Payment Processing Basics

TL;DR: We built a transformer-based payments foundation model. It works. For years, Stripe has been using machine learning models trained on discrete features (BIN, zip, payment method, etc.) to improve our products for users. And these feature-by-feature efforts have worked well: +15% conversion, -30% fraud. But these models have limitations. We have to select (and therefore constrain) the features considered by the model. And each model requires task-specific training: for authorization, for fraud, for disputes, and so on. Given the learning power of generalized transformer architectures, we wondered whether an LLM-style approach could work here. It wasn’t obvious that it would—payments is like language in some ways (structural patterns similar to syntax and semantics, temporally sequential) and extremely unlike language in others (fewer distinct ‘tokens’, contextual sparsity, fewer organizing principles akin to grammatical rules). So we built a payments foundation model—a self-supervised network that learns dense, general-purpose vectors for every transaction, much like a language model embeds words. Trained on tens of billions of transactions, it distills each charge’s key signals into a single, versatile embedding. You can think of the result as a vast distribution of payments in a high-dimensional vector space. The location of each embedding captures rich data, including how different elements relate to each other. Payments that share similarities naturally cluster together: transactions from the same card issuer are positioned closer together, those from the same bank even closer, and those sharing the same email address are nearly identical. These rich embeddings make it significantly easier to spot nuanced, adversarial patterns of transactions; and to build more accurate classifiers based on both the features of an individual payment and its relationship to other payments in the sequence. Take card-testing. Over the past couple of years traditional ML approaches (engineering new features, labeling emerging attack patterns, rapidly retraining our models) have reduced card testing for users on Stripe by 80%. But the most sophisticated card testers hide novel attack patterns in the volumes of the largest companies, so they’re hard to spot with these methods. We built a classifier that ingests sequences of embeddings from the foundation model, and predicts if the traffic slice is under an attack. And it does this all in real time so we can block attacks before they hit businesses. This approach improved our detection rate for card-testing attacks on large users from 59% to 97% overnight. Perhaps even more fundamentally, it suggests that payments have semantic meaning. Just like words in a sentence, transactions possess complex sequential dependencies and latent feature interactions that simply can’t be captured by manual feature engineering. Turns out attention was all payments needed!

