Smoothing and stationarity enforcement framework for deep learning time-series forecasting

Time-series analysis and forecasting problems are generally considered as some of the most challenging and complicated problems in data mining. In this work, we propose a new complete framework for enhancing deep learning time-series models, which is based on a data preprocessing methodology. The proposed framework focuses on conducting a sequence of transformations on the original low-quality time-series data for generating high-quality time-series data, “suitable” for efficiently training and fitting a deep learning model. These transformations are performed in two successive stages: The first stage is based on the smoothing technique for the development of a new de-noised version of the original series in which every value contains dynamic knowledge of the all previous values. The second stage of transformations is performed on the smoothed series and it is based on differencing the series in order to be stationary and be considerably easier fitted and analyzed by a deep learning model. A number of experiments were performed utilizing time-series datasets from the cryptocurrency market, energy sector and financial stock market application domains on both regression and classification problems. The comprehensive numerical experiments and statistical analysis provide empirical evidence that the proposed framework considerably improves the forecasting performance of a deep learning model.

[1]  Mike West,et al.  Probabilistic forecasting of heterogeneous consumer transaction–sales time series , 2018, International Journal of Forecasting.

[2]  Vladimir Stojanovic,et al.  A Nature Inspired Parameter Tuning Approach to Cascade Control for Hydraulically Driven Parallel Robot Platform , 2016, J. Optim. Theory Appl..

[3]  Jun Wang,et al.  Forecasting neural network model with novel CID learning rate and EEMD algorithms on energy market , 2018, Neurocomputing.

[4]  W. Enders.  Applied Econometric Time Series , 1994 .

[5]  Timo Teräsvirta,et al.  Smooth transition autoregressive models - A survey of recent developments , 2000 .

[6]  Ioannis E. Livieris,et al.  A novel validation framework to enhance deep learning models in time-series forecasting , 2020, Neural Computing and Applications.

[7]  Eric R. Ziegel,et al.  Analysis of Financial Time Series , 2002, Technometrics.

[8]  Konstantinos Demertzis,et al.  Modeling and Forecasting the COVID-19 Temporal Spread in Greece: An Exploratory Approach Based on Complex Network Defined Splines , 2020, International journal of environmental research and public health.

[9]  Autoregressive Moving-Average Models , 2016 .

[10]  R. Shanmugam.  Introduction to Time Series and Forecasting , 1997 .

[11]  Giuseppe Nunnari,et al.  Forecasting Monthly Sales Retail Time Series: A Case Study , 2017, 2017 IEEE 19th Conference on Business Informatics (CBI).

[12]  Zhengqiang Zhang,et al.  Event-based fuzzy control for T-S fuzzy networked systems with various data missing , 2020, Neurocomputing.

[13]  Panayiotis E. Pintelas,et al.  Forecasting stock price index movement using a constrained deep neural network training algorithm , 2020, Intell. Decis. Technol..

[14]  P. Tkachenko,et al.  Stacking-based GRNN-SGTM Ensemble Model for Prediction Tasks , 2020, 2020 International Conference on Decision Aid Sciences and Application (DASA).

[15]  Fan Zhang,et al.  A review on time series forecasting techniques for building energy consumption , 2017 .

[16]  Derya Birant,et al.  Stock Market Forecasting Using Machine Learning Models , 2019, 2019 Innovations in Intelligent Systems and Applications Conference (ASYU).

[17]  Christophe Mues,et al.  An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market , 2016, Eur. J. Oper. Res..

[18]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[19]  J. L. Hodges,et al.  Rank Methods for Combination of Independent Experiments in Analysis of Variance , 1962 .

[20]  Ruey S. Tsay,et al.  Analysis of Financial Time Series: Tsay/Analysis of Financial Time Series , 2005 .

[21]  George Athanasopoulos,et al.  Forecasting: principles and practice , 2013 .

[22]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[23]  Autoregressive Moving Average Processes (ARMA) , 2016 .

[24]  H. Finner.  On a Monotonicity Problem in Step-Down Multiple Test Procedures , 1993 .

[25]  Mirco Fabbri,et al.  Dow Jones Trading with Deep Learning: The Unreasonable Effectiveness of Recurrent Neural Networks , 2018, DATA.

[26]  Ivan Izonin,et al.  An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data based on the GRNN-SGTM Ensemble † , 2020, Sensors.

[27]  Peng Wang,et al.  An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks , 2020, J. Frankl. Inst..

[28]  Wei Shang,et al.  Text-based crude oil price forecasting: A deep learning approach , 2019, International Journal of Forecasting.

[29]  Vladimir Stojanovic,et al.  Robust identification for fault detection in the presence of non-Gaussian noises: application to hydraulic servo drives , 2020 .

[30]  Ioannis E. Livieris,et al.  An Advanced Deep Learning Model for Short-Term Forecasting U.S. Natural Gas Price and Movement , 2020, AIAI Workshops.

[31]  Enrique Benavides Rosales,et al.  Time-series and cross-sectional momentum and contrarian strategies within the commodity futures markets , 2017 .

[32]  Mohammad Sohel Rahman,et al.  An approach to predict and forecast the price of constituents and index of cryptocurrency using machine learning , 2019, Physica A: Statistical Mechanics and its Applications.

[33]  M. Hashem Pesaran,et al.  Time Series and Panel Data Econometrics , 2015 .

[34]  Ivan Izonin,et al.  Hybridization of the SGTM Neural-Like Structure Through Inputs Polynomial Extension , 2018, 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP).

[35]  Murat Kulahci,et al.  Introduction to Time Series Analysis and Forecasting , 2008 .

[36]  Vladimir Stojanovic,et al.  Robust fault detection filter design for a class of discrete‐time conic‐type non‐linear Markov jump systems with jump fault signals , 2020, IET Control Theory & Applications.

[37]  Theodore Kotsilieris,et al.  Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach , 2020, AIAI.

[38]  P. Mantalos,et al.  Forecasting ARMA models: a comparative study of information criteria focusing on MDIC , 2010 .

[39]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[40]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[41]  Siu Cheung Hui,et al.  Multi-Cast Attention Networks , 2018, KDD.