, 1990

25 Xu, C., "The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets" 95 : 47-60, 2018

26 Wu, Q., "The forecasting model based on wavelet -support vector machine" 36 : 7604-7610, 2009

27 Chintagunta, P. K., "The effects of online user reviews on movie box office performance : Accounting for sequential rollout and aggregation across local markets" 29 : 944-957, 2010

28 Pai, P. F., "The application of support vector machines to forecast tourist arrivals in Barbados : an empirical study" 23 : 375-385, 2006

29 Sen, A., "The US fashion industry : a supply chain review" 114 : 571-593, 2008

30 Lee, J., "The Jeonse price forecasting used by news big data" Korea Real Estate Academy 43-57, 2017

31 Cortes, C., "Support-vector networks" 20 : 273-297, 1995

32 Chen, K. Y., "Support vector regression with genetic algorithms in forecasting tourism demand" 28 : 215-226, 2007

33 이형로, "Support Vector Regression에 기반한 전력 수요 예측" 대한산업공학회 24 (24): 351-361, 2011

34 Friedman, J. H., "Stochastic gradient boosting" 38 : 367-378, 2002

35 Lolli, F., "Single-hidden layer neural networks for forecasting intermittent demand" 183 : 116-128, 2017

36 Kong, W., "Short-term residential load forecasting based on resident behaviour learning" 33 : 1087-1088, 2017

37 Kong, W., "Short-term residential load forecasting based on LSTM recurrent neural network" 10 : 841-851, 2017

38 Fan, S., "Short-term load forecasting based on an adaptive hybrid method" 21 : 392-401, 2006

39 Ramanathan, R., "Short-run forecasts of electricity loads and peaks" 13 : 161-174, 1997

40 Ansuj, A. P., "Sales forecasting using time series and neural networks" 31 : 421-424, 1996

41 Sun, Z. L., "Sales forecasting using extreme learning machine with applications in fashion retailing" 46 : 411-419, 2008

42 Hong, W. C., "SVR with hybrid chaotic genetic algorithms for tourism demand forecasting" 11 : 1881-1890, 2011

43 Kim, T., "Residential energy consumption prediction using CNN-LSTM neural network based on particle swarm optimization" The Korean Institute of Information Scientists and Engineers 737-739, 2018

44 Hinton, G. E., "Reducing the dimensionality of data with neural networks" 313 : 504-507, 2006

45 Fischer, A., "Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications" Springer 14-36, 2012

46 Regue, R., "Proactive vehicle routing with inferred demand to solve the bikesharing rebalancing problem" 72 : 192-209, 2014

47 Song, H., "Predicting tourist demand using big data, Analytics in Smart Tourism Design" 13-29, 2017

48 Wang, C. H., "Predicting tourism demand using fuzzy time series and hybrid grey theory" 25 : 367-374, 2004

49 Hu, Y. C., "Predicting foreign tourists for the tourism industry using soft computing-based Grey-Markov models" 9 : 1228-, 2017

50 Rahman, A., "Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks" 212 : 372-385, 2018

51 Lee, H., "Pre-launch new product demand forecasting using the Bass model : a statistical and machine learning-based approach" 86 : 49-64, 2014

52 Shalev-Shwartz, S., "Online learning and online convex optimization" 4 : 107-194, 2012

53 Voitcu, O., "On the construction of a nonlinear recursive predictor" 190 : 393-407, 2006

54 Lopez Farias, R., "Multi-model prediction for demand forecast in water distribution networks" 11 : 660-, 2018

55 Orozco, B. P., "Mordred: Memory-based ordinal regression deep neural networks for time series forecasting"

56 Taylor, G. W., "Modeling human motion using binary latent variables" 1345-1352, 2007

57 Tiwari, M. K., "Medium-term urban water demand forecasting with limited data using an ensemble wavelet-bootstrap machine-learning approach" 141 : 04014053-, 2014