Stripe 𝗯𝘂𝗶𝗹𝘁 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝘁𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿 𝗺𝗼𝗱𝗲𝗹 𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗼𝗻 𝗽𝗮𝘆𝗺𝗲𝗻𝘁 𝗱𝗮𝘁𝗮! Not for text and NOT for code, BUT for billions of payments. Think GPT, but instead of learning language, it learned the structure, behavior, and patterns behind every transaction: ⬇️ 𝗛𝗲𝗿𝗲 𝗶𝘀 𝘄𝗵𝗮𝘁 Stripe 𝗷𝘂𝘀𝘁 𝗱𝗶𝗱? For years, Stripe used traditional ML — separate models for fraud, disputes, and authorizations. Each one relied on handpicked features like BIN codes, ZIP codes, email addresses, and payment methods. That worked — but it was narrow, manually intensive, couldn’t scale and most importantly, it missed the bigger picture. So Stripe trained a transformer, just like GPT — but instead of learning language, it learned from billions of transactions. Each payment — from a coffee in Paris to a subscription in Tokyo — was turned into a dense vector: a numerical fingerprint capturing its behavior and context. 𝗧𝗵𝗲 𝗼𝘂𝘁𝗰𝗼𝗺𝗲? ➜ Transactions with similar behavior cluster naturally — by issuer, merchant, location, or risk ➜ Suspicious patterns emerge organically — without handcrafted rules ➜ Fraud becomes easier to detect — not because it was labeled, but because it’s "understood" This foundation model captures now the structure and relationships between transactions — in real time — the way GPT models understand the flow of words in a sentence. Stripe no longer needs a different model for every use case. They’ve built one that generalizes across many — and keeps learning. 𝗧𝗵𝗲 𝗿𝗲𝘀𝘂𝗹𝘁? They tested it on one of the hardest problems in the space: Card testing attacks that hide in legitimate traffic. ➜ Traditional ML: 59% detection ➜ Transformer-based model: 97% — overnight Visionary work by Stripe! BUT this approach has implications far beyond payments. Great example to see that foundation models aren’t limited to text. The next phase of AI will probably focus more on transformer architectures trained on high-value, underexplored data domains: transactions, supply chains, behavioral signals, scientific processes — even spreadsheets. 𝗜 𝗮𝗺 𝗽𝗿𝗲𝘁𝘁𝘆 𝘀𝘂𝗿𝗲 𝘄𝗲 𝘄𝗶𝗹𝗹 𝘀𝗲𝗲 𝗺𝘂𝗰𝗵 𝗺𝗼𝗿𝗲 𝗱𝗼𝗺𝗮𝗶𝗻-𝘀𝗽𝗲𝗰𝗶𝗳𝗶𝗰 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀 — 𝗽𝘂𝗿𝗽𝗼𝘀𝗲-𝗯𝘂𝗶𝗹𝘁 𝘁𝗼 𝗼𝗽𝗲𝗿𝗮𝘁𝗲 𝗶𝗻𝘀𝗶𝗱𝗲 𝗰𝗼𝗺𝗽𝗹𝗲𝘅 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗹𝗶𝗸𝗲 𝗳𝗶𝗻𝗮𝗻𝗰𝗲, 𝗵𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲, 𝗮𝗻𝗱 𝗲𝗻𝗲𝗿𝗴𝘆. 𝗙𝗼𝗿 𝘆𝗲𝗮𝗿𝘀, 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗵𝗮𝘀 𝗯𝗲𝗲𝗻 𝗳𝗼𝗰𝘂𝘀𝗲𝗱 𝗼𝗻 𝗹𝗮𝗯𝗲𝗹𝗶𝗻𝗴 𝗽𝗿𝗼𝗯𝗹𝗲𝗺𝘀. 𝗡𝗼𝘄, 𝘄𝗲'𝗿𝗲 𝗲𝗻𝘁𝗲𝗿𝗶𝗻𝗴 𝗮 𝗽𝗵𝗮𝘀𝗲 𝘄𝗵𝗲𝗿𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝗯𝗲𝗴𝗶𝗻 𝘁𝗼 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱 𝘁𝗵𝗲𝗺 — 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗮𝗹𝗹𝘆, 𝗰𝗼𝗻𝘁𝗲𝘅𝘁𝘂𝗮𝗹𝗹𝘆, 𝗮𝗻𝗱 𝗮𝘁 𝘀𝗰𝗮𝗹𝗲. Full story in the comments. 𝗣.𝗦. 𝗜 𝗷𝘂𝘀𝘁 𝗹𝗮𝘂𝗻𝗰𝗵𝗲𝗱 𝗮 𝗳𝗿𝗲𝗲 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿 𝗼𝗻 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 — 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗿𝗲𝗮𝗱 𝗯𝘆 𝟮𝟬,𝟬𝟬𝟬+. 𝗝𝗼𝗶𝗻 𝗵𝗲𝗿𝗲: https://lnkd.in/dbf74Y9E

Payments have evolved from paper and plastic to APIs and orchestration - giving rise to a new breed of players that simplify the complexity and connect the dots behind the scenes. Here's how we got here. 𝟭. 𝗜𝗻 𝘁𝗵𝗲 𝗽𝗿𝗲-𝟭𝟵𝟵𝟬𝘀 𝗲𝗿𝗮, banks owned the entire payments value chain -acquiring, processing, settlement. Merchant onboarding was complex, and domestic clearing systems ruled. 𝟮. 𝗧𝗵𝗲 𝗿𝗶𝘀𝗲 𝗼𝗳 𝗲-𝗰𝗼𝗺𝗺𝗲𝗿𝗰𝗲 in the late 1990s changed everything. Players like PayPal and Authorize made online payments possible, while banks began exiting the acquiring space or partnering with processors to keep up with demand. 𝟯. 𝗕𝗲𝘁𝘄𝗲𝗲𝗻 𝟮𝟬𝟬𝟬 𝗮𝗻𝗱 𝟮𝟬𝟭𝟬, specialized gateways and regional wallets began to scale, offering merchants greater flexibility and control. The launch of SEPA in Europe marked a push toward payment harmonization, while non-bank players started building infrastructure that bypassed traditional acquiring models altogether. 