Search results

1 – 10 of over 10000
To view the access options for this content please click here
Article
Publication date: 29 July 2014

Chih-Fong Tsai and Chihli Hung

Credit scoring is important for financial institutions in order to accurately predict the likelihood of business failure. Related studies have shown that machine learning…

Abstract

Purpose

Credit scoring is important for financial institutions in order to accurately predict the likelihood of business failure. Related studies have shown that machine learning techniques, such as neural networks, outperform many statistical approaches to solving this type of problem, and advanced machine learning techniques, such as classifier ensembles and hybrid classifiers, provide better prediction performance than single machine learning based classification techniques. However, it is not known which type of advanced classification technique performs better in terms of financial distress prediction. The paper aims to discuss these issues.

Design/methodology/approach

This paper compares neural network ensembles and hybrid neural networks over three benchmarking credit scoring related data sets, which are Australian, German, and Japanese data sets.

Findings

The experimental results show that hybrid neural networks and neural network ensembles outperform the single neural network. Although hybrid neural networks perform slightly better than neural network ensembles in terms of predication accuracy and errors with two of the data sets, there is no significant difference between the two types of prediction models.

Originality/value

The originality of this paper is in comparing two types of advanced classification techniques, i.e. hybrid and ensemble learning techniques, in terms of financial distress prediction.

Details

Kybernetes, vol. 43 no. 7
Type: Research Article
ISSN: 0368-492X

Keywords

To view the access options for this content please click here
Article
Publication date: 25 September 2009

Menderes Kalkat, Şahin Yıldırım and Selçuk Erkaya

The purpose of this paper is to improve the application of neural networks on vehicle engine systems for fault detecting and analysing engine oils.

Downloads
1410

Abstract

Purpose

The purpose of this paper is to improve the application of neural networks on vehicle engine systems for fault detecting and analysing engine oils.

Design/methodology/approach

Three types of neural networks are employed to find exact neural network predictor of vehicle engine oil performance and quality. Nevertheless, two oil types are analysed for predicting performance in the engine. These oils are used and unused oils. In experimental work, two accelerometers are located at the bottom of the car engine to measure related vibrations for analysing oil quality of both cases.

Findings

The results of both computer simulation and experimental work show that the radial basis neural network predictor gives good performance at adapting different cases.

Research limitations/implications

The results of the proposed neural network analyser follow the desired results of the vehicle engine's vibration variation. However, this kind of neural network scheme can be used to analyse oil quality of the car in experimental applications.

Practical implications

As theoretical and practical studies are evaluated together, it is hoped that oil analysers and interested researchers will obtain significant results in this application area.

Originality/value

This paper is an original contribution on vehicle oil quality analysis using a proposed artificial neural network and it should be helpful for industrial applications of vehicle oil quality analysis and fault detection.

Details

Industrial Lubrication and Tribology, vol. 61 no. 6
Type: Research Article
ISSN: 0036-8792

Keywords

To view the access options for this content please click here
Article
Publication date: 25 January 2008

Yi‐Hui Liang

The purpose of this paper is to propose an accurate product reliability prediction model in order to enhance product quality and reduce product costs.

Abstract

Purpose

The purpose of this paper is to propose an accurate product reliability prediction model in order to enhance product quality and reduce product costs.

Design/methodology/approach

This study proposes a new method for predicting the reliability of repairable systems. The novel method employed constructs a predictive model by integrating neural networks and genetic algorithms. Findings – The novel method employed constructs a predictive model by integrating neural networks and genetic algorithms. Genetic algorithms are used to globally optimize the number of neurons in the hidden layer, the learning rate and momentum of neural network architecture. Research limitations/implications – This study only adopts real failure data from an electronic system to verify the feasibility and effectiveness of the proposed method. Future research may use other product's failure data to verify the proposed method. The proposed method is superior to ARIMA and neural network model prediction techniques in the reliability of repairable systems. Practical implications – Based on the more accurate analytical results achieved by the proposed method, engineers or management authorities can take follow‐up actions to ensure that products meet quality requirements, provide logistical support and correct product design. Originality/value – The proposed method is superior to other prediction techniques in predicting the reliability of repairable systems.

