Cost-sensitive ensemble methods for bankruptcy prediction in a highly imbalanced data distribution: a real case from the Spanish market

Ghatasheh, Nazeeh; Faris, Hossam; Abukhurma, Ruba; Castillo, Pedro; Al-Madi, Nailah; Mora, Antonio M.; Al-Zoubi, Ala’ M.; Hassanat, Ahmad B. A.

doi:10.1007/s13748-020-00219-x

Cited by 32 publications

(31 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it can be seen in the table, the outputs obtained by MLP-6L + SMOTE-ENN clearly outperform the rest of results obtained by previous approaches, regarding the bankruptcy prediction and misprediction, according to Accuracy, Recall and Type II error metrics. Our tested approach outperformed even the most promising approaches proposed in our most recent paper in this scope [36].…”

Section: Comparison With the State Of The Artmentioning

confidence: 68%

“…However, in recent studies, ML algorithms showed better performance than the statistical models concerning bankruptcy prediction [35]. For this reason, many researchers have considered it as a classification problem, and have applied standard ML classification or regression methods for prediction [4], [10], [36]- [38].…”

Section: Related Workmentioning

confidence: 99%

“…In that study, AdaBoost showed higher performance than the rest of classifiers applied to the imbalanced dataset without using data resampling techniques, but it did not provide a considerable alternative to use the balancing techniques. Finally, [36] compared the performance of combining three costsensitive methods, with several ensemble classifiers. The combination of RF with cost-sensitive classification methods outperformed the rest.…”

Section: Related Workmentioning

confidence: 99%

“…Once we have tested the DL and ensemble methods together with the data balancing techniques, we aim now to compare the most effective ones with previous algorithms/results of the state of the art working with the same datasets considered First, focusing on the Spanish companies' dataset, Table 15 presents a comparison between the best approach selected in this work (MLP-6L + SMOTE-ENN) and the best algorithms or combinations found in five previous works, namely: [4], [5], [7], [36], [46]. In [4], the superior classifier was RF applied to the Spanish dataset balanced using a technique based on dividing the dataset into subsets, which were balanced using a simple oversampling approach.…”

Section: Comparison With the State Of The Artmentioning

confidence: 99%

“…It also outperformed the results of using this combination with five different Feature Selection approaches. Finally, in [36], the combination of RF with a Cost-Sensitive Classification (CSC) method outperformed many other ensemble and cost-sensitive methods.…”

Section: Comparison With the State Of The Artmentioning

confidence: 99%

See 4 more Smart Citations

Comparing the Performance of Deep Learning Methods to Predict Companies’ Financial Failure

et al. 2021

Self Cite

View full text Add to dashboard Cite

One of the most crucial problems in the field of business is financial forecasting. Many companies are interested in forecasting their incoming financial status in order to adapt to the current financial and business environment to avoid bankruptcy. In this work, due to the effectiveness of Deep Learning methods with respect to classification tasks, we compare the performance of three well-known Deep Learning methods (Long-Short Term Memory, Deep Belief Network and Multilayer Perceptron model of 6 layers) with three bagging ensemble classifiers (Random Forest, Support Vector Machine and K-Nearest Neighbor) and two boosting ensemble classifiers (Adaptive Boosting and Extreme Gradient Boosting) in companies' financial failure prediction. Because of the inherent nature of the problem addressed, three extremely imbalanced datasets of Spanish, Taiwanese and Polish companies' data have been considered in this study. Thus, five oversampling balancing techniques, two hybrid balancing techniques (undersampling-oversampling) and one clustering-based balancing technique have been applied to avoid this data inconsistency problem. Considering the real financial data complexity level and type, the obtained results show that Multilayer Perceptron model of 6 layers, in conjunction with SMOTE-ENN balancing method, yielded the best performance according to the Accuracy, Recall and Type II error metrics. In addition, Long-Short Term Memory, Multilayer Perceptron and ensemble methods obtained also very good results, outperforming several classifiers used in previous studies with the same datasets.INDEX TERMS Economic forecasting, classification algorithms, machine learning, deep learning, data balancing.

show abstract

Section: Comparison With the State Of The Artmentioning

confidence: 68%