𝟰. 𝗧𝗵𝗲 𝘀𝗵𝗶𝗳𝘁 𝘁𝗼 𝗔𝗣𝗜-𝗱𝗿𝗶𝘃𝗲𝗻 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 transformed payments from siloed systems into modular, developer-friendly tools. Merchant onboarding became faster, integrations simpler, and innovation more scalable. Open Banking regulations enabled direct access to bank data, while new credit models redefined consumer behavior. Payments evolved into a flexible, programmable layer of the digital economy. 𝟱. 𝗧𝗼𝗱𝗮𝘆, we’re in the age of seamless integration. Payments are embedded in everything - from ride-hailing apps to SuperApps. Real-time rails like SEPA Instant, UPI and PIX are live. CBDCs are in pilot. However, as payment ecosystems grow more fragmented - with new methods, regional schemes, compliance layers, and fraud risks -complexity has become a major bottleneck for merchants, fintechs, and even banks. Integrating multiple providers, maintaining uptime across systems, and ensuring regulatory compliance isn't just costly - it's unsustainable without the right foundation. This is where a new breed of infrastructure players like 𝗔𝗸𝘂𝗿𝗮𝘁𝗲𝗰𝗼 fit in - offering the tools to simplify complexity and still retain control. • 𝗪𝗵𝗶𝘁𝗲-𝗹𝗮𝗯𝗲𝗹 𝗽𝗮𝘆𝗺𝗲𝗻𝘁 𝗴𝗮𝘁𝗲𝘄𝗮𝘆𝘀 let banks, PSPs, and fintechs launch their own branded platforms fast - without building from scratch. • 𝗣𝗮𝘆𝗺𝗲𝗻𝘁 𝗼𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 enables merchants to route transactions dynamically across multiple acquirers, reducing costs and failed payments while improving UX. • 𝗕𝗮𝗻𝗸𝘀 can embed API-driven acquiring services into their offerings without the burden of a full-scale tech overhaul. In a world where growth brings fragmentation, the real challenge isn’t enabling payments - it’s managing them. The advantage will lie with infrastructure that can unify complexity, adapt in real time, and scale across borders without adding friction. Opinions: my own, Graphic source: Akurateco Payment Hub Subscribe to my newsletter: https://lnkd.in/dkqhnxdg

Alternative Payments raises a $22 million for its B2B payment platform for underserved industries #AlternativePayments has raised $22 million to expand its B2B #payments and checkout infrastructure platform, aiming to digitize financial workflows for industries often overlooked by #fintech innovation. Founded by CEO Baxter Lanius, the company focuses on sectors such as IT service providers, managed services, and blue-collar industries that still rely on outdated processes for accounts payable and receivable, merchant services, and client-facing financing. The funding, backed by investors including MissionOG, will accelerate Alternative Payments’ global growth and product development. The company’s turnkey platform offers automated solutions to key B2B challenges like invoice processing, cross-border payments, and cash flow management. According to the firm, clients using the platform have seen a 40 to 50 percent reduction in days sales outstanding, illustrating its impact on financial efficiency. With a mission to bring secure, autonomous, and accessible payments infrastructure to underserved segments of the B2B market, Alternative Payments is positioning itself as a modern solution provider at a time when automation and operational resilience are more critical than ever. The article on PYMNTS in the first comment.

