Credit rating by hybrid machine learning techniques

Tsai, Chih‐Fong; Chen, Ming-Lun

doi:10.1016/j.asoc.2009.08.003

Cited by 147 publications

(99 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case we make use of HFT trade data from a set of stocks listed on the London Stock Exchange and investigate a combination of technical rules on 2 minute returns with holding periods ranging between 2 to 10 minutes. Contrary to findings in AI surveys (Tsai and Wang, 2009;Krollner et al, 2010), we align ourselves with the priorities of investors and regulators and focus on comparing the proposed models using risk-adjusted performance (Choey and Weigend, 1997;Xufre Casqueiro and Rodrigues, 2006;Vanstone and Finnie, 2010). We are not aware of any previous studies which investigate the link between higher order fuzzy systems and riskadjusted performance.…”

Section: A C C E P T E D Mmentioning

confidence: 95%

“…Another important consideration when selecting stocks for back-testing purposes is the importance of picking a mix of stocks which exhibit different trends. As can be seen from the numerous machine learning and artificial intelligence studies surveyed in Krollner et al (2010) and Tsai and Wang (2009), this is rarely considered. Pardo (2011) warns that including only stocks that follow similar trends can lead to ungeneralised models which work in specific scenarios only, hence introducing a bias in the experiment results.…”

Section: Datamentioning

confidence: 99%

“…Surveys (Krollner et al, 2010;Tsai and Wang, 2009) show that the great majority of machine learning studies with application to trading applications focus on the minimisation of error functions, directional accuracy or else profitability (issues with these measures are discussed in Brabazon and O'Neill, 2006;Pardo, 2011;Vella and Ng, 2014b). The danger with error functions is that a small error does not necessarily translate into profitability since it does not reflect the direction.…”

Section: Performance Measuresmentioning

confidence: 99%

“…Unfortunately, surveys show that the great majority of computational finance research disregards the essential requirement that an investor always measures investment returns in line with risk measures in order to compare relative trading performance (Tsai and Wang, 2009;Krollner et al, 2010). A higher return trading strategy does not necessarily outperform other strategies if the associated risk is also substantially higher.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving risk-adjusted performance in high frequency trading using interval type-2 fuzzy logic

Vella

2016

Expert Systems with Applications

View full text Add to dashboard Cite

Highlights• We investigate the viability of Type-2 fuzzy systems in high frequency trading.• We propose Type-2 models based on a generalisation of the popular ANFIS model.• Type-2 models score significant risk adjusted performance improvements over Type-1.• Benefits of Type-2 models increase with higher trading frequencies. AbstractIn this paper, we investigate the ability of higher order fuzzy systems to handle increased uncertainty, mostly induced by the market microstructure noise inherent in a high frequency trading (HFT) scenario. Whilst many former studies comparing type-1 and type-2 Fuzzy Logic Systems (FLSs) focus on error reduction or market direction accuracy, our interest is predominantly risk-adjusted performance and more in line with both trading practitioners and upcoming regulatory regimes. We propose an innovative approach to design an interval type-2 model which is based on a generalisation of the popular type-1 ANFIS model. The significance of this work stems from the contributions as a result of introducing type-2 fuzzy sets in intelligent trading algorithms, with the objective to improve the risk-adjusted performance with minimal increase in the design and computational complexity. Overall, the proposed ANFIS/T2 model scores significant performance improvements when compared to both standard ANFIS and Buy-and-Hold methods. As a further step, we identify a relationship between the increased trading performance benefits of the proposed type-2 model and higher levels of microstructure noise. The results resolve a desirable need for practitioners, researchers and regulators in the design of expert and intelligent systems for better management of risk in the field of HFT.

show abstract

Section: A C C E P T E D Mmentioning

confidence: 95%

Section: Datamentioning

confidence: 99%

Section: Performance Measuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving risk-adjusted performance in high frequency trading using interval type-2 fuzzy logic

Vella

2016

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…First using Cart, then using Mart and at last using grid search for model variable improvement. Tsai and Chen [23] present four hybrid credit scoring model and compare the performance of these hybrid models. Motivated by the hybrid model, integrating multiple classifier into aggregated output, ensemble learning, has been turned out to be an efficient method for achieving high classification performance.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Support Vector Machine Ensemble Model for Credit Scoring

Ghodselahi¹

2011

IJCA

View full text Add to dashboard Cite

Credit risk is the most challenging risk to which financial institution are exposed. Credit scoring is the main analytical technique for credit risk assessment. In this paper a hybrid model for credit scoring is designed which applies ensemble learning for credit granting decisions. The hybrid model combines clustering and classification techniques. Ten Support Vector Machine (SVM) classifiers are utilized as the members of ensemble model. Since even a small improvement in credit scoring accuracy causes significant loss reduction, then the application of ensemble in hybrid model leads to better performance of classification. A real dataset is used to test the model performance. The test results shows that proposed hybrid SVM ensemble has better classification accuracy when compared with other methods.

show abstract

Modeling credit risk with a multi‐stage hybrid model: An alternative statistical approach

Uddin

Chi

Janabi

et al. 2022

Journal of Forecasting

View full text Add to dashboard Cite

This paper examines the impact of hybridizations on the classification performances of sophisticated machine learning classifiers such as gradient boosting (GB, TreeNet ® ) and random forest (RF) using multi-stage hybrid models. The empirical findings confirm that, overall, hybrid model GB (X* Di ; Ŷ Di, LR ), which consists of TreeNet ® combined with logistic regression along with a new dependent variable, offers significantly superior accuracy compared to the baselines and other hybrid classifiers. However, the performances of hybrid classifiers are not consistent across all types of datasets. For low-dimensional data, the constructed models consistently outperform the base classifiers; however, on high dimensional data, the classification outcomes provide little evidence of improvement and in certain cases, they underperform the baseline models. These findings have relevance for the analysis of high-and lowdimensional credit risk, small and medium enterprises, agricultural credits, and so on. Furthermore, the example credit risk scenario and its outcomes provide an alternative path for hybrid and machine learning approaches to be applied to more general applications in accounting and finance fields.

show abstract

Credit rating by hybrid machine learning techniques

Cited by 147 publications

References 18 publications

Improving risk-adjusted performance in high frequency trading using interval type-2 fuzzy logic

Improving risk-adjusted performance in high frequency trading using interval type-2 fuzzy logic

A Hybrid Support Vector Machine Ensemble Model for Credit Scoring

Modeling credit risk with a multi‐stage hybrid model: An alternative statistical approach

Contact Info

Product

Resources

About