SWIFT MT940 Customer Statement Parser
535,000.00 in end-of-day SWIFT MT940 transactions parsed and normalized across across 2 items.
Parsed credit receipt of EUR 450,000.00. Mapped to Account 1010 / 4010 (SaaS License Revenue).
Method1Parsed Tag 60F, 61, 86, and 62F fields into structured JSON accounting records.
2Validated mathematical balance continuity between opening Tag 60F and closing Tag 62F.
| Reference | Description | Statement_Amount_EUR |
|---|---|---|
| 2605120512CR450000.00NTRFNONREF//CUST-88192 | Customer SaaS License Receipt Tag 61 | 450,000.00 |
| 2605120512DR85000.00NTRFNONREF//SUPP-44102 | Cloud Hosting Vendor Disbursement Tag 61 | 85,000.00 |
Raw SWIFT MT940 text messages with Tag 61 statement lines and Tag 86 transaction details
Normalized ISO 20022 CAMT.053 XML payload and general ledger bank reconciliation schedule (Resolution Dossier, Findings Schedule)
Open SWIFT MT940 Customer Statement Parser on sample data now with no sign-up, then run your own files free for 14 days. $3,000 a month after that, cancel any time. 30% goes to the referring partner.
Read in memory for the session, never stored, never used to train a model.
Outputs are computed from your inputs and the tool's rules. Check them before you rely on them.
14 days on your own files, then $3,000 a month.
Open SWIFT MT940 Customer Statement Parser on sample data now with no sign-up, then run your own files free for 14 days. $3,000 a month after that, cancel any time.
On a sample file: 535,000.00 in end-of-day SWIFT MT940 transactions parsed and normalized across across 2 items.
Why not just use ChatGPT?
Rules that stay current: the rate cards, tariffs, code sets and regulations it checks against are kept up to date for you; a one-off prompt starts from nothing each time. Evidence that stands up: every finding cites the line, the file and the rule, so it holds up with a vendor, a payer or an auditor. The same answer every time: the checks are written rules, not a fresh guess, so this month's result can be compared with last month's. Nobody has to own it: no one inside has to build, test and maintain a home-made tool, and files are not pasted into a public chatbot.
Start on your own files
If you would rather talk it through, write to dev.sathya@baseloom.app; that reaches Dev Sathya, founder.