Is the future of payments about competition—or coexistence? Payments in Change: Where is the journey heading? The payments industry is at a crossroads. Digitalisation, regulation, and cybersecurity are reshaping everything—from how we pay to who controls the rails. But here's the twist: instead of one dominant winner, we may be heading toward a complex coexistence of models. This whitepaper by Thede Consulting explores five scenarios shaping the future of payments—and what they mean for banks, PSPs, fintechs, and merchants. Let’s break it down: 1. Digitalisation is changing the game. Cash is declining, mobile and digital are rising. AI is improving fraud detection and personalisation, while APIs and cloud tech enable new business models like embedded finance. Consumers want fast, seamless, and secure payments—and businesses must keep up. 2. Regulation is ramping up. PSD3, PSR, DORA, and FIDA are coming fast, with major implications: - Stricter fraud liability rules and SCA requirements. - Mandatory IBAN-name verification. - Open finance mandates (FIDA) enabling broader data sharing via APIs. These shifts mean higher compliance costs—but also new chances to innovate. 3. The digital Euro is on its way. The ECB is building a CBDC aimed at complementing cash. If adopted widely, it could reshape the ecosystem: - Legal tender status means merchants must accept it. - No scheme fees like Visa/Mastercard—only regulated service charges. - PSPs and banks must adapt roles fast or risk losing relevance. But success depends on user adoption and seamless UX, not just regulation. 4. Europe wants independence with Wero (EPI). Wero, the European initiative backed by major banks, aims to be the continent’s answer to PayPal. But lack of awareness and limited functionality are holding it back. Without convenience, it won't compete—even with patriotic backing. 5. Cybersecurity meets usability. As AI enables sophisticated fraud, the EU is doubling down on DORA to enforce resilience. But there's tension between security and user experience. The winners will be those who master both. What’s next? Multiple futures. Thede outlines 5 plausible paths: - A2A payments replace cards. - The digital Euro takes over. - Card networks maintain dominance. - A new super app (like X or WeChat) breaks through. - Or… business as usual, with overlapping systems. Each scenario comes with implications for players across the ecosystem—no one is immune. Adaptation isn’t optional. Source: Thede Consulting #payments #embeddedfinance #psd3

The payments stack is quietly being rebuilt — and the latest move from Visa shows how fast that transformation is accelerating. Visa Intelligent Authorization is a new capability on the Visa Acceptance Platform that allows acquirers to modernize payment processing through a single API integration, capable of processing transactions across multiple card networks. On the surface, this looks like an infrastructure upgrade. But the implications for the payments ecosystem are far bigger. 1️⃣ Payments infrastructure is becoming “API-first.” Instead of banks or acquirers building and maintaining their own authorization stacks, they can plug into modular infrastructure through a single API. This significantly reduces the cost and complexity of modernization. 2️⃣ Orchestration is becoming the new battleground. As payment flows become more complex — with wallets, A2A, stablecoins and AI-driven commerce entering the mix — the ability to intelligently route and authorize transactions across networks will be a key differentiator. 3️⃣ Lower barriers for ecosystem innovation. Fintechs, PSPs and software platforms can integrate once and access multiple payment rails, accelerating innovation for merchants and enabling new commerce experiences without rebuilding core infrastructure. 4️⃣ Networks are evolving into platforms. Moves like this reinforce a broader trend: payment networks are no longer just processing transactions — they are becoming programmable infrastructure layers that others build on. For those of us working in payments, this shift is fascinating. The industry is moving from “card networks” to “payments platforms.” And when infrastructure becomes programmable, the real innovation happens at the edges — where fintechs, merchants, developers and partners build the next generation of commerce experiences. Exciting times ahead for the ecosystem! #payments #fintech #apis #digitalpayments #innovation https://lnkd.in/gXkpYQ2i

