Automation of Audit Sampling Using Rule-Based Decision Systems

Sathiri Dhanaraj

Abstract: Automation of Audit Sampling Using Rule-Based Decision Systems: an objective, scholarly analysis of automated sampling approaches, evidence-based assessment, and formal structure. Automation and computerization in auditing are ubiquitous and offer unparalleled assistance to auditors in improving efficiency, effectiveness, and overall cost. Audit sampling is an effective means to make audit decisions based on part of the evidence rather than the whole. Rule-based decision systems are popular in many business and accounting areas, but not widely deployed for audit sampling yet. Audit sampling can be automated by creating sampling rules based on audit data, professional guidelines, and/or judgment. Such rules specify sampling conditions and thresholds, the population elements that trigger the rule-set, the sampling specification produced, and the sample sizes required and whether the auditor should consider additional information of other related decisions. The approach also supports a human-in-the-loop function, providing the auditor with automation assistance but allowing judgment to deviate from the rules. The extent of automation can vary to meet auditors? needs and is not limited only to the mention mode of rule-based systems. Effectiveness and efficiency can be evaluated in terms of accuracy, coverage, false positives, false negatives, processing time, and resource utilization.

Keywords: Automated Audit Sampling, Rule-Based Decision Systems, Audit Automation, Computerized Auditing, Evidence-Based Audit Methods, Sampling Rule Design, Audit Decision Support, Professional Judgment Integration, Human-In-The-Loop Auditing, Sampling Threshold Specification, Audit Data Analytics

How to Cite?: Sathiri Dhanaraj, "Automation of Audit Sampling Using Rule-Based Decision Systems", Volume 10 Issue 12, December 2021, International Journal of Science and Research (IJSR), Pages: 1660-1667, https://www.ijsr.net/getabstract.php?paperid=MS2112181638, DOI: https://dx.doi.org/10.21275/MS2112181638