Why Finance Data Quality Needs Rule Engines, Not ML Hype
Five years inside one of the country’s largest financial systems gave me a view of data quality that doesn’t match the conference pitch. ML didn’t save us. Governance and a rule catalog did.
Most data failures in finance don’t arrive dramatically. They survive quietly long enough to become someone else’s reconciliation issue, reporting error or regulatory escalation. By the time someone notices, the bad data has already left fingerprints on a tax statement, a NAV calculation or a filing that’s now public record.
That’s the part of data quality conferences rarely talk about. When I started my career at a large financial company in 2010, I was the analyst on call for a system that priced billions of dollars in positions every night. Our automated workflows scrubbed 596,000+ attributes across 482,000+ securities. Reference data fed Tax Lot Accounting, the system that produced cost basis, gain and loss numbers and IRS...
Copyright of this story solely belongs to hackernoon.com. To see the full text click HERE