💻 Using Python to Detect Duplicate Payments — A Simple but Powerful Audit Tool 💡 As internal auditors and risk professionals, we often review large volumes of payment data for anomalies. One common (and costly) control gap? Duplicate payments. (Its a nightmare for inhouse internal audit team.) This can be automated using Python — and the results were immediate. 🔍 How it can be done Write a Python script to: ✅ Read ledger/exported payment data (from SAP, Oracle, Tally, etc.) ✅ Clean and normalize key fields (Invoice No., Vendor, Amount, Date) ✅ Flag records with identical or near-identical fields ✅ Highlight suspicious duplicates (same invoice paid twice, or minor reference differences with same amount/vendor/date) 📈 Results A list of suspected duplicate payments across multiple entities Identified control gaps in manual validation and workflow bypass This will help in recovering overpaid amounts and tighten the review process 🧠 Why This Matters ✅ Manual review can’t scale ✅ ERPs may not always block duplicates — especially if entries are slightly altered ✅ Python is flexible, fast, and easy to integrate into monthly audits or exception reports Its equally important to note that in a good environment, the ratio of confirmed to suspected duplicate payment can be as high as 1:1000 (1 transaction out of 1000 suspected transaction.) 👁️ Audit isn’t just about hindsight — it’s about real-time insight. Are you using analytics to enhance your internal controls? Let’s talk automation, fraud detection, and data-driven auditing. #InternalAudit #DataAnalytics #Python #DuplicatePayments #ControlTesting #RiskManagement #FinanceAudit #FraudPrevention #Automation #AccountsPayable #AuditTech

Innovators today are rapidly building for the future of agentic commerce and our clients are already asking so many of the right questions: ‘how do I prepare my business for an AI customer’ or ‘where do I start and what’s the risk of waiting too long?’   We’re helping accelerate this future with two new announcements:   We’ve opened our Model Context Protocol (MCP) Server, a secure integration layer that lets AI agents connect directly to Visa Intelligent Commerce API.   And we’re piloting the Visa Acceptance Solutions Agent Toolkit, which lets you use plain language prompts to generate invoices and payment links, create quick revenue summaries, and orchestrate agentic workflows.   These are great examples of the Visa-as-a-Service stack in-practice: enabling consumers, merchants, acquirers and AI companies to plug-in to our infrastructure, services, and global connectivity.   This helps innovators build, launch and scale fast – but it’s about so much more than speed. This is about building the next phase of commerce, and ensuring trust and security are embedded into the solutions that will define it.   Read our blog to see how developers and business users can connect to our tech stack to help power next‑gen payments 👇   #AgenticCommerce #AI #Innovation #Payments

𝐓𝐨𝐩 𝐏𝐚𝐲𝐦𝐞𝐧𝐭 𝐓𝐫𝐞𝐧𝐝𝐬 by Capgemini (Part 3) — Composable Cloud-based Payment Hub & Multi-rail Payment Strategy —— #5: 𝐂𝐨𝐦𝐩𝐨𝐬𝐚𝐛𝐥𝐞 𝐂𝐥𝐨𝐮𝐝-𝐛𝐚𝐬𝐞𝐝 𝐏𝐚𝐲𝐦𝐞𝐧𝐭 𝐇𝐮𝐛 𝐃𝐞𝐟𝐢𝐧𝐢𝐭𝐢𝐨𝐧 & 𝐁𝐚𝐜𝐤𝐠𝐫𝐨𝐮𝐧𝐝: A composable cloud-based payment hub refers to a modular, cloud-native platform that allows businesses to rapidly integrate payment services from different providers to adjust to evolving market demands with a single centralized hub. 𝐊𝐞𝐲 𝐈𝐦𝐩𝐚𝐜𝐭𝐬: ► Banks & FinTechs — Ability to launch new products faster. ► Businesses — Seamless integration with a wide range of payment solutions. ► Consumers — Faster processing, more personalized services and payment choice. 