UK-Based B2B Payments Platform
$2.1M annual compliance savings through automated KYC/AML document processing.
The client operates a B2B payments platform used by approximately 3,200 small and mid-sized businesses across the UK and EU for cross-border transactions. As a company regulated by the FCA, they are required to perform Know Your Customer (KYC) and Anti-Money Laundering (AML) checks on every business onboarding to their platform, and to run periodic re-verification on existing accounts.
At the time of engagement, the compliance team consisted of 14 analysts processing an average of 1,800 KYC applications per month. Each application required manual review of identity documents, proof of address, corporate registration filings, beneficial ownership declarations, and screening against sanctions lists and PEP databases. The average processing time per application was 47 minutes. Approximately 30% of applications required at least one round of follow-up because documents were incomplete, expired, or did not match the information provided during onboarding.
The backlog was a persistent problem. During peak onboarding periods — particularly Q1 and Q4 — the queue regularly exceeded 600 pending applications, pushing average onboarding time past 11 business days. The sales team reported losing an estimated 15-20 prospective clients per quarter who abandoned the process before approval, citing delays. One enterprise deal worth approximately $340,000 in annual transaction volume was lost specifically because the prospect's compliance review took 16 days.
Two prior attempts at automation had stalled. A rules-based document classifier built by the internal engineering team achieved 61% accuracy on document type identification and was abandoned after four months. An evaluation of a third-party KYC-as-a-service provider revealed integration limitations with the client's existing transaction monitoring system and a per-check pricing model that would have increased costs at their volume.
A phased engagement across 14 weeks, starting with the document processing bottleneck and expanding to risk scoring and workflow automation. Each phase was deployed into production against live applications before the next phase began.
Diagnose: Compliance Process Audit (Weeks 1-2)
Two weeks were spent embedded with the compliance team, observing the full lifecycle of 120 applications from submission through approval or rejection. The goal was to identify where analyst time was actually going. The finding was not surprising but it was specific: 58% of total analyst time was consumed by three activities that did not require judgment — verifying document type and completeness, extracting entity names and addresses from corporate filings, and cross-referencing those details against the application form. The remaining 42% involved risk assessment decisions that required human judgment. That split defined the automation boundary.
Design & Deploy: Document AI Pipeline (Weeks 3-7)
A document processing pipeline was built using a combination of OCR, document classification, and entity extraction models. The system was trained on 4,200 historical applications spanning 23 document types across UK, EU, and offshore jurisdictions. The pipeline classified incoming documents by type, extracted key fields (entity name, registration number, address, director names, dates), and performed automated completeness checks against the requirements for each business category. Documents that passed automated validation were routed directly to the risk assessment queue with pre-populated data. Documents that failed were flagged with specific reasons and returned to the applicant with an automated request listing exactly what was missing.
Deploy: Risk Scoring Model (Weeks 7-10)
A risk scoring model was developed using the client's historical decision data — 14,000 completed applications spanning three years. The model produced a risk score based on jurisdiction of incorporation, business type, transaction volume profile, beneficial ownership structure, and screening results. Applications scoring below a calibrated threshold were routed for expedited review with a recommended approval. Applications scoring above the threshold were flagged for enhanced due diligence with specific risk factors highlighted. The model was not designed to replace analyst judgment on risk decisions. It was designed to prioritize the queue and pre-surface the relevant information so that an analyst could reach a decision faster.
Scale: Workflow Integration & Analyst Tooling (Weeks 10-14)
The document pipeline and risk scoring model were integrated into the existing compliance workflow through a custom review interface. Analysts saw each application with documents already classified, key fields extracted and validated, screening results summarized, and a risk score with the factors that drove it. The interface was designed in close collaboration with the compliance lead and three senior analysts, iterated across four rounds of feedback before production deployment. The system did the mechanical work. The analyst made the decision. Average review time for a standard-risk application dropped from 47 minutes to 8 minutes.
$2.1M
Annual compliance cost savings
Through reduced manual processing time and avoided headcount growth
92%
Reduction in manual review time
Average review time from 47 minutes to 8 minutes per application
2.4 days
Average onboarding time
Down from 11 business days
94.3%
Document classification accuracy
Across 23 document types and multiple jurisdictions
73%
Reduction in incomplete submissions
Automated pre-validation catches issues before analyst review
0
Compliance findings in subsequent FCA audit
Full audit trail maintained for every automated and manual decision
The compliance team was restructured from 14 analysts doing mostly document processing to 9 analysts focused on actual risk assessment and complex cases. Five analysts were redeployed to a new transaction monitoring function the company had been unable to staff. The compliance lead noted that analyst retention improved once the repetitive document-checking work, which had driven the highest turnover, was handled by the system. The sales team reported that the faster onboarding cycle was winning them deals in enterprise conversations, and the company closed two accounts in the following quarter that specifically cited onboarding speed during their vendor evaluation.
“We were hiring analysts just to keep the queue from growing. Now the queue barely exists, and the analysts we have are doing work that actually requires their expertise. The FCA audit was the real proof point — every decision had a clean trail, automated or not.”
Head of Compliance, B2B Payments Platform
Compliance team buried in document review?
If your KYC or AML process is bottlenecked by manual work that doesn't require human judgment, we can fix that.