A Full Population Auditing Method Based on Machine Learning

Abstract

As it is urgent to change the traditional audit sampling method that is based on manpower to meet the growing audit demand in the era of big data. This study uses empirical methods to propose a full population auditing method based on machine learning. This method can extend the application scope of the audit to all samples through the self-learning feature of machine learning, which helps to address the dependence on auditors’ personal experience and the audit risks arising from audit sampling. First, this paper demonstrates the feasibility of this method, then selects the financial data of a large enterprise for full population testing, and finally summarizes the critical steps of practical applications. The study results indicate that machine learning for full population auditing is able to detect, in all samples, abnormal business whose execution does not adhere to existing accounting rules, as well as abnormal business with irregular accounting rules, thus improving the efficiency of internal control audits. By combining the learning ability of machine-learning algorithms and the arithmetic power of computers, the proposed full population auditing method provides a feasible approach for the intellectual development of future auditing at the application level.

Sampling Audit Evidence Using a Naive Bayes Classifier

“…Their goal was to develop unique sampling methods for improving the performance of machine learning algorithms in solving specific problems (e.g., [3]). Some studies (e.g., [4]) suggested sampling with machine learning in auditing; moreover, only some researchers (e.g., [5]) have indeed implemented machine learning-based sampling in auditing.…”

Symmetrical and Asymmetrical Sampling Audit Evidence Using a Naive Bayes Classifier

“…If the purpose is to improve the efficiency of auditing, some published studies (e.g., [5]) integrated machine learning with sampling for detecting anomalies. For example, Chen et al [5] selected the ID3, CART, and C4.5 algorithms to find anomalies in financial transactions.…”

“…If the purpose is to improve the efficiency of auditing, some published studies (e.g., [5]) integrated machine learning with sampling for detecting anomalies. For example, Chen et al [5] selected the ID3, CART, and C4.5 algorithms to find anomalies in financial transactions. Their results indicated that a machine learning algorithm can simplify the audit of financial transactions by efficiently exploring their attributes.…”

“…Many published studies (e.g., [3][4][5]) attempted to integrate machine learning with sampling; however, the research interest of most was not auditing. Their goal was to develop unique sampling methods for improving the performance of machine learning algorithms in solving specific problems (e.g., [3]).…”

“…Their goal was to develop unique sampling methods for improving the performance of machine learning algorithms in solving specific problems (e.g., [3]). Some studies (e.g., [4]) suggested sampling with machine learning in auditing; moreover, only some researchers (e.g., [5]) have implemented machine-learning-based sampling in auditing.…”