58 Bajari, P., "Machine learning methods for demand estimation" 105 : 481-485, 2015

59 Hochreiter, S., "Long short-term memory" 9 : 1735-1780, 1997

60 Scholkopf, B., "Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond" MIT press 2002

61 Lu, R., "Incentive-based demand response for smart grid with reinforcement learning and deep neural network" 236 : 937-949, 2019

62 Brentan, B. M., "Hybrid regression model for near real-time urban water demand forecasting" 309 : 532-541, 2017

63 Friedman, J. H., "Greedy function approximation : a gradient boosting machine" 29 : 1189-1232, 2001

64 김보경, "GLS와 Bass 모형을 결합한 하이브리드 모형을 이용한 영화 관객 수 예측" 한국통계학회 31 (31): 447-461, 2018

65 Pal, A., "Free-floating bike sharing : solving real-life large-scale static rebalancing problems" 80 : 92-116, 2017

66 Parry, M. E., "Forecasting new product adoption with probabilistic neural networks" 28 (28): 78-88, 2011

67 Kaytez, F., "Forecasting electricity consumption : a comparison of regression analysis, neural networks and least squares support vector machines" 67 : 431-438, 2015

68 Croston, J. D., "Forecasting and stock control for intermittent demands" 23 : 289-303, 1972

69 Huang, G. B., "Extreme learning machine : a new learning scheme of feedforward neural networks" 2 : 985-990, 2004

70 Duan, K., "Evaluation of simple performance measures for tuning SVM hyperparameters" 51 : 41-59, 2003

71 Park, J., "Evaluation of demand power prediction performance based on deep learning algorithm and data preprocessing" The Korean Institute of Information Scientists and Engineers 1882-1884, 2017

72 Xia, C., "Electric load forecasting using virtual instrument based on dynamic recurrent Elman neural network" IEEE 1-4, 2012

73 Jegede, C. A., "Effects of automated teller machine on the performance of nigerian banks" 2 : 40-46, 2014

74 Hsu, C. C., "Dynamically optimizing parameters in support vector regression: an application of electricity load forecasting" IEEE 2 : 30c-30c, 2006

75 Chu, B. S., "Dynamic cubic neural network with demand momentum for new product sales forecasting" 14 : 1171-1182, 2011

76 Ghods, L., "Different methods of long-term electric load demand forecasting; a comprehensive review" 7 : 249-259, 2011

77 Apostolopoulos, P. A., "Demand response management in smart grid networks: a two-stage game-theoretic learning-based approach" Mobile Networks and Applications 1-14, 2018

78 Nenni, M. E., "Demand forecasting in the fashion industry a review" 5 : 37-, 2013

79 Amirkolaii, K. N., "Demand forecasting for irregular demands in business aircraft spare parts supply chains by using artificial intelligence(AI)" 50 : 15221-15226, 2017

80 Mocanu, E., "Demand forecasting at low aggregation levels using factored conditional restricted Boltzmann machine" 1-7, 2016

81 Wang, D., "DeepSD: supply-demand prediction for online car-hailing services using deep neural networks" 243-254, 2017

82 Yao, H., "Deep multi-view spatial-temporal network for taxi demand prediction" 2018

83 Shi, H., "Deep learning for household load forecasting?a novel pooling deep RNN" 9 : 5271-5280, 2017

84 Mocanu, E., "Deep learning for estimating building energy consumption, Sustainable Energy" 6 : 91-99, 2016

85 Anbazhagan, S., "Day-ahead deregulated electricity market price forecasting using recurrent neural network" 7 : 866-872, 2012

86 Mnih, V., "Conditional restricted Boltzmann machines for structured output prediction"

87 Mocanu, E., "Comparison of machine learning methods for estimating energy consumption in buildings" 1-6, 2014

88 Venkatesh, K., "Cash demand forecasting in ATMs by clustering and neural networks" 232 : 383-392, 2014

89 Simutis, R., "Cash demand forecasting for ATM using neural networks and support vector regression algorithms" 416-421, 2008

