
π¦ Finance & Banking Β· Data Flow
How a bank scores every transaction for fraud in milliseconds: features from history, an ML model, rules, and a case queue for analysts.
Opening a template is free and never counts toward your daily diagrams. Asking the AI to change it counts as one.
Drawing diagramβ¦
Data flow for real-time fraud detection: card and UPI transactions stream through Kafka to a scoring service, which pulls features (spend velocity, device, location, merchant risk) from a feature store, runs an ML model and business rules, and returns approve, decline or step-up authentication to the payment switch. High-risk cases go to an analyst case queue; analyst decisions are labelled and feed model retraining. Number the processes and label every flow.
flowchart LR
subgraph EXT ["External entities"]
payment_switch["Payment Switch"]
fraud_analyst["Fraud Analyst"]
end
subgraph PROC ["Processes"]
p1("1.0 Ingest transaction stream")
p2("2.0 Fetch transaction features")
p3("3.0 Evaluate fraud risk")
p4("4.0 Route high-risk cases")
p5("5.0 Review and label cases")
p6("6.0 Retrain ML model")
end
subgraph STORE ["Data stores"]
d1[("D1 Kafka Transaction Stream")]
d2[("D2 Feature Store")]
d3[("D3 Analyst Case Queue")]
d4[("D4 Labelled Fraud Dataset")]
d5[("D5 ML Model Registry")]
end
payment_switch -- "Raw transaction stream data" --> p1
p1 -- "Streamed transaction data" --> d1
d1 -- "Real-time transaction event" --> p2
d2 -- "Spend velocity, device, location, and merchant risk features" --> p2
p2 -- "Enriched feature vector" --> p3
d5 -- "Trained ML model parameters" --> p3
p3 -- "Transaction decision (Approve, Decline, Step-Up)" --> payment_switch
p3 -- "High-risk transaction score and details" --> p4
p4 -- "Flagged case record" --> d3
d3 -- "Pending case data" --> p5
p5 -- "Analyst decision and investigation label" --> d4
p5 -- "Manual review outcome" --> fraud_analyst
fraud_analyst -- "Case disposition and analyst label" --> p5
d4 -- "Historical labelled transaction data" --> p6
p6 -- "Updated ML model artifact" --> d5A data flow diagram with 8 processes and outside parties, 5 data stores and 15 data flows.
Describe your own system in plain English and CloudSketch AI draws it in seconds. See all AI diagram generators.
The steps behind a UPI payment: the payer's app, the payer's bank, NPCI's UPI switch and the payee's bank, from entering a UPI ID to the money arriving.
A payment gateway that lets online merchants accept cards and UPI: the checkout, the payment core with fraud checks, and the card networks and banks it connects to.
A personal loan from application to disbursal: KYC, credit bureau check, underwriting rules, manual review for borderline cases, and the final agreement.
What happens in the second after a card is tapped or entered online: the acquirer, card network and issuing bank authorise the payment, with 3-D Secure for online payments.
The main building blocks of a bank's core platform: accounts, deposits, loans, payments and the general ledger, used by branches, internet banking and mobile.
How a bank or fintech opens an account fully online: Aadhaar/PAN verification, video KYC, risk checks and account creation.