Forecasting Daily Forex Using Large Dimensional Vector Autoregression with Time-Varying Parameters

Taveeapiradeecharoen, Paponpat; Jongsureyapart, Chatrudee; Aunsri, Nattapol

doi:10.1109/gws.2018.8686610

Cited by 8 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study uses and combines them as described in many papers (Mikhaylov et al 2022;Shaikh et al 2022). As for methodology literature, the major areas for time-varying parameter (TVP) regression with the Kalman filter are the dynamics of the volatility skew; impacts of factor price changes and technological progress on energy intensity; the time-varying parameter vector autoregressive model for economy and monetary policy; financial time series analysis in ecofriendly computing and communication systems; daily currency forecasting; and the price elasticity of electricity (Primiceri 2005;Marcellino et al 2006;Koop et al 2009;Bedendo and Hodges 2009;Nakajima et al 2011, Rajan et al 2012, Taveeapiradeecharoen et al 2018Tiwari and Menegaki 2019;Taveeapiradeecharoen and Aunsri 2020;Cooke 2020).…”

Section: Golden Cut Q-rung Orthopair Fuzzy Multicriteria Decision-mak...mentioning

confidence: 99%

Market capitalization shock effects on open innovation models in e-commerce: golden cut q-rung orthopair fuzzy multicriteria decision-making analysis

et al. 2023

View full text Add to dashboard Cite

This research paper analyzes revenue trends in e-commerce, a sector with an annual sales volume of more than 340 billion dollars. The article evaluates, despite a scarcity of data, the effects on e-commerce development of the ubiquitous lockdowns and restriction measures introduced by most countries during the pandemic period. The analysis covers monthly data from January 1996 to February 2021. The research paper analyzes relative changes in the original time series through the autocorrelation function. The objects of this analysis are Amazon and Alibaba, as they are benchmarks in the e-commerce industry. This paper tests the shock effect on the e-commerce companies Alibaba in China and Amazon in the USA, concluding that it is weaker for companies with small market capitalizations. As a result, the effect on estimated e-trade volume in the USA was approximately 35% in 2020. Another evaluation considers fuzzy decision-making methodology. For this purpose, balanced scorecard-based open financial innovation models for the e-commerce industry are weighted with multistepwise weight assessment ratio analysis based on q-rung orthopair fuzzy sets and the golden cut. Within this framework, a detailed analysis of competitors should be made. The paper proves that this situation positively affects the development of successful financial innovation models for the e-commerce industry. Therefore, it may be possible to attract greater attention from e-commerce companies for these financial innovation products.

show abstract

Section: Golden Cut Q-rung Orthopair Fuzzy Multicriteria Decision-mak...mentioning

confidence: 99%

Market capitalization shock effects on open innovation models in e-commerce: golden cut q-rung orthopair fuzzy multicriteria decision-making analysis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This work was supported by the Hong Kong GRF 16207019 research grant. models constitute an important tool for multivariate time series analysis, and are widely used for data description, forecasting, structural inference, and policy analysis [1,3,4,5].…”

Section: Introductionmentioning

confidence: 99%

Parameter Estimation for Student’s t VAR Model with Missing Data

Zhou

Liu

Kumar

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The vector autoregressive (VAR) models provide a significant tool for multivariate time series analysis. Most existing works on VAR modeling are based on the multivariate Gaussian distribution. However, heavy-tailed distributions are suggested more reasonable for capturing the real-world phenomena, like the presence of outliers and a stronger possibility of extreme values. Furthermore, missing values in observed data is a real problem, which typically happens during the data observation or recording process. In this paper, we propose an algorithmic framework to estimate the parameters of a VAR model with heavy-tailed Student's t distributed innovations from incomplete data based on the stochastic approximation expectation maximization (SAEM) algorithm coupled with a Markov Chain Monte Carlo (MCMC) procedure. Extensive experiments with synthetic data corroborate our claims.

show abstract

“…In literature, number of research works based on Bayesian approach have been reported [16]- [19]. The curse of dimensionality typically arises when the number of observations is less than the number of predictors in the VARs equation.…”

Section: Introductionmentioning

confidence: 99%

A Time-Varying Bayesian Compressed Vector Autoregression for Macroeconomic Forecasting

Aunsri

Taveeapiradeecharoen

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents macroeconomic forecasting by using a time-varying Bayesian compressed vector autoregression approach. We apply a random compression by using projection matrix to randomly select predictive variables in vector autoregression (VAR), and then perform true out-of-sample forecast where the forecast values are averaged across all estimated models, containing different in both explanatory variables and number of those variables by using Bayesian model averaging (BMA). In addition to this, we allow the parameters in Bayesian compressed VAR to be time-varying by implementing dynamic model averaging (DMA) algorithm that is applicable with VAR using forgetting factor to control the degree of time-varying in the estimating parameters. We validate the performance of the proposed method via real macroeconomic data including up to 53 variables. The empirical results demonstrate that the predictive performance of time-varying Bayesian compressed VAR can beat traditional VAR types which are considered to have a potentiality to deal with large size variables. INDEX TERMS Bayesian econometrics, macroeconomics, Bayesian model averaging, mathematical models, time-varying parameters, dynamic model averaging, compression, Kalman filter

show abstract

Forecasting Daily Forex Using Large Dimensional Vector Autoregression with Time-Varying Parameters

Cited by 8 publications

References 21 publications

Market capitalization shock effects on open innovation models in e-commerce: golden cut q-rung orthopair fuzzy multicriteria decision-making analysis

Market capitalization shock effects on open innovation models in e-commerce: golden cut q-rung orthopair fuzzy multicriteria decision-making analysis

Parameter Estimation for Student’s t VAR Model with Missing Data

A Time-Varying Bayesian Compressed Vector Autoregression for Macroeconomic Forecasting

Contact Info

Product

Resources

About