Neural Network Data Preprocessing: Is It Necessary For Time Series Forecasting?

Yıl 2017, Cilt: 9 Sayı: 17, 147 - 154, 27.11.2017

Hakan Pabuçcu

https://doi.org/10.20990/kilisiibfakademik.329247

Öz

Neural networks (NNs) are a commonly used method to solve the time series-forecasting problem. NNs have some advantages compared with traditional forecasting models, such as auto regressive moving average or auto regressive integrated moving average. NNs do not need to have any statistical assumption like normal distribution. However, data preprocessing, normalization, trend adjusting, seasonal adjusting, or both differencing can introduce better results in some studies. In this study, we have tried to investigate whether data preprocessing methods are useful for time series data, which contains trend, seasonality, or unit root. For this purpose, we collected the real time series data belonging to monthly or quarterly figures and used nonlinear autoregressive (NAR) and multilayer perceptron (MLP) models. Although we obtained significant differences between data preprocessing methods, the structure of MLP with differenced variable produced the worst results.

Anahtar Kelimeler

data preprocessing, neural networks, time series forecasting

NEURAL NETWORK DATA PREPROCESSING: IS IT NECESSARY FOR TIME SERIES FORECASTING?

Öz

Neural
networks (NNs) are a commonly used method to solve the time series-forecasting
problem. NNs have some advantages compared with traditional forecasting models,
such as auto regressive moving average or auto regressive integrated moving
average. NNs do not need to have any statistical assumption like normal
distribution. However, data preprocessing, normalization, trend adjusting,
seasonal adjusting, or both differencing can introduce better results in some
studies. In this study, we have tried to investigate whether data preprocessing
methods are useful for time series data, which contains trend, seasonality, or
unit root. For this purpose, we collected the real time series data belonging
to monthly or quarterly figures and used nonlinear autoregressive (NAR) and
multilayer perceptron (MLP) models. Although we obtained significant
differences between data preprocessing methods, the structure of MLP with
differenced variable produced the worst results.

Anahtar Kelimeler

data preprocessing, neural networks, time series forecasting

Kaynakça

• Alon, I., Qi, M., & Sadowski, R. J. (2001). Forecasting aggregate retail sales: Journal of Retailing and Consumer Services, 8(3), 147–156. http://doi.org/http://dx.doi.org/10.1016/S0969-6989(00)00011-4
• Bishop, C. M. (1995). Neural networks for pattern recognition. New York, NY: Oxford University Press.
• Findley, D. F., Monsell, B. C., Bell, W. R., Otto, M. C., & Chen, B.-C. (1998). New Capabilities and Methods of the X-12-ARIMA Seasonal-Adjustment Program. Journal of Business & Economic Statistics, 16(2), 127–152. http://doi.org/10.1080/07350015.1998.10524743
• Ghysels, E., Granger, C. W. J., & Siklos, P. L. (1996). Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process? Journal of Business & Economic Statistics, 14(3), 374–386. http://doi.org/10.1080/07350015.1996.10524663
• Gorr, W. L. (1994). Editorial: Research prospective on neural network forecasting. International Journal of Forecasting, 10(1), 1–4. http://doi.org/http://dx.doi.org/10.1016/0169-2070(94)90044-2
• Hamzaçebi, C. (2008). Improving artificial neural networks’ performance in seasonal time series forecasting. Information Sciences, 178(23), 4550–4559. http://doi.org/http://dx.doi.org/10.1016/j.ins.2008.07.024
• Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. http://doi.org/http://dx.doi.org/10.1016/0893-6080(89)90020-8
• Hylleberg, S. (1992). Modelling seasonality (1st ed.). Oxford: Oxford University Press.
• Makridakis, S., Andersen, A., Carbone, R., Fildes, R., Hibon, M., Lewandowski, R., … Winkler, R. (1982). The accuracy of extrapolation (time series) methods: Results of a forecasting competition. Journal of Forecasting, 1(2), 111–153. http://doi.org/10.1002/for.3980010202
• Nelson, M., Hill, T., Remus, W., & O’Connor, M. (1999). Time series forecasting using neural networks: should the data be deseasonalized first? Journal of Forecasting, 18(5), 359–367. http://doi.org/10.1002/(SICI)1099-131X(199909)18:5<359::AID-FOR746>3.0.CO;2-P
• Öztemel, E. (2006). Yapay Sinir Ağları (2nd ed.). İatanbul: Papatya Yayıncılık.
• Ripley, B. D. (1996). Pattern recognition and neural networks. http://doi.org/http://dx.doi.org/10.1017/cbo9780511812651
• Sharda, R., & Patil, R. B. (1992). Connectionist approach to time series prediction: an empirical test. Journal of Intelligent Manufacturing, 3(5), 317–323. http://doi.org/10.1007/BF01577272
• Yegnanarayana, B. (2005). Artificial Neural Networks (11th ed.). New Delhi: Prentice-Hall of lndia Private Limited.
• Zhang, G. P., & Kline, D. M. (2007). Quarterly time-series forecasting with neural networks. IEEE Transactions on Neural Networks, 18(6), 1800–1814. http://doi.org/10.1109/TNN.2007.896859
• Zhang, G. P., & Qi, M. (2005). Neural network forecasting for seasonal and trend time series. European Journal of Operational Research, 160, 501–514. http://doi.org/10.1016/j.ejor.2003.08.037