Transaction risk with a random forest
A real random forest trains in your browser, ranks its features and scores live transactions at the threshold you choose.
The same modelling approach we use for transaction studies and anomaly detection. All data on this page is synthetic and generated in your browser.
How it works
- 01
Synthetic transactions with amount, hour, beneficiary, country risk, velocity and account age.
- 02
Each tree trains on a bootstrap sample with a random subset of features.
- 03
Feature importance comes from the impurity each feature removes.
- 04
Move the threshold to trade precision against recall and watch the confusion matrix.
Bank-to-ledger reconciliation
Four matching passes clear a month of bank lines against the general ledger and leave only true exceptions.
Accounts payable automation
Invoices are captured, read, three-way matched against PO and goods receipt, and routed for approval.
Cash application for receipts
Incoming payments are applied to open invoices by reference, exact amount or combination, with partials tracked.
GL variance analysis
Actual against budget for every GL line, anomalies flagged by statistics, and the commentary written for you.
Report migration between warehouses
Legacy SQL reports are parsed, mapped to the new model and chart of accounts, and tied out to the fils.
Synthetic customer data generator
Learn the shape of a customer table, generate new rows that keep it, and prove no real record was copied.
- 01
Tell us the problem
A short call or email on what you want built, fixed or automated.
- 02
We scope it together
A discovery session with your people and your data, then a fixed scope and price.
- 03
See it working
A working prototype on your real case before you commit to the full build.
