A wavelet and neural network model for the prediction of dry bulk shipping indices

Leonov, Yordan; Nikolov, Ventsislav

doi:10.1057/mel.2012.10

Cited by 31 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Leonov and Nikolov [16] use a model based on wavelets and neural networks to predict dry bulk freight rates. Bulut et al [17] apply a fuzzy vector autoregressive integrated logical model to forecast time charter rates.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index

2019

View full text Add to dashboard Cite

The shipping market, a major component of the global economy, is characterized by high risk and volatility. The Baltic dry index is an influential indicator in the world shipping market and international trade. Several studies have used a variety of techniques to generate Baltic dry index predictions. The most prominent techniques utilize either econometric or artificial intelligence computing. We compare the forecasting accuracy of two typical univariant econometric models and three artificial neural networks (ANNs)-based algorithms. We find that when using daily data, econometric forecasting models produce better one-step-ahead predictions than ANN-based algorithms. When forecasting weekly and monthly data, ANN-based algorithms produce fewer errors and a higher direction matching rate than econometric models. We also compare the predictive power of a number of different models when applied to the 2008 financial crisis and find that the generalized autoregressive conditional heteroskedasticity model and the back propagation neural network algorithm produce the best one-step-ahead and seven-steps ahead predictions, respectively. INDEX TERMS Baltic dry index prediction, ARIMA,GARCH, artificial neural networks(ANN), BP neural network, RBFNN, ELM.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index

2019

View full text Add to dashboard Cite

show abstract

“…VAR outperformed out of the sample ARIMA. Leonova and Nikolov [98] used a model based on "wavelet" and "neural network" in order to predict dry bulk freight rates. Bulut et al [99] developed a "VAR fuzzy integrated logical" forecasting model for time charter rates.…”

Section: Maritime Economic Models (2003-2016) In Forecastingmentioning

confidence: 99%

“…The above attempt [103] is the 6th in a series between 1997 and 2016 using "Artificial Neural Networks" among Li & Parsons [105]; Lyridis et al [106]; Goulielmos et al [107]; Mehrara et al [108]; Leonova and Nikolov [98]; and Zheng et al [21]. At last maritime economists used nonlinear regressions.…”

Section: A M Goulielmosmentioning

confidence: 99%

Maritime Economic Modeling: A Survey, 2006-2016

Γουλιέλμος¹

2018

View full text Add to dashboard Cite

We surveyed quite a number of papers (~60), where one third of them belonged to maritime economic dynamic systems, meaning multi variable models. The emphasis we placed was on works published the last 11 years or so (2006-2016). In addition, we provided a general picture of maritime economic research from 1973 to 2013. The survey had to be combined with advances in General Econometrics. As a result and despite long delays maritime economists (Glen et al. [1] applied the VAR-vector autoregressive (1987-1988) model due to Sims [2]. But this was not the only one as co-integration [3] [4] dominated the scene given that SEM-simultaneous equations model had defects in relation to exogenous variables. Moreover, VEC-the vector error correction model and a representation of VAR appeared based on Granger's representation theorem. The models for 2006-2016 were 36 including 5 for maritime futures after 2003 and 7 on forecasting (2003-2016). A description of a shipping cycle has been given with the presence of time.

show abstract

“…Accordingly, the weighted matrix (wji; wkj) of interconnections allows the neural networks to learn and remember. (Fausett, 1994), (Leonov & Nikolov, 2012).…”

Section: Page |mentioning

confidence: 99%

Artificial neural network (ANN) approach to predicting micro hardness profile values of iron-based sintered alloys

Mincheva

Antonov

2017

AJTUV

View full text Add to dashboard Cite

show abstract

A wavelet and neural network model for the prediction of dry bulk shipping indices

Cited by 31 publications

References 11 publications

Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index

Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index

Maritime Economic Modeling: A Survey, 2006-2016

Artificial neural network (ANN) approach to predicting micro hardness profile values of iron-based sintered alloys

Contact Info

Product

Resources

About