90 Marino, D. L., "Building energy load forecasting using deep neural networks" 7046-7051, 2016

91 Buhlmann, P., "Boosting with the L2 loss : regression and classification" 98 : 324-339, 2003

92 Freund, Y., "Boosting a weak learning algorithm by majority" 121 : 256-285, 1995

93 Bier, I. J., "Boeing commercial airplane group spares department: simulation of spare parts operations" 1984

94 Chen, M., "Big data: Related Technologies, Challenges and Future Prospects" Springer 2014

95 Msiza, I. S., "Artificial neural networks and support vector machines for water demand time series forecasting" 638-643, 2007

96 Chae, Y. T., "Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings" 111 : 184-194, 2016

97 Nam, S., "Applying text mining and deep learning method to analyzing movie scenarios and predicting the performance" The Korea Society of Information Technology Service 515-518, 2017

98 Singh, A. K., "An overview of electricity demand forecasting techniques" 3 : 38-48, 2013

99 Pai, P., "An improved neural network model in forecasting arrivals" 32 : 1138-1141, 2005

100 Tiwari, M. K., "An ensemble wavelet bootstrap machine learning approach to water demand forecasting : a case study in the city of Calgary, Canada" 14 : 185-201, 2017

101 Holland, J. H., "Adaptation in Natural and Arti cial Systems: An Introductory Analysis with Applications to Biology, Control, and Arti cial Intelligence" MIT Press 1992

102 Boser, B. E., "A training algorithm for optimal margin classifiers" 36 : 144-152, 1992

103 Gil, S., "A study on the method of energy demand prediction using deep learning" 1014-1015, 2016

104 Liu, Y., "A static free-floating bike repositioning problem with multiple heterogeneous vehicles, multiple depots, and multiple visits" 92 : 208-242, 2018

105 Wu, Q., "A sparse Gaussian process regression model for tourism demand forecasting in Hong Kong" 39 : 4769-4774, 2012

106 Wang, Z., "A review of artificial intelligence based building energy use prediction : contrasting the capabilities of single and ensemble prediction models" 75 : 796-808, 2017

107 Chen, K., "A novel data-driven approach for residential electricity consumption prediction based on ensemble learning" 150 : 49-60, 2018

108 Thomassey, S., "A neural clustering and classification system for sales forecasting of new apparel items" 7 : 1177-1187, 2007

109 Jung, G., "A modified bootstrap method for intermittent demand forecasting for rare spare parts" 24 : 245-254, 2017

110 Wu, Q., "A hybrid-forecasting model based on Gaussian support vector machine and chaotic particle swarm optimization" 37 : 2388-2394, 2010

111 Hua, Z., "A hybrid support vector machines and logistic regression approach for forecasting intermittent demand of spare parts" 181 : 1035-1048, 2006

112 Mayrink, V., "A hybrid method using exponential smoothing and gradient boosting for electrical short-term load forecasting" 1-6, 2016

113 Wong, W. K., "A hybrid intelligent model for medium-term sales forecasting in fashion retail supply chains using extreme learning machine and harmony search algorithm" 128 : 614-624, 2010

114 Yuan, X., "A hybrid chaotic genetic algorithm for short-term hydro system scheduling" 59 : 319-327, 2002

115 Taieb, S. B., "A gradient boosting approach to the Kaggle load forecasting competition" 30 : 382-394, 2014

116 Frank, C., "A fuzzy forecasting model for women’s casual sales" National Textile Center 2004

117 Ai, Y., "A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system" 31 : 1665-1677, 2019

118 Lipton, Z. C., "A critical review of recurrent neural networks for sequence learning"

119 Chu, C. W., "A comparative study of linear and nonlinear models for aggregate retail sales forecasting" 86 : 217-231, 2003

120 Bergman, J. J., "A Bayesian approach to demand forecasting for new equipment programs" 47 : 17-21, 2017