Forvis Mazars
04 / 09

JEDI

Journal Entries Detection & Insights. Find the dark side of the ledger

MAM: Fraud: Journal Entries Testing
ISA: ISA 240
Module: operations.audit.jedi

Mission

This programme is an ABI module with its own agent and Nexus app. Production tooling for each sub-solution is not built yet. The list below is the mission contract from the digested catalog.

Sub-solutions (4)

Task-skill pairs (18)

IDSub-solutionTaskSkill
JR-01JEDI.RuleScoreExtract and structure the full GL journal entry population from client ERP/accounting systemGLExtractionSkill
JR-02JEDI.RuleScoreApply ISA 240 non-standard entry criteria: outside business hours, round amounts, unusual account combinations, entries by unusual users, reversing entries, entries near period-endNonStandardEntryDetectorSkill
JR-03JEDI.RuleScoreFlag entries posting to sensitive account combinations (e.g. revenue-to-liability, expense-to-equity, intercompany with unusual counterparties)SensitiveAccountComboSkill
JR-04JEDI.RuleScoreScore each entry with a composite rule-based risk score and produce a ranked population for auditor selectionRuleScoreAggregatorSkill
JS-01JEDI.StatScoreApply Benford's Law analysis to first and second digit distributions of journal entry amountsBenfordAnalysisSkill
JS-02JEDI.StatScoreDetect distributional outliers in amounts, frequencies and timing using Z-score and IQR methodsDistributionalOutlierSkill
JS-03JEDI.StatScoreAnalyse posting frequency patterns by user and account to detect unusual activity spikesFrequencyPatternSkill
JC-01JEDI.ClusterScoreFeature engineering: build multi-dimensional entry feature vectors (amount, timing, user, account type, description embedding, system/manual, reversal flag)FeatureEngineeringSkill
JC-02JEDI.ClusterScoreRun k-means clustering to identify natural posting behaviour clusters and find entries far from cluster centroidsKMeansClusteringSkill
JC-03JEDI.ClusterScoreRun DBSCAN to identify low-density entry groups that do not fit any natural clusterDBSCANSkill
JC-04JEDI.ClusterScoreRun Isolation Forest to score each entry by how easily it can be isolated from the populationIsolationForestSkill
JC-05JEDI.ClusterScoreApply ensemble voting: only flag entries anomalous in at least 2 of the 3 clustering methods to reduce false positivesEnsembleVotingSkill
JC-06JEDI.ClusterScoreContextual enrichment: cross-reference flagged entries with authorisation logs and ERP workflow data to filter explainable outliersContextualEnrichmentSkill
JC-07JEDI.ClusterScoreApply relative rarity scoring: compute outlier score relative to entity's own baseline, not external normsRelativeRarityScorer
JC-08JEDI.ClusterScoreHuman-in-the-loop calibration: feed auditor accept/reject decisions back to recalibrate cluster boundaries for subsequent yearsSemiSupervisedCalibrationSkill
JI-01JEDI.InsightTranslate cluster/statistical anomaly outputs into plain-language audit findingsAnomalyNarratorSkill
JI-02JEDI.InsightPopulate the journal entry testing working paper template with flagged items, scores and descriptionsWPDrafterSkill
JI-03JEDI.InsightRecommend next audit steps based on identified anomaly patterns (e.g. cluster of year-end revenue entries → consider additional revenue cut-off procedures)NBASuggesterSkill

Back to the nine programmes