Rule Engine
25 rules: duplicate IDs, velocity spikes, amount clustering near approval thresholds, blacklist matching, and cross-field conditional logic. Outputs: rule_score (0–100) + reason.
Upload a CSV or Excel ledger. Auraium runs 25+ detection rules, statistical outlier scoring, and unsupervised ML — then delivers plain-English audit reports in under 60 seconds.
Fast, deterministic checks for known suspicious patterns (duplicates, blacklisted accounts, threshold breaches).
Robust outlier scoring using distribution-aware math for volume, frequency and velocity deviations.
Models identify complex patterns and subtle fraud that rules miss — continuously improving with data.
Auraium auto-detects your ledger type and adapts the entire pipeline — rules, statistical baselines, ML features, enrichment context, and LLM prompts — to match.
Detect counterparty fraud, velocity spikes, pass-through structuring, round-amount patterns, and weekend anomalies.
Flag journal entry anomalies, period-end manipulation, unusual department-account combinations, and misclassification risk.
Catch duplicate invoices, invoice splitting near approval thresholds, first-time vendor fraud, and vendor concentration risk.
Identify revenue recognition anomalies, fictitious customers, credit manipulation, and collection irregularities.
Surface personal charges, duplicate reimbursements, round-amount padding, and out-of-policy spending patterns.
Flag timing gaps, unreconciled items, unusual sweep patterns, and discrepancies between bank and book balances.
Detect phantom inventory, unusual write-offs, valuation irregularities, and misclassified capital vs. operating expenditure.
Catch ghost employees, duplicate pay runs, excessive overtime, and compensation deviating from peer benchmarks.
Not sure which type? Upload anything — Auraium classifies your ledger automatically and applies the right detection profile.
Three phases run in sequence. Within Phase 2, all three detection engines run in parallel — their scores fused by the Decision Engine.
Auto-detect CSV or Excel. Normalize columns, validate schema, map to standard fields.
Identify: Bank Statement, General Ledger, or Accounts Payable. All downstream stages adapt accordingly.
25 rules: duplicates, velocity spikes, threshold clustering, blacklist matching, cross-field logic.
4-method ensemble — rolling z-score (40%), personal baseline (40%), peer group (15%), velocity (5%).
Isolation Forest + PCA reconstruction. Unsupervised — no labeled training data required.
90-day account baselines, counterparty history, new-party flag, pass-through & velocity enrichment.
Agreement amplifier: 3 detectors = 1.6× boost, 2 = 1.3×. Flag rate capped between 0.1%–5%.
3-tier recheck: heuristics → small ML → LLM. Each flagged transaction is confirmed or cleared.
8-field audit report: tldr, what happened, why unusual, red flags, data gaps, verdict, action, next steps.
Scroll through the five core engines — each outputs a score, a reason, and contributes to the final decision.
Every flagged transaction gets a structured 8-field report — written in plain English, not jargon.
"₹1,20,000 payment — 12× this account's typical transaction size — sent to a first-time counterparty on a weekend."
We minimize data shared with external services and always prefer on-premise or private inference for sensitive fields.
Only column headers, metadata tags, and hashed IDs are sent to external services. Raw PII — names, account numbers — is never sent without being obfuscated, and only when explicitly allowed.
Rule and statistical engines run entirely on your infrastructure. If cloud ML is used, data is pseudonymized before leaving your environment, and no transaction data is retained after processing.
Every LLM call is logged with a prompt hash, model version, and minimal field bleed. You can reproduce any explanation, verify any decision, and export a full audit trail per run.
If automatic mapping fails, Auraium will (optionally) call an internal LLM helper with only column names — not values — to suggest mappings. You always see suggested mappings before they’re applied.
Auraium tracks precision, recall, and false positive rate per rule and per model. You can view suite-level metrics on the dashboard and set thresholds to meet your tolerance.
Yes — Auraium supports on-premise models and private inference. Cloud ML is optional and used only after explicit configuration.