A Novel Ensemble Neuro-Fuzzy Model for Financial Time Series Forecasting

Vlasenko, Alexander; Vlasenko, Nataliia; Vynokurova, Olena; Bodyanskiy, Yevgeniy; Peleshko, Dmytro

doi:10.3390/data4030126

Cited by 19 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study inferred that the GD required low time to optimize the phase-only CGH distribution and provided higher-precision images compared to the Gerchberg-Saxton (GS) algorithm. Next, researchers in [32] used the GD method to optimize the vector centers of the consequent layer functions and receptive field matrices in a neuro-fuzzy model based on the standard criterion of mean square error. Furthermore, GD was also used by [33] for minimizing the equation of error used in the study by updating the W 1 and W 2 matrices in order to solve the predicting student performance (PSP) problem.…”

Section: Gradient Descentmentioning

confidence: 99%

A Novel Methodology for Hydrocarbon Depth Prediction in Seabed Logging: Gaussian Process-Based Inverse Modeling of Electromagnetic Data

et al. 2021

View full text Add to dashboard Cite

Seabed logging (SBL) is an application of electromagnetic (EM) waves for detecting potential marine hydrocarbon-saturated reservoirs reliant on a source–receiver system. One of the concerns in modeling and inversion of the EM data is associated with the need for realistic representation of complex geo-electrical models. Concurrently, the corresponding algorithms of forward modeling should be robustly efficient with low computational effort for repeated use of the inversion. This work proposes a new inversion methodology which consists of two frameworks, namely Gaussian process (GP), which allows a greater flexibility in modeling a variety of EM responses, and gradient descent (GD) for finding the best minimizer (i.e., hydrocarbon depth). Computer simulation technology (CST), which uses finite element (FE), was exploited to generate prior EM responses for the GP to evaluate EM profiles at “untried” depths. Then, GD was used to minimize the mean squared error (MSE) where GP acts as its forward model. Acquiring EM responses using mesh-based algorithms is a time-consuming task. Thus, this work compared the time taken by the CST and GP in evaluating the EM profiles. For the accuracy and performance, the GP model was compared with EM responses modeled by the FE, and percentage error between the estimate and “untried” computer input was calculated. The results indicate that GP-based inverse modeling can efficiently predict the hydrocarbon depth in the SBL.

show abstract

Section: Gradient Descentmentioning

confidence: 99%

A Novel Methodology for Hydrocarbon Depth Prediction in Seabed Logging: Gaussian Process-Based Inverse Modeling of Electromagnetic Data

et al. 2021

View full text Add to dashboard Cite

show abstract

“…GD is a well-known method that is commonly used in optimization problems, such as in the applications of machine learning. Researchers in Reference [33] exercised the GD for the purpose of optimizing the vector centers of the consequent layer functions and receptive field matrices in a neuro-fuzzy model. This study relied on the mean squared error (MSE) criterion as its standard of the optimization.…”

Section: Gradient Descentmentioning

confidence: 99%

Stochastic Process-Based Inversion of Electromagnetic Data for Hydrocarbon Resistivity Estimation in Seabed Logging

et al. 2021

View full text Add to dashboard Cite

This work proposes a stochastic process-based inversion to estimate hydrocarbon resistivity based on multifrequency electromagnetic (EM) data. Currently, mesh-based algorithms are used for processing the EM responses which cause high time-consuming and unable to quantify uncertainty. Gaussian process (GP) is utilized as the alternative forward modeling approach to evaluate the EM profiles with uncertainty quantification. For the optimization, gradient descent is used to find the optimum by minimizing its loss function. The prior EM profiles are evaluated using finite element (FE) through computer simulation technology (CST) software. For validation purposes, mean squared deviation and its root between EM profiles evaluated by the GP and FE at the unobserved resistivities are computed. Time taken for the GP and CST to evaluate the EM profiles is compared, and absolute error between the estimate and its simulation input is also computed. All the resulting deviations were significantly small, and the GP took lesser time to evaluate the EM profiles compared to the software. The observational datasets also lied within the 95% confidence interval (CI) where the resistivity inputs were estimated by the proposed inversion. This indicates the stochastic process-based inversion can effectively estimate the hydrocarbon resistivity in the seabed logging.

show abstract

“…Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance [10,42], transportation [17,44], health care [6,47], and power systems [3,34]. A major problem in TSF is that models often do not perform well over long time periods due to changing distributions between their original training data and new inference data, as the properties or important features of the data change over time [18].…”

Section: Introductionmentioning

confidence: 99%

ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting

Lyu¹,

Desell²

2022

Preprint

View full text Add to dashboard Cite

Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance, transportation, health care, and power systems. However, real-world utilization of machine learning (ML) models for TSF suffers due to pretrained models being able to learn and adapt to unpredictable patterns as previously unseen data arrives over longer time scales. To address this, models must be periodically retained or redesigned, which takes significant human and computational resources. This work presents the Online NeuroEvolution based Neural Architecture Search (ONE-NAS) algorithm, which to the authors' knowledge is the first neural architecture search algorithm capable of automatically designing and training new recurrent neural networks (RNNs) in an online setting. Without any pretraining, ONE-NAS utilizes populations of RNNs which are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world large-scale multivariate wind turbine data as well a univariate Dow Jones Industrial Average (DJIA) dataset, and is shown to outperform traditional statistical time series forecasting, including naive, moving average, and exponential smoothing methods, as well as state of the art online ARIMA strategies. CCS CONCEPTS• Theory of computation → Online algorithms; • Computing methodologies → Neural networks; • Applied computing → Forecasting.

show abstract

A Novel Ensemble Neuro-Fuzzy Model for Financial Time Series Forecasting

Cited by 19 publications

References 25 publications

A Novel Methodology for Hydrocarbon Depth Prediction in Seabed Logging: Gaussian Process-Based Inverse Modeling of Electromagnetic Data

A Novel Methodology for Hydrocarbon Depth Prediction in Seabed Logging: Gaussian Process-Based Inverse Modeling of Electromagnetic Data

Stochastic Process-Based Inversion of Electromagnetic Data for Hydrocarbon Resistivity Estimation in Seabed Logging

ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting

Contact Info

Product

Resources

About