Modelling Nonlinear Nonstationary Processes in Macroeconomy and Finances

Bidyuk, Petro I.; Prosyankina-Zharova, Tetyana; Терентьєв, Олександр Миколайович

doi:10.1007/978-3-319-91008-6_72

Cited by 5 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classical methods of autoregression with moving average (ARMA) [1,2] are used to analyze and predict stationary time series. Autoregressive models with integrated moving average (ARIMA) [1,3], heteroskedastic (ARCH/GARCH) [1,4,5] and other [6] are designed to analyze a wider class of nonstationary processes. GARCH models, in particular, help to provide the volatility analysis of financial time series [7].…”

Section: Introductionmentioning

confidence: 99%

Generative time series model based on encoder-decoder architecture

Nedashkovskaya

Androsov

2022

SRIT

View full text Add to dashboard Cite

Encoder-decoder neural network models have found widespread use in recent years for solving various machine learning problems. In this paper, we investigate the variety of such models, including the sparse, denoising and variational autoencoders. To predict non-stationary time series, a generative model is presented and tested, which is based on a variational autoencoder, GRU recurrent networks, and uses elements of neural ordinary differential equations. Based on the constructed model, the system is implemented in the Python3 environment, the TensorFlow2 framework and the Keras library. The developed system can be used for modeling continuous time-dependent processes. The system minimizes a human factor in the process of time series analysis, and presents a high-level modern interface for fast and convenient construction and training of deep models.

show abstract

Section: Introductionmentioning

confidence: 99%