An experimental study of Multi-Objective Evolutionary Algorithms for balancing interpretability and accuracy in fuzzy rulebase classifiers for financial prediction

Ghandar, Adam; Michalewicz, Zbigniew

doi:10.1109/cifer.2011.5953570

Cited by 11 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FICDP is used in the process of balancing the data set containing only a small number of defaults by oversampling this minority class. Ghandar and Michalewicz [32] perform an experimental evaluation of how the predictive capability relates to interpretability of fuzzy rule based systems obtained using Multi-Objective Evolutionary Algorithms (MOEA) by predicting whether the Bombay Stock Index will rise or fall based on momentum indicators.…”

Section: Linguistic Modeling and Machine Learning In Financementioning

confidence: 99%

Credit Risk Evaluation in Peer-to-peer Lending With Linguistic Data Transformation and Supervised Learning

Mezei¹,

Byanjankar²,

Heikkilä³

2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

The widespread availability of various peer-to-peer lending solutions is rapidly changing the landscape of financial services. Beside the natural advantages over traditional services, a relevant problem in the domain is to correctly assess the risk associated with borrowers. In contrast to traditional financial services industries, in peerto-peer lending the unsecured nature of loans as well as the relative novelty of the platforms make the assessment of risk a difficult problem. In this article we propose to use traditional machine learning methods enhanced with fuzzy set theory based transformation of data to improve the quality of identifying loans with high likelihood of default. We assess the proposed approach on a real-life dataset from one of the largest peer-to-peer platforms in Europe. The results demonstrate that (i) traditional classification algorithms show good performance in classifying borrowers, and (ii) their performance can be improved using linguistic data transformation.

show abstract

Section: Linguistic Modeling and Machine Learning In Financementioning

confidence: 99%

Credit Risk Evaluation in Peer-to-peer Lending With Linguistic Data Transformation and Supervised Learning

Mezei¹,

Byanjankar²,

Heikkilä³

2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Model transparency [50], also referred to as comprehensibility [50] or interpretability [21] can be defined as the ability of a human user to understand what the model consists of, leading ideally to the ability to apply it to new observations [50]. Another aspect, is the transparency of model development process [17,55] i.e.…”

Section: The Transparency Of Prediction Modelsmentioning

confidence: 99%

Interpreting tree-based prediction models and their data in machining processes

Bustillo

Grzenda

Macukow

2016

ICA

View full text Add to dashboard Cite

Machine-learning techniques frequently predict the results of machining processes, based on predetermined cutting tool settings. By doing so, key parameters of a machined product can be predicted before production begins. Nevertheless, a prediction model cannot capture all the features of interest under real-life industrial conditions. Moreover, careful assessment of prediction credibility is necessary for accurate calibration; aspects that should be addressed through appropriate modeling and visualization techniques. A machine process test problem is proposed to analyze data-visualization techniques, in which a real data set is analyzed that describes deep-drilling under different cutting and cooling conditions. The main objective is the efficient fusion of visualization techniques with the knowledge of industrial engineers. Common modeling and visualization techniques were first surveyed, to contrast standard practice with our novel approach. A hybrid technique combining conditional inference trees with dimensionality reduction was then examined. The results show that a process engineer will be able to estimate overall model accuracy and to verify the extent to which accuracy depends on industrial process settings and the statistical significance of model predictions. Moreover, evaluation of the data set in terms of its sufficiency for modeling purposes will help assess the credibility of these decisions.

show abstract

“…Using EMO in fuzzy systems, several applications have been developed. A genetic fuzzy framework has been proposed for financial prediction in [117] in multi-objective evolutionary algorithms. In this contribution, the relationship between predictive capability and interpretability of FRBS obtained by MOEA is studied.…”

Section: Other Specific Applications Developed Using Emomentioning

confidence: 99%

A Review on the Interpretability-Accuracy Trade-Off in Evolutionary Multi-Objective Fuzzy Systems (EMOFS)

Shukla

Tripathi

2012

Information

View full text Add to dashboard Cite

Interpretability and accuracy are two important features of fuzzy systems which are conflicting in their nature. One can be improved at the cost of the other and this situation is identified as “Interpretability-Accuracy Trade-Off”. To deal with this trade-off Multi-Objective Evolutionary Algorithms (MOEA) are frequently applied in the design of fuzzy systems. Several novel MOEA have been proposed and invented for this purpose, more specifically, Non-Dominated Sorting Genetic Algorithms (NSGA-II), Strength Pareto Evolutionary Algorithm 2 (SPEA2), Fuzzy Genetics-Based Machine Learning (FGBML), (2 + 2) Pareto Archived Evolutionary Strategy ((2 + 2) PAES), (2 + 2) Memetic- Pareto Archived Evolutionary Strategy ((2 + 2) M-PAES), <em>etc</em>. This paper introduces and reviews the approaches to the issue of developing fuzzy systems using Evolutionary Multi-Objective Optimization (EMO) algorithms considering ‘Interpretability-Accuracy Trade-off’ and mainly focusing on the work in the last decade. Different research issues and challenges are also discussed

show abstract

An experimental study of Multi-Objective Evolutionary Algorithms for balancing interpretability and accuracy in fuzzy rulebase classifiers for financial prediction

Cited by 11 publications

References 30 publications

Credit Risk Evaluation in Peer-to-peer Lending With Linguistic Data Transformation and Supervised Learning

Credit Risk Evaluation in Peer-to-peer Lending With Linguistic Data Transformation and Supervised Learning

Interpreting tree-based prediction models and their data in machining processes

A Review on the Interpretability-Accuracy Trade-Off in Evolutionary Multi-Objective Fuzzy Systems (EMOFS)

Contact Info

Product

Resources

About