Earticle

초록

영어

In the era of stringent and dynamic business environment, it is crucial for organizations to foresee their clients’ delinquency behavior. Such environment and behavior create unreliable base for strategic planning and risk management. Business Analytics combines the business expertise and computer intelligence to assist the decision makers by predicting an individual's credit status. This empirical research aims to evaluate the performance of different Machine Learning algorithms for credit risk prediction with more focus on Random Forest Trees. Several experiments inspired by observation and literature illustrate the potentials of computer-based model in classifying a number of bank history records. However, enhanced classification outcomes require tuning the randomness and tree growing parameters of the Random Forests algorithm. The model based on Random Forest Trees overperformed most of the other models. Moreover, such a model has various advantages to business experts as the ability to help in understanding the relations between the analyzed attributes.

목차

Abstract
 1. Introduction
 2. Related Work
 3. Random Forest Trees
 4. Data and Methodology
 5. Results and Discussion
  5.1. Tuning of the Parameters
  5.2. Comparison
 6. Conclusions and Future Work
 Acknowledgements
 References

키워드

저자

• Nazeeh Ghatasheh [ Department of Business Information Technology, The University of Jordan ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Science and Technology

• 간기

  월간

• pISSN

  2005-4238

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605