# Affirm: Credit decisioning AI Source: https://www.bankingnewsai.com/fintech/affirm/credit-decisioning-ai Last updated: Oct 19, 2026 *Part of the [Affirm AI strategy profile](https://www.bankingnewsai.com/fintech/affirm).* ## How does Affirm use AI to make credit decisions? Affirm underwrites every purchase individually, in real time, with models it builds in-house. Its fiscal 2026 10-K says the risk model turns user identifiers and transaction details into over 1,000 data points (over 500 a year earlier), models repayment probability month by month, and is trained on data from approximately 553 million loans. On September 17, 2026 Affirm added a transformer that reads individual credit-report accounts and payment histories and feeds an XGBoost model. Affirm's engineering blog says it delivered about 1.8 times the risk-ranking gain of the next XGBoost iteration, 2.1 times among thin-file applicants with no FICO score, and +1.2 percentage points (3.4% relative) conversion in an A/B test; to explain declines, Affirm developed a proprietary attribution algorithm. On credit, 30-plus-day delinquencies on monthly installment loans, excluding Pay in X and Peloton, were 2.5% in the June 2026 quarter against 2.3% a year earlier. Substantially all US loans are originated by Celtic Bank and Lead Bank. The rulebook moved in 2024 to 2026: the CFPB's May 2024 interpretive rule treating BNPL lenders as card providers was slated for revocation in March 2025, and FCA rules requiring affordability checks for UK BNPL took effect on July 15, 2026. ([Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm), [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000182095325000080/afrm-20250630.htm), [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260917918887/en/), [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6), [PYMNTS](https://www.pymnts.com/bnpl/2026/affirm-makes-smaller-purchases-bnpls-next-growth-test/), [Consumer Financial Protection Bureau](https://www.consumerfinance.gov/archive/newsroom/cfpb-takes-action-to-ensure-consumers-can-dispute-charges-and-obtain-refunds-on-buy-now-pay-later-loans/), [American Banker](https://www.americanbanker.com/payments/news/cfpb-retreats-from-classifying-bnpl-like-credit-cards), [Financial Conduct Authority](https://www.fca.org.uk/news/press-releases/new-protections-confirmed-buy-now-pay-later-borrowers)) ## What goes into Affirm's underwriting model, and what has changed? From Affirm's 10-K filings, releases and the September 2026 engineering post on the transformer model. | Item | What the record shows | Date | Sources | | --- | --- | --- | --- | | Inputs | Key user identifiers and transaction details become over 1,000 data points (FY2026); in FY2025 five top-of-mind user inputs became over 500 data points | 2025–2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm), [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000182095325000080/afrm-20250630.htm) | | Pricing logic | Month-by-month repayment probabilities combined with term length, purchase size, merchant and item to price and score risk, usually in seconds | August 27, 2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm) | | Data beyond scores | Transaction history, credit usage and Affirm's own repayment history; data from approximately 553 million loans to date (343 million a year earlier) | 2025–2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm), [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000182095325000080/afrm-20250630.htm) | | Bank-account data | Balances and cash-flow trends from linked accounts for Affirm Card and Affirm Money Account users | January 14, 2026 | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260114588934/en/Affirm-updates-underwriting-with-enhanced-signals-to-better-reflect-consumers-real-time-finances) | | Previous architecture | Hand-engineered features and tree-based models such as XGBoost, with further gains depending on new features | September 17, 2026 | [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6) | | Transformer stage | Tradelines and inquiries become tokens; the transformer is trained on repayment outcomes and its embeddings feed an accelerated failure time XGBoost model with credit, merchant and user features | September 17, 2026 | [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6) | | Offline results | Overall AUC improvement of 3.83% for the hybrid against 2.16% for the next XGBoost iteration (about 1.8x); about 2.1x among thin-file users | September 17, 2026 | [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6) | | Online results | +1.2 percentage points (3.4% relative) end-to-end conversion among eligible new users; added loans performed better than a comparable expansion under the previous models | September 17, 2026 | [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6), [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260917918887/en/) | | Rollout | Now running a first-look experiment with full approve-and-decline decisions for new users, and launching the next iteration to repeat and new users | September 17, 2026 | [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6) | ## How are the loans Affirm's models approve performing? Affirm reports delinquency on monthly installment loans excluding Pay in X and Peloton; a loan is charged off at 120 days past due. | Metric | Value | Period | Sources | | --- | --- | --- | --- | | 30+ day delinquencies | 2.8%, up 29 basis points