시계열 분해 및 데이터 증강 기법 활용 건화물운임지수 예측
Forecasting Baltic Dry Index by Implementing Time-Series Decomposition and Data Augmentation Techniques
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t + 1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.
Abstract
Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t + 1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.
참고문헌 (23)
- Abdollahi, H., "A novel hybrid model for forecasting crude oil price based on time series decomposition", Applied energy, 267, pp.115035~ (2020)
- Allaire, JJ., "Package ‘keras’. R Interface to 'Keras'", ~ (2022)
- Allaire, JJ., "Package ‘tensorflow’. R Interface to 'TensorFlow'", ~ (2022)
- Benkachcha, S, "Seasonal time series forecasting models based on artificial neural network", International Journal of Computer Applications, 116(20) (2015)
- Cleveland, R. B., "STL: A seasonal-trend decomposition", J. Off. Stat, 6(1), pp.3~73 (1990)
- Demir, S., "Data augmentation for time series regression : Applying transformations, autoencoders and adversarial networks to electricity price forecasting", Applied Energy, 304, pp.117695~ (2021)
- Fritsch, S., "Training of Neural Networks" (2019)
- Gers, F. A., "Neural Nets WIRN Vietri-01", pp.193~200 (2002), Springer
- Hafen, R., "Package ‘stlplus’. Ehanced Seasonal Decomposition of Time Series by Loess", ~ (2016)
- 한민수, "Long Short-Term Memory를 활용한 건화물운임지수 예측", 품질경영학회지, 47(3), pp.497~508 (2019), 한국품질경영학회[DOI]
- Hansen, J. V., "Forecasting and recombining time-series components by using neural networks", Journal of the Operational Research Society, 54(3), pp.307~317 (2003)
- Iwana, B. K., "An empirical survey of data augmentation for time series classification with neural networks", Plos one, 16(7), pp.e0254841~ (2021)
- 강수람, "Attention 기반 Encoder-Decoder 모델을 활용한 작물의 생산량 예측", 품질경영학회지, 49(4), pp.569~579 (2021), 한국품질경영학회[DOI]
- Khandelwal, I., "Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition", Procedia Computer Science, 48, pp.173~179 (2015)
- Lee, S. W., "Stock market forecasting with super-high dimensional time-series data using ConvLSTM, trend sampling, and specialized data augmentation", Expert Systems with Applications, 161, pp.113704~ (2020)
- Lin, Y, "SSDNet: State space decomposition neural network for time series forecasting", 2021 IEEE International Conference on Data Mining (ICDM), pp.370~378 (2021), IEEE
- Méndez-Jiménez, I., "Time series decomposition for improving the forecasting performance of convolutional neural networks", Conference of the Spanish Association for Artificial Intelligence, pp.87~97 (2018), Springer
- Oh, C., "Time-series data augmentation based on interpolation", Procedia Computer Science, 175, pp.64~71 (2020)
- Oliveira, D. D., "Forecasting vehicular traffic flow using MLP and LSTM", Neural Computing and applications, 33(24), pp.17245~17256 (2021)
- Ouyang, Z., "STL Decomposition of Time Series Can Benefit Forecasting Done by Statistical Methods but Not by Machine Learning Ones", Engineering Proceedings, 5(1), pp.42~ (2021)
- Quast, B., "Recurrent Nerual Network" (2022)
- Wen, Q., "Time series data augmentation for deep learning : A survey", arXiv preprint arXiv:2002.12478, ~ (2020)
- Zhang, G. P, "Time series forecasting using a hybrid ARIMA and neural network model", Neurocomputing, 50, pp.159~175 (2003)