Impact of Data Normalization on Deep Neural Network for Time Series Forecasting

For the last few years it has been observed that the Deep Neural Networks (DNNs) has achieved an excellent success in image classification, speech recognition. But DNNs are suffer great deal of challenges for time series forecasting because most of the time series data are nonlinear in nature and highly dynamic in behaviour. The time series forecasting has a great impact on our socio-economic environment. Hence, to deal with these challenges its need to be redefined the DNN model and keeping this in mind, data pre-processing, network architecture and network parameters are need to be consider before feeding the data into DNN models. Data normalization is the basic data pre-processing technique form which learning is to be done. The effectiveness of time series forecasting is heavily depend on the data normalization technique. In this paper, different normalization methods are used on time series data before feeding the data into the DNN model and we try to find out the impact of each normalization technique on DNN to forecast the time series. Here the Deep Recurrent Neural Network (DRNN) is used to predict the closing index of Bombay Stock Exchange (BSE) and New York Stock Exchange (NYSE) by using BSE and NYSE time series data.

[1]  B. Misra,et al.  Impact of Data Normalization on Stock Index Forecasting , 2013 .

[2]  Yew-Soon Ong,et al.  Deep transfer learning for classification of time-delayed Gaussian networks , 2015, Signal Process..

[3]  Majid Vafaei Jahan,et al.  Stock market prediction with Hidden Markov Model , 2015, 2015 International Congress on Technology, Communication and Knowledge (ICTCK).

[4]  Lyubka A. Doukovska,et al.  Design and application of Artificial Neural Networks for predicting the values of indexes on the Bulgarian Stock market , 2013, 2013 Signal Processing Symposium (SPS).

[5]  R. K. Agrawal,et al.  An Introductory Study on Time Series Modeling and Forecasting , 2013, ArXiv.

[6]  Fangwen Zhai,et al.  Hybrid forecasting model research on stock data mining , 2010, 4th International Conference on New Trends in Information Science and Service Science.

[7]  Tian-Shyug Lee,et al.  Investigating the information content of non-cash-trading index futures using neural networks , 2002, Expert Syst. Appl..

[8]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[9]  Thomas Villmann,et al.  Fusion of deep learning architectures, multilayer feedforward networks and learning vector quantizers for deep classification learning , 2017, 2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM).

[10]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[11]  Qi Tang,et al.  Day-Ahead Electricity Prices Forecasting Using Artificial Neural Networks , 2009, 2009 International Conference on Artificial Intelligence and Computational Intelligence.

[12]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[13]  Chih-Ming Hsu,et al.  Forecasting stock/futures prices by using neural networks with feature selection , 2011, 2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference.

[14]  Stelios D. Bekiros,et al.  Sign Prediction and Volatility Dynamics With Hybrid Neurofuzzy Approaches , 2011, IEEE Transactions on Neural Networks.