Details

International Journal of Quality & Reliability Management, vol. 25 no. 2
Type: Research Article
ISSN: 0265-671X

Keywords

To view the access options for this content please click here
Article
Publication date: 1 August 1995

Michiel C. van Wezel and Walter R.J. Baets

Market response modelling is well covered in the marketingliterature. However, much less research has been undertaken in the useof neural networks for market response…

Downloads
1043

Abstract

Market response modelling is well covered in the marketing literature. However, much less research has been undertaken in the use of neural networks for market response modelling. Describes experiments to fit neural networks to the consumer goods market. Compares the neural network approach with several other possible models. Focuses on the out‐of‐sample performance of the models. Describes a method for adjusting the neural network architecture which leads to better performance on out‐of‐sample data.

Details

Marketing Intelligence & Planning, vol. 13 no. 7
Type: Research Article
ISSN: 0263-4503

Keywords

To view the access options for this content please click here
Article
Publication date: 13 July 2020

Gültekin Işık, Selçuk Ekici and Gökhan Şahin

Determining the performance parameters of the propulsion systems of the aircraft, which is the key product of the aviation industry, plays a critical role in reducing…

Abstract

Purpose

Determining the performance parameters of the propulsion systems of the aircraft, which is the key product of the aviation industry, plays a critical role in reducing adverse environmental impacts. Therefore, the purpose of this paper is to present a temperature performance template for turbojet engines at the design stage using a neural network model that defines the relationship between the performance parameters obtained from ground tests of a turbojet engine used in unmanned aerial vehicles (UAV).

Design/methodology/approach

The main parameters of the flow passing through the engine of the UAV propulsion system, where ground tests were performed, were obtained through the data acquisition system and injected into a neural network model created. Fifteen sensors were mounted on the engine – six temperature sensors, six pressure sensors, two flow meters and one load cell were connected to the data acquisition system to make sense of this physical environment. Subsequently, the artificial neural network (ANN) model as a complement to the approach was used. Thus, the predicted model relationship with the experimental data was created.

Findings

Fuel flow and thrust parameters were estimated using these components as inputs in the feed-forward neural network. In the network experiments to estimate fuel flow parameter, r-square and mean absolute error were calculated as 0.994 and 0.02, respectively. Similarly, for thrust parameter, these metrics were calculated as 0.994 and 1.42, respectively. In addition, the correlation between fuel flow, thrust parameters and each input parameters was examined. According to this, air compressor inlet (ACinlet,temp) and outlet (ACoutlet,temp) temperatures and combustion chamber (CCinlet,temp, CCoutlet,temp) temperature parameters were determined to affect the output the most. The proposed ANN model is applicable to any turbojet engines to model its behavior.

Practical implications

Today, deep neural networks are the driving force of artificial intelligence studies. In this study, the behavior of a UAV is modeled with neural networks. Neural networks are used here as a regressor. A neural network model has been developed that predicts fuel flow and thrust parameters using the real parameters of a UAV turbojet engine. As a result, satisfactory findings were obtained. In this regard, fuel flow and thrust values of any turbojet engine can be estimated using the neural network hyperparameters proposed in this study. Python codes of the study can be accessed from https://github.com/tekinonlayn/turbojet.

Originality/value

The originality of the study is that it reports the relationships between turbojet engine performance parameters obtained from ground tests using the neural network application with open source Python code. Thus, small-scale unmanned aerial propulsion system provides designers with a template showing the relationship between engine performance parameters.

Details

Aircraft Engineering and Aerospace Technology, vol. 92 no. 8
Type: Research Article
ISSN: 1748-8842

Keywords

To view the access options for this content please click here
Article
Publication date: 1 July 2000

M.L. Nasir, R.I. John, S.C. Bennett, D.M. Russell and A Patel

An appropriate use of neural computing techniques is to apply them to corporate bankruptcy prediction, where conventional solutions can be hard to obtain. Having said…

Abstract

An appropriate use of neural computing techniques is to apply them to corporate bankruptcy prediction, where conventional solutions can be hard to obtain. Having said that, choosing an appropriate Artificial Neural Network topology (ANN) for predicting corporate bankruptcy would remain a daunting prospect. The context of the problem is that there are no fixed rules in determining the ANN structure or its parameter values, a large number of ANN topologies may have to be constructed with different structures and parameters before determining an acceptable model. The trial‐and‐error process can be tedious, and the experience of the ANN user in constructing the topologies is invaluable in the search for a good model. Yet, a permanent solution does not exist. This paper identifies a non trivial novel approach for implementing artificial neural networks for the prediction of corporate bankruptcy by applying inter‐connected neural networks. The proposed approach is to produce a neural network architecture that captures the underlying characteristics of the problem domain. The research primarily employed financial data sets from the London Stock Exchange and Jordans financial database of major public and private British companies. Early results indicate that an ANN appears to outperform the traditional approach in forecasting corporate bankruptcy.

