Audit Data Analytics (ADA)
Use of technology and data to identify anomalies
Descriptive Analytics
Explains what happened using summaries
Diagnostic Analytics
Explains why something happened through relationships
Predictive Analytics
Forecasts potential future outcomes based on historical data patterns.
Prescriptive Analytics
Suggests actions or responses to achieve desired results
Continuous Auditing
Automated real-time testing of transactions and controls to detect irregularities.
Continuous Monitoring
Management-driven monitoring process to identify emerging issues early.
Data Extraction
Pulling data from client systems such as general ledger
Data Cleaning
Correcting
Data Visualisation
Using dashboards
Full Population Testing
Examining entire datasets instead of samples for higher audit assurance.
Stratification
Dividing data into categories or risk bands to isolate unusual transactions.
Outlier Analysis
Identifying transactions that deviate from normal patterns (e.g.
Correlation Testing
Examining relationships between datasets to detect inconsistencies or fraud risk.
Benford’s Law
Mathematical law stating that in naturally occurring datasets
Benford’s Law in Auditing
Used to detect data manipulation or fraud by comparing actual digit distribution to expected Benford distribution.
Expected First-Digit Frequencies (Benford)
1=30.1%
Benford’s Law Application
Applied to expense accounts
Advantages of Benford Testing
Quickly flags anomalies across large datasets and provides quantitative fraud indicators.
Limitations of Benford Testing
Not effective for small or restricted datasets
ADA Tools
Software like IDEA
Data Integrity
Ensuring extracted data matches original records to maintain reliability.
ADA Advantages
Improves risk targeting
ADA Challenges
Requires data literacy
