Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks

Alfaro, Esteban; García, Noelia; Gámez, Matías; Elizondo, David

doi:10.1016/j.dss.2007.12.002

Cited by 249 publications

(125 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As it turns out, the most recent research papers continue to rely on traditional methods: variables are still selected for their performance on univariate statistical tests [38] or as a result of their popularity in the field of financial analysis [39]. Finally, we have shown that healthy companies have a much wider variety of financial profiles than failing firms, as already stated by Pérez [37].…”

Section: Resultsmentioning

confidence: 83%

“…Alfaro et al [39] Variables used in previous studies MLP-BP Altman et al [9] Method and criterion not indicated MLP-BP Anandarajan et al [42] Variables used in previous studies MLP-BP -MLP-GA Back et al [11] Genetic algorithm applied to a set of variables used in previous studies MLP-BP -SOM -BM Back et al [26] Genetic algorithm applied to a set of variables used in studies by Altman [2], Altman [17], Blum [19], Beaver [18], Deakin [20], Merwin [21], Ramser and Foster [22] and five other studies…”

Section: Mlp-bpmentioning

confidence: 99%

“…means that no indication was given. [39] 92.37% 82.20% 87.29% Altman et al [9] 89.40% 86.20% 87.80% Anandarajan et al [42] 93.75% 95.45% 95.19% Back et al [11] 100.00% 98.00% 99.00% Back et al [26] 100.00% 94.25% 97.30% Back et al [27] 100.00% 94.40% 97.30% Bell et al [43] 97.70% 61.80% 94.00% Berg [44] ? ?…”

Section: Mlp-bpmentioning

confidence: 99%

See 2 more Smart Citations

Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Jardin

2010

Neurocomputing

112

View full text Add to dashboard Cite

We evaluate the prediction accuracy of models designed using different classification methods depending on the technique used to select variables, and we study the relationship between the structure of the models and their ability to correctly predict financial failure. We show that a neural network based model using a set of variables selected with a criterion that it is adapted to the network leads to better results than a set chosen with criteria used in the financial literature. We also show that the way in which a set of variables may represent the financial profiles of healthy companies plays a role in Type I error reduction.

show abstract

Section: Resultsmentioning

confidence: 83%

Section: Mlp-bpmentioning

confidence: 99%

See 1 more Smart Citation

Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Jardin

2010

Neurocomputing

112

View full text Add to dashboard Cite

show abstract

“…In turn, neural networks are less accurate than the boosting type of classifier aggregation, as shown by Alfaro et al [8]. Furthermore, the Random Forest classifier [6] has been shown to have good accuracy compared to other classifiers [9] [10].…”

Section: Classifier Algorithmsmentioning

confidence: 99%

Process Prediction in Noisy Data Sets: A Case Study in a Dutch Hospital

Spoel

Keulen

Amrit

2013

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Abstract. Predicting the amount of money that can be claimed is critical to the effective running of an Hospital. In this paper we describe a case study of a Dutch Hospital where we use process mining to predict the cash flow of the Hospital. In order to predict the cost of a treatment, we use different data mining techniques to predict the sequence of treatments administered, the duration and the final "care product" or diagnosis of the patient. While performing the data analysis we encountered three specific kinds of noise that we call sequence noise, human noise and duration noise. Studies in the past have discussed ways to reduce the noise in process data. However, it is not very clear what effect the noise has to different kinds of process analysis. In this paper we describe the combined effect of sequence noise, human noise and duration noise on the analysis of process data, by comparing the performance of several mining techniques on the data.

show abstract

“…Problems of application, advantages and disadvantages of AdaBoost and neural networks are presented in the works (Alfaro, García, Gámez, & Elizondo, 2008;Azmitov, Ivanovskiy, & Korabelnikova, 2014). Dimitras, A. I., Slowinski, R., Susmaga, R., Zopounidis, C. (1999) offer to use rough sets.…”

Section: Introductionmentioning

confidence: 99%

Z-Score for Bankruptcy Forecasting of the Companies Producing Building Materials

Burganova¹,

Salahieva²

2015

ASS

View full text Add to dashboard Cite

The article is dedicated to developing of methodological basis for the probability of enterprises' bankruptcy forecasting. The authors have identified the reasons of the existing bankruptcy forecasting models failure, the necessity of models developing for companies in various industries on the basis of the existing instruments. As a result of the multivariate discriminate analysis we offer Z-scores based on the average annual rates of change and taking into account the peculiarities of the industry companies. The model is developed for companies specializing in the production of building materials, it has a high level of productivity -90.4%.

show abstract

Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks

Cited by 249 publications

References 34 publications

Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Process Prediction in Noisy Data Sets: A Case Study in a Dutch Hospital

Z-Score for Bankruptcy Forecasting of the Companies Producing Building Materials

Contact Info

Product

Resources

About