Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms

Erdal, Halil İbrahim; Karakurt, Onur

doi:10.1016/j.jhydrol.2012.11.015

Cited by 171 publications

(89 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, CART does not need a priori information about data. This enables considering a bigger variety of possible model specifications when the combination of continuous and categorical data is available for use (Erdal and Karakurt 2012). Even if training set holds some irrelevant information (e.g.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Reducing Overreliance on Sovereign Credit Ratings: Which Model Serves Better?

Öztürk

Namlı

Erdal³

2015

Comput Econ

Self Cite

View full text Add to dashboard Cite

Sovereign credit ratings have been a controversial issue since the outbreak of the 2008 financial crisis. Among the debates the inaccuracies stay at the centre. By employing classification and regression trees, multilayer perceptron, support vector machines (SVM), Bayes net, and naïve Bayes; we compare the ability of various learning techniques with the conventional statistical method in predicting sovereign credit ratings. Experimental results suggest that all the techniques excluding SVM have over 90 % accurate prediction. According to within one and two notch accurate prediction measure, the prediction performance of SVM also increases above 90 %. These findings indicate a clear outperformance of AI methods over the conventional statistical method. The results have many implications for the practitioners in credit scoring industry. Amidst the regulatory measures that encourage individual credit scoring for international financial institutions, these findings suggest that up-to-date AI methods serve quite reliable technical tools to predict sovereign credit ratings.

show abstract

Section: Resultsmentioning

confidence: 99%

“…When there is no data structure hypotheses are available, non-parametric analysis becomes more effective. Since, the need for any additional assumptions concerning model errors distribution disappears (Erdal and Karakurt 2012).…”

Section: Resultsmentioning

confidence: 99%

Reducing Overreliance on Sovereign Credit Ratings: Which Model Serves Better?

Öztürk

Namlı

Erdal³

2015

Comput Econ

Self Cite

View full text Add to dashboard Cite

show abstract

“…They are usually showed as systems of interconnected "neurons" that can count different values from inputs via feeding information through the network. As the algorithm develops, this method is mature and has been adopted into the module of the software [6][7][8][9][10][11][12].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Prediction of Thermophysical Properties of Helium Using Linear Prediction and Artificial Neural Networks

Yang¹,

Li²,

Zhou³

2014

IJCA

View full text Add to dashboard Cite

show abstract

“…[12], where the authors demonstrated the advantages of an improved version of boosting, namely, AdaBoost.RT, which is compared to other learning methods for several benchmarking problems, and two problems involving river flow forecasting. In a recent study [13], the authors investigated the potential usage of bagging and boosting in building classification and regression tree ensembles to refine the accuracy of streamflow predictions. They report that the bagged model performs slightly better than the boosted model in the testing phase.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Prediction of Stream Flows Enhanced by Harmony Search Optimization

Čistý¹,

Soldanova²

2018

Time Series Analysis and Applications

View full text Add to dashboard Cite

This work presents the application of a data-driven model for streamflow predictions, which can be one of the possibilities for the preventive protection of a population and its property. A new methodology was investigated in which ensemble modeling by data-driven models was applied and in which harmony search was used to optimize the ensemble structure. The diversity of the individual basic learners which form the ensemble is achieved through the application of different learning algorithms. In the proposed ensemble modeling of river flow predictions, powerful algorithms with good performances were used as ensemble constituents (gradient boosting machines, support vector machines, random forests, etc.). The proposed ensemble provides a better degree of precision in the prediction task, which was evaluated as a case study in comparison with the ensemble components, although they were powerful algorithms themselves. For this reason, the proposed methodology could be considered as a potential tool in flood predictions and prediction tasks in general.

show abstract

Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms

Cited by 171 publications

References 32 publications

Reducing Overreliance on Sovereign Credit Ratings: Which Model Serves Better?

Reducing Overreliance on Sovereign Credit Ratings: Which Model Serves Better?

Prediction of Thermophysical Properties of Helium Using Linear Prediction and Artificial Neural Networks

Ensemble Prediction of Stream Flows Enhanced by Harmony Search Optimization

Contact Info

Product

Resources

About