𝐊𝐞𝐲 𝐀𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐨𝐫𝐬: ► Microservices Architecture ► Cloud-Native Platforms ► APIs ► Advanced Security 𝐔𝐬𝐞 𝐂𝐚𝐬𝐞𝐬: ► Businesses — Accelerating time-to-market for new payment products, personalized experiences, and cross-channel payment solutions. ► Consumers — Access to a variety of options such as mobile wallets, credit cards, and digital currencies. ► Financial Institutions — Simplified back-end operations. 𝐄𝐱𝐚𝐦𝐩𝐥𝐞𝐬: 🔸 Stripe: Specializes in the "ease-to-integrate" payment solutions for businesses of all sizes. 🔸 Adyen: Cloud-based unified payments platform, built in-house. —— #6: Multi-rail Payment Strategy 𝐃𝐞𝐟𝐢𝐧𝐢𝐭𝐢𝐨𝐧 & 𝐁𝐚𝐜𝐤𝐠𝐫𝐨𝐮𝐧𝐝: A multi-rail payment strategy involves utilizing multiple payment networks (rails), such as card networks, ACH, real-time payments, and cryptocurrencies, to enable businesses to select the best rail for a specific transaction. 𝐊𝐞𝐲 𝐈𝐦𝐩𝐚𝐜𝐭𝐬: ► Banks & Payment Providers — More control over costs & improved fraud detection ► Businesses — Flexibility to choose the right payment method based on cost, speed, and convenience. ► Consumers — Enhanced choice of Payment Method 𝐊𝐞𝐲 𝐀𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐨𝐫𝐬: ► Real-Time Payments ► Digital Currencies & Blockchain ► Integrated Payment Systems ► Cross-border Payment Capabilities 𝐔𝐬𝐞 𝐂𝐚𝐬𝐞𝐬: ► Businesses — Global payments with lower fees, faster settlement times, and improved cross-border capabilities. ► Consumers — Real-time payments for peer-to-peer transactions, bill payments, and e-commerce purchases. ► Financial Institutions — A more resilient payment system, reducing reliance on any single payment network. 𝐄𝐱𝐚𝐦𝐩𝐥𝐞𝐬: 🔸 Visa: Expanding beyond traditional card networks, Visa is integrating various payment methods including ACH, RTP, and digital wallets. 🔸 PayPal: Offering rails including ACH, credit cards, and digital currencies for both B2B and B2C. — 🚨 This is #3 out of a series of 5 posts — next up 🚨 7️⃣ — Operational Resilience 8️⃣ — Decentralized Identity Get ready, it is just the beginning! —— Source: Capgemini ► Sign up to The Payments Brews: https://lnkd.in/g5cDhnjC ► Marcel van Oost and Connecting the dots in payments...

Thrilled to share the spring edition of Worldpay’s Innovation Focus, focusing on our latest innovations each designed to help businesses expand globally, optimize revenue and fraud exposure, and run more efficiently. Here are some highlights: 🌎 New market expansion into Mexico and Colombia  🌍 20+ new alternative payment methods including Affirm, MBWAY, WeChatPay and Oxxo—so customers can pay how they want, wherever they are 💱 Dynamic currency conversion at POS— in an additional 30+ currencies ☕ Omnichannel enhancements with pay-at-table and counter functionality for flexible checkout 📲 Worldpay 360: an all-in-one business management system for U.K. small businesses 💸 Immediate retries: automatic payment retries to reduce failed transactions 🤖 AI-powered dynamic debit routing—28% average savings for enterprise clients 🔒 Smarter 3DS with 3DS Flex—more approvals, less friction 🔐 Acquirer-agnostic token vault for greater control and flexibility 💼 Instant working capital for merchants—no lengthy paperwork, no waiting 🔁 Account Updater to reduce churn and failed recurring payments 🛡 Streamlined PCI compliance with SaferPayments—easy onboarding, simple UI 💳 PushtoWallet payouts in local currencies and real-time ⚡ Faster refunds in 30 minutes, across 120+ currencies 💷 Live and forward FX tools to help manage currency risk 🧾 Virtual cards for streamlined supplier payments 🤝 Split funding capabilities for EMEA marketplaces 📊 Enhanced small business portal: real-time insights and easier onboarding ✈️ Enriched transaction data for airlines 🔌 More provider integrations for sharper enterprise insights And that’s just the beginning! 👇 Link below to our latest edition of Innovation Focus in the comments Explore what this means for your business! #InnovationFocus #Worldpay #PaymentsTechnology #GlobalCommerce #SmartPayments