FRFE: Fast Recursive Feature Elimination for Credit Scoring

Ha, Van-Sang; Nguyen, Ha-Nam

doi:10.1007/978-3-319-46909-6_13

Cited by 6 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, credit scoring databases are often large and characterised by redundant and irrelevant features [56]. Financial data and credit data in particular usually contain irrelevant and redundant features [57]. The redundancy and the deficiency in data can reduce the classification accuracy and lead to incorrect decision [58], [39].…”

Section: Existing Workmentioning

confidence: 99%

Information gain directed genetic algorithm wrapper feature selection for credit rating

Jadhav

Jenkins

2018

Applied Soft Computing

249

View full text Add to dashboard Cite

Financial credit scoring is one of the most crucial processes in the finance industry sector to be able to assess the credit-worthiness of individuals and enterprises. Various statistics-based machine learning techniques have been employed for this task. "Curse of Dimensionality" is still a significant challenge in machine learning techniques. Some research has been carried out on Feature Selection (FS) using genetic algorithm as wrapper to improve the performance of credit scoring models. However, the challenge lies in finding an overall best method in credit scoring problems and improving the time-consuming process of feature selection. In this study, the credit scoring problem is investigated through feature selection to improve classification performance. This work proposes a novel approach to feature selection in credit scoring applications, called as Information Gain Directed Feature Selection algorithm (IGDFS), which performs the ranking of features based on information gain, propagates the top m features through the GA wrapper (GAW) algorithm using

show abstract

Section: Existing Workmentioning

confidence: 99%

Information gain directed genetic algorithm wrapper feature selection for credit rating

Jadhav

Jenkins

2018

Applied Soft Computing

249

View full text Add to dashboard Cite

show abstract

“…decision trees, SVMs, linear models). Although initially the algorithm was coupled with SVM for selecting features in high-dimensional small sample gene-expression data, it has since been used in a variety of settings with various base models [12,16,21,27].…”

Section: Related Workmentioning

confidence: 99%

“…However, due to possibly high computational costs, the authors of RFE suggest that in some scenarios it may be more efficient to remove several features at a time, at the expense of possible classification performance degradation [11]. With the purpose of speeding up RFE, Ha and Nguyen recently put forward the Fast Recursive Feature Elimination (Fast RFE) algorithm [12]. The authors propose to use Parallel Random Forest as the wrapped classifier, and, thus, save model training time.…”

Section: Related Workmentioning

confidence: 99%

“…However, this approach is tied to a concrete learning algorithm and complicates the feature selection process by resorting to distributed cluster computing. Moreover, apart from distributing classifier training, Fast RFE relies on exactly the same iterative process as RFE and removes one feature at a time [12].…”

Section: Related Workmentioning

confidence: 99%

“…Out of several heuristic wrapper selection methods, the Recursive Feature Elimination (RFE) [11] algorithm has received considerable interest. It has been successfully used with various classifiers on biological, chemical, gene-expression, financial, and text data [11,12,16,27]. RFE is a hybrid wrapper-filter algorithm that uses information about feature importance exposed by the wrapped classifier to recursively eliminate the least promising attributes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fibonacci and k-Subsecting Recursive Feature Elimination

Brzeziński¹

2020

Preprint

View full text Add to dashboard Cite

Feature selection is a data mining task with the potential of speeding up classification algorithms, enhancing model comprehensibility, and improving learning accuracy. However, finding a subset of features that is optimal in terms of predictive accuracy is usually computationally intractable. Out of several heuristic approaches to dealing with this problem, the Recursive Feature Elimination (RFE) algorithm has received considerable interest from data mining practitioners. In this paper, we propose two novel algorithms inspired by RFE, called Fibonacci-and k-Subsecting Recursive Feature Elimination, which remove features in logarithmic steps, probing the wrapped classifier more densely for the more promising feature subsets. The proposed algorithms are experimentally compared against RFE on 28 highly multidimensional datasets and evaluated in a practical case study involving 3D electron density maps from the Protein Data Bank. The results show that Fibonacci and k-Subsecting Recursive Feature Elimination are capable of selecting a smaller subset of features much faster than standard RFE, while achieving comparable predictive performance.

show abstract