Avoiding Pitfalls in Neural Network Research

Zhang, G.P.

doi:10.1109/tsmcc.2006.876059

Cited by 133 publications

(70 citation statements)

References 134 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then 10-by-10 cross-validation was applied to the dataset to obtain the parameters and their deviations (Hastie et al, 2009). For training the neural network, an additional step-extracting one of the folds of the cross-validation set to search for the optimal parameter configuration-was taken, a crucial step in order to get useful results in these types of statistical models (Zhang, 2007). Since the training is performed 100 times, a set of 100 results is obtained for both the parameters and the performances of the models.…”

Section: Classification Resultsmentioning

confidence: 99%

Improving credit scoring by differentiating defaulter behaviour

Bravo

Thomas

Weber

2015

Journal of the Operational Research Society

View full text Add to dashboard Cite

We present a methodology for improving credit scoring models by distinguishing two forms of rational behaviour of loan defaulters. It is common knowledge among practitioners that there are two types of defaulters, those who do not pay because of cash flow problems ('Can't Pay'), and those that do not pay because of lack of willingness to pay ('Won't Pay'). This work proposes to differentiate them using a game theory model that describes their behaviour. This separation of behaviours is represented by a set of constraints that form part of a semi-supervised constrained clustering algorithm, constructing a new target variable summarizing relevant future information. Within this approach the results of several supervised models are benchmarked, in which the models deliver the probability of belonging to one of these three new classes (good payers, 'Can't Pays', and 'Won't Pays'). The process improves classification accuracy significantly, and delivers strong insights regarding the behaviour of defaulters.

show abstract

Section: Classification Resultsmentioning

confidence: 99%

Improving credit scoring by differentiating defaulter behaviour

Bravo

Thomas

Weber

2015

Journal of the Operational Research Society

View full text Add to dashboard Cite

show abstract

“…This is used to test the resulting system parameters after simulation with training dataset. Almost 2/3rd of the total dataset has been taken as training set (Zhang, 2007). This is done through the analysis of the accuracy achieved through different testing cases.…”

Section: Training With Elmmentioning

confidence: 99%

An improved extreme learning machine to classify multinomial datasets using particle swarm optimisation

Dash

Priyadarshini

Misra

2017

IJISDC

View full text Add to dashboard Cite

Abstract:In this paper, we propose a particle swarm-based extreme learning machine (ELM) to classify datasets with varying number of classes. This work emphasises on a couple of important parameters, like maximisation of classification accuracy and minimisation of training time. As a machine classifier, an ELM has been chosen, which is an improvement over back propagation network. For each of the input dataset an optimised target was determined by using particle swarm optimisation (PSO) technique. Those specific targets are used with the input data to train the ELM during classification process. For this, some of the bench mark classification datasets are used. To compare the proposed method and some of the existing methods an extensive experimental study has been carried out; a comparative analysis is done by taking parameters like percentage of classification accuracy, training time and complexity of the computing algorithm.Keywords: multinomial classification; extreme learning machine; ELM; normalisation; particle swarm optimisation; PSO; back propagation neural network; classification; classification accuracy; input; target; complexity of algorithm.Reference to this paper should be made as follows: Dash, N., Priyadarshini, R. and Misra, R. (2017) 'An improved extreme learning machine to classify multinomial datasets using particle swarm optimisation', Int. J. Intelligent Systems Design and Computing, Vol. 1, Nos. 1/2, pp.127-144. Rachita Misra received her Doctoral degree from IIT Kharagpur, and is currently working as a Professor in the Department of IT, in C.V. Raman College of Engineering, Bhubaneswar. With more than 15 years of IT industry experience and 15 years of teaching and research experience, she has more than 30 publications in various reputed journals and conferences. Her areas of interest are digital image processing, data mining, soft computing, parallel computing, software engineering and project management. This paper is a revised and expanded version of a paper entitled 'An ANN Model to classify multinomial datasets with optimized target using particle swarm optimization technique' presented at

show abstract

“…However, the main drawback with ANNs is their black-box nature, revealing difficulty in interpreting the results by not providing an insight into the dynamic of the interactions between the technical indicators and the currency market fluctuations [11]. Another challenge in ANN approaches is the learning process for models with memory like recurrent networks, essential for time-dependent environments, which requires intensive training and suffers low convergence, revealing a key problem in dynamic markets [12].…”

Section: Introductionmentioning

confidence: 99%

Forecasting Exchange Rates with Fuzzy Granular Evolving Modeling for Trading Strategies

Maciel

Gomide

Ballini

2013

Proceedings of the 8th Conference of the European Society for Fuzzy Logic and Technology

View full text Add to dashboard Cite

This paper addresses a fuzzy set based evolving modeling (FBeM) approach and the task of forecasting exchange rates in order to perform trading strategies. FBeM is a granular computing technique that uses fuzzy information granules to model nonstationary functions providing functional and linguistic approximations. As an application, this work considers the BRL/USD exchange rate market data for the period from January 2000 to October 2012. Comparisons in terms of goodness of fit and based on trading performance indicators includes the granular model against a Multi-Layer Perceptron (MLP), an autoregressive moving average (ARMA), a naïve strategy and some state of the art evolving fuzzy systems. Computational results suggest that the FBeM model statistically outperforms the alternative approaches.

show abstract

Avoiding Pitfalls in Neural Network Research

Cited by 133 publications

References 134 publications

Improving credit scoring by differentiating defaulter behaviour

Improving credit scoring by differentiating defaulter behaviour

An improved extreme learning machine to classify multinomial datasets using particle swarm optimisation

Forecasting Exchange Rates with Fuzzy Granular Evolving Modeling for Trading Strategies

Contact Info

Product

Resources

About