Detecting financial restatements using data mining techniques

作者：

Highlights：

• Both intentional and unintentional restatements may destroy shareholders value.

• Financial restatements (intentional/unintentional) detection models are developed.

• Performance of all widely used data mining techniques are compared.

• A reduced set of significant attributes are identified for predicting restatements.

• Class imbalance and cost imbalance issues are addressed.

摘要

•Both intentional and unintentional restatements may destroy shareholders value.•Financial restatements (intentional/unintentional) detection models are developed.•Performance of all widely used data mining techniques are compared.•A reduced set of significant attributes are identified for predicting restatements.•Class imbalance and cost imbalance issues are addressed.

论文关键词：Data mining,Financial restatements,Decision tree (DT),Artificial neural network (ANN),Naïve Bayes (NB),Support vector machine (SVM)

论文评审过程：Received 24 January 2017, Revised 13 August 2017, Accepted 14 August 2017, Available online 16 August 2017, Version of Record 24 August 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.08.030