Details

Journal of Applied Accounting Research, vol. 5 no. 3
Type: Research Article
ISSN: 0967-5426

Keywords

To view the access options for this content please click here
Article
Publication date: 1 October 2002

Ravi S. Behara, Warren W. Fisher and Jos G.A.M. Lemmink

Effective measurement and analysis of service quality are an essential first step in its improvement. This paper discusses the development of neural network models for…

Downloads
3182

Abstract

Effective measurement and analysis of service quality are an essential first step in its improvement. This paper discusses the development of neural network models for this purpose. A valid neural network model for service quality is initially developed. Customer data from a SERVQUAL survey at an auto‐dealership network in The Netherlands provide the basis for model development. Different definitions of service quality measurement are modelled using the neural network approach. The perception‐minus‐expectation model of service quality was found not to be as accurate as the perception‐only model in predicting service quality. While this is consistent with the literature, this study also shows that the more intuitively appealing but mathematically less convenient expectation‐minus‐perception model out‐performs all the other service quality measurement models. The study also provides an analytical basis for the importance of expectation in the measurement of service quality. However, the study demonstrates the need for further study before neural network models may be effectively used for sensitivity analyses involving specific dimensions of service quality.

Details

International Journal of Operations & Production Management, vol. 22 no. 10
Type: Research Article
ISSN: 0144-3577

Keywords

To view the access options for this content please click here
Article
Publication date: 1 January 1993

Mohammed H. A. Tafti and Ehsan Nikbakht

Neural networks and expert systems are two major branches ofartificial intelligence (AI). Their emergence has created the potentialfor a new generation of computer‐based…

Abstract

Neural networks and expert systems are two major branches of artificial intelligence (AI). Their emergence has created the potential for a new generation of computer‐based applications in the area of financial decision making. Both systems are used by financial institutions and corporations for a variety of new applications from credit scoring to bond rating to detection of credit card fraud. While both systems belong to the applied field of artificial intelligence, there are many differences between them which differentiate their potential capabilities in the field of business. Presents an analysis of both neural networks and expert systems applications in terms of their capabilities and weaknesses. Uses examples of financial applications of expert systems and neural networks to provide a unified context for the comparison.

Details

Information Management & Computer Security, vol. 1 no. 1
Type: Research Article
ISSN: 0968-5227

Keywords

To view the access options for this content please click here
Article
Publication date: 1 March 2001

M.L. Nasir, R.I. John, S.C. Bennett and D.M. Russell

Neural network topology selection refers to a systematic procedure for selecting between competing models. Naturally, it is regarded as a key aspect in optimisation and…

Downloads
1376

Abstract

Neural network topology selection refers to a systematic procedure for selecting between competing models. Naturally, it is regarded as a key aspect in optimisation and replicability of neural network performance. When constructing neural network topologies, it is necessary to determine from the outset the general taxonomy of the neural network architectures to be constructed. The taxonomy considered in this study is the general taxonomy of time‐varying patterns which subsumes many existing architectures in the literature and points to several promising neural network architectures that have yet to be examined. The context of the problem is that choosing the right neural network topology for use in a particular domain such as corporate bankruptcy prediction with optimum generalisation performance is not, in any case, a trivial problem. The results of experiments presented in this paper would serve as a baseline against which to select between two competing architectures.

Details

Campus-Wide Information Systems, vol. 18 no. 1
Type: Research Article
ISSN: 1065-0741

Keywords

To view the access options for this content please click here
Article
Publication date: 1 December 2001

Zoran Vojinovic and Vojislav Kecman

In this paper we are presenting our research findings on how effective neural networks are at forecasting and estimating preliminary project costs. We have shown that…

Abstract

In this paper we are presenting our research findings on how effective neural networks are at forecasting and estimating preliminary project costs. We have shown that neural networks completely outperform traditional techniques in such tasks. In exploring nonlinear techniques almost all of the current research involves neural network techniques, especially multilayer perceptron (MLP) models and other statistical techniques and few authors have considered radial basis function neural network (RBF NN) models in their research. For this purpose we have developed RBF NN models to represent nonlinear static and dynamic processes and compared their performance with traditional methods. The traditional methods applied in this paper are multiple linear regression (MLR) and autoregressive moving average models with eXogenous input (ARMAX). The performance of these and RBF neural network and traditional models is tested on common data sets and their results are presented.

Details

Construction Innovation, vol. 1 no. 4
Type: Research Article
ISSN: 1471-4175

Keywords

1 – 10 of over 10000