Neural Network Based Models for Efficiency Frontier Analysis: An Application to East Asian Economies’ Growth Decomposition

Liao, Hailin; Wang, Bin; Weyman‐Jones, Thomas

doi:10.1080/12265080701694561

Cited by 8 publications

(4 citation statements)

References 46 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aside from the aforementioned integrated approach, a group of researchers has utilized ANN as an alternative to DEA, which again implies promising opportunities in this research arena. Insightful research outcomes are found from the literature (Angelidis and Lyroudi, 2006;Liao et al, 2007;Santin, 2008;Santín et al, 2004;Wang, 2003).…”

Section: Literature Reviewmentioning

confidence: 99%

Performance modeling of mobile phone providers: a DEA-ANN combined approach

Kwon

2014

Benchmarking: An International Journal

View full text Add to dashboard Cite

Purpose – The purpose of this paper is to investigate the feasibility of using artificial neural networks (ANNs) in conjunction with data envelopment analysis (DEA) for the performance measurement of major mobile phone providers, and for subsequent predictions related to best performance benchmarking and decision making. Design/methodology/approach – DEA and ANN are combined, providing an integrated modeling approach via a two-stage process. DEA is used for front end measurement, while ANN provides learning and prediction capabilities. DEA analysis of industry characteristics is based on the measurement of each decision-making unit's (DMU) performance. Back propagation neural networks (BPNN) can then predict each DMU's efficiency score, based on the results of the DEA models. Additional BPNN models provide best performance predictions. Findings – The DEA module successfully evaluates the competitive status of firms in the mobile phone industry in terms of efficiency. Efficiency trends over the observation period reveal the dynamic nature of competition in this industry. The predictive power of the BPNN module has been demonstrated as well. The proposed system is an effective benchmarking and decision support tool, via its capability to simulate performance scenarios, thereby facilitating insightful, prudent decision making. Originality/value – This paper proposes the use of two different but complementary methods, DEA and ANN, in a combined performance modeling approach, and examines mobile phone providers. This methodology can improve users’ performance benchmarking and decision-making processes. Additionally, adaptive prediction capability is provided through approximating efficient frontiers, in addition to performance measurement.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Performance modeling of mobile phone providers: a DEA-ANN combined approach

Kwon

2014

Benchmarking: An International Journal

View full text Add to dashboard Cite

show abstract

“…To compute the performance of the ith unit, the error (E i ) between the actual output (P Actual(i) ) and the output obtained from the best structure of ANFIS (P ANFIS×(i) ) should be calculated using Equation ( 1) (Delgado, 2005;Liao et al, 2007):…”

Section: Anfis-based Algorithmmentioning

confidence: 99%

Performance assessment of human resource by integration of HSE and ergonomics and EFQM management system

Amalnick

Zarrin

2017

IJHCQA

View full text Add to dashboard Cite

Purpose The purpose of this paper is to present an integrated framework for performance evaluation and analysis of human resource (HR) with respect to the factors of health, safety, environment and ergonomics (HSEE) management system, and also the criteria of European federation for quality management (EFQM) as one of the well-known business excellence models. Design/methodology/approach In this study, an intelligent algorithm based on adaptive neuro-fuzzy inference system (ANFIS) along with fuzzy data envelopment analysis (FDEA) are developed and employed to assess the performance of the company. Furthermore, the impact of the factors on the company's performance as well as their strengths and weaknesses are identified by conducting a sensitivity analysis on the results. Similarly, a design of experiment is performed to prioritize the factors in the order of importance. Findings The results show that EFQM model has a far greater impact upon the company's performance than HSEE management system. According to the obtained results, it can be argued that integration of HSEE and EFQM leads to the performance improvement in the company. Practical implications In current study, the required data for executing the proposed framework are collected via valid questionnaires which are filled in by the staff of an aviation industry located in Tehran, Iran. Originality/value Managing HR performance results in improving usability, maintainability and reliability and finally in a significant reduction in the commercial aviation accident rate. Also, study of factors affecting HR performance authorities participate in developing systems in order to help operators better manage human error. This paper for the first time presents an intelligent framework based on ANFIS, FDEA and statistical tests for HR performance assessment and analysis with the ability of handling uncertainty and vagueness existing in real world environment.

show abstract

“…Athanassopoulos and Curram first introduced the idea of the combination of neural networks (NNs) and DEA for classification and/or prediction. Other papers that presented the benefits of combining DEA and NN are Liu et al, Liao et al, Santin, Santin et al and Wang . Azadeh et al proposed a highly unique flexible ANN algorithm to measure and rank scores of Iranian steam power.…”

Section: Introductionmentioning

confidence: 99%

Efficiency analysis for stochastic dynamic facility layout problem using meta‐heuristic, data envelopment analysis and machine learning

Tayal

Köse

Solanki

et al. 2019

Computational Intelligence

View full text Add to dashboard Cite

The facility layout problem (FLP) is a combinatorial optimization problem. The performance of the layout design is significantly impacted by diverse, multiple factors. The use of algorithmic or procedural design methodology in ranking and identification of efficient layout is ineffective. In this context, this study proposes a three‐stage methodology where data envelopment analysis (DEA) is augmented with unsupervised and supervised machine learning (ML). In stage 1, unsupervised ML is used for the clustering of the criteria in which the layouts need to be evaluated using homogeneity. Layouts are generated using simulated annealing, chaotic simulated annealing, and hybrid firefly algorithm/chaotic simulated annealing meta‐heuristics. In stage 2, the nonparametric DEA approach is used to identify efficient and inefficient layouts. Finally, supervised ML utilizes the performance frontiers from DEA (efficiency scores) to generate a trained model for getting the unique rankings and predicted efficiency scores of layouts. The proposed methodology overcomes the limitations associated with large datasets that contain many inputs / outputs from the conventional DEA and improves the prediction accuracy of layouts. A Gaussian distribution product demand dataset for time period T = 5 and facility size N = 12 is used to prove the effectiveness of the methodology.

show abstract

Neural Network Based Models for Efficiency Frontier Analysis: An Application to East Asian Economies’ Growth Decomposition

Cited by 8 publications

References 46 publications

Performance modeling of mobile phone providers: a DEA-ANN combined approach

Performance modeling of mobile phone providers: a DEA-ANN combined approach

Performance assessment of human resource by integration of HSE and ergonomics and EFQM management system

Efficiency analysis for stochastic dynamic facility layout problem using meta‐heuristic, data envelopment analysis and machine learning

Contact Info

Product

Resources

About