year over year; allowance for credit losses 6.0% of loans held for investment | Q3 fiscal 2026 (March quarter) | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026032105/affirmfq326shareholderle.htm) | | 30+ and 60+ day delinquencies | 30+ days 2.5% (2.3% a year earlier); 60+ days 1.5% (1.4%); 90+ days unchanged at 0.6% | Q4 fiscal 2026 (June quarter) | [PYMNTS](https://www.pymnts.com/bnpl/2026/affirm-makes-smaller-purchases-bnpls-next-growth-test/) | | Charge-off expectations | Recent monthly installment cohorts tracking toward roughly 3.5% ultimate net charge-offs; recent Pay in 4 vintages below 1% of GMV | August 27, 2026 | [PYMNTS](https://www.pymnts.com/bnpl/2026/affirm-makes-smaller-purchases-bnpls-next-growth-test/) | | Rate caps | Celtic Bank and Lead Bank generally allow borrowers to agree to annual rates up to 36%; Cross River Bank up to 30% | August 27, 2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm) | | Credit reporting | All pay-over-time loans issued from April 1, 2025, including Pay in 4, reported to Experian | March 19, 2025 | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20250319542289/en) | ## Which banks and regulators shape Affirm's credit models? | Body | What | Date | Sources | | --- | --- | --- | --- | | Partner banks | Celtic Bank (Utah industrial bank) and Lead Bank (Missouri) originate substantially all US loans; underwriting is automated under their policies and those of Affirm's direct lending entity | August 27, 2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm) | | Nevada FID and FDIC | Applications for Affirm Bank, a Nevada industrial loan company | January 23, 2026 | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260123233238/en/) | | CFPB | Interpretive rule that BNPL lenders are credit card providers with dispute and refund duties (May 22, 2024); the Bureau told a court in March 2025 it planned to revoke it | 2024–2025 | [Consumer Financial Protection Bureau](https://www.consumerfinance.gov/archive/newsroom/cfpb-takes-action-to-ensure-consumers-can-dispute-charges-and-obtain-refunds-on-buy-now-pay-later-loans/), [American Banker](https://www.americanbanker.com/payments/news/cfpb-retreats-from-classifying-bnpl-like-credit-cards) | | State attorneys general | A coalition of seven began coordinated inquiries into BNPL providers in December 2025, as the CFPB signaled reduced prioritization of BNPL enforcement, per Affirm's 10-K | August 27, 2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm) | | FCA | Unregulated BNPL comes under FCA rules from July 15, 2026, including proportionate affordability checks and the Consumer Duty; Affirm U.K. Limited is already authorised for consumer credit | February 11, 2026 | [Financial Conduct Authority](https://www.fca.org.uk/news/press-releases/new-protections-confirmed-buy-now-pay-later-borrowers), [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm) | | ECOA and Regulation B | Listed in the 10-K among laws that apply; the transformer post says underwriting models must give the principal reasons for a decline | 2026 | [Affirm Holdings via SEC EDGAR](https://www.sec.gov/Archives/edgar/data/1820953/000162828026059279/afrm-20260630.htm), [Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6) | ## What does Affirm not disclose about its credit AI? Affirm reports the transformer model's gains against its own baselines and a control group; it has not published approval rates, loss rates for the loans the model added, or results by demographic group, and the offline AUC figures measure ranking, not losses. ([Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6), [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260917918887/en/)) The explainability method is proprietary; Affirm says validation and ongoing monitoring check that its reasons stay accurate, but it has not described the method or any external review. ([Affirm Tech Blog](https://tech.affirm.com/learning-richer-credit-representations-with-transformers-at-affirm-c774e7c1cea6), [PYMNTS](https://www.pymnts.com/bnpl/2026/exclusive-affirm-rebuilds-underwriting-to-approve-borrowers-a-credit-score-cant-see/)) ## What does the Affirm profile record on this topic? | Date | Move | Detail | Sources | | --- | --- | --- | --- | | Sep 18, 2026 | Levchin: no staff cuts to fund AI | On CNBC's Closing Bell Overtime, Levchin discussed the new AI underwriting system and said Affirm has not had to cut staff to implement AI. | [CNBC](https://www.cnbc.com/video/2026/09/18/never-had-to-cut-staff-to-buy-more-ai-tokens-says-affirm-ceo-as-it-rolls-out-ai-underwriting.html) | | Sep 17, 2026 | Transformer underwriting model goes live | Affirm launched a transformer-based model that reads the order and timing of events in a credit history; in its first deployment it produced 3.4% more completed purchases than a control group, with a proprietary algorithm providing explainability at checkout speed. | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260917918887/en/) | | May 12, 2026 | Investor Forum: transformer models outperforming | At its 2026 Investor Forum, President Libor Michalek said Affirm had processed $150 billion of volume and tracked 2.3 billion repayments over 14 years, and that its newer transformer-based underwriting architecture was already outperforming previous model generations. | [PYMNTS](https://www.pymnts.com/buy-now-pay-later/2026/affirm-targets-card-networks-with-broader-payments-push/) | | Jan 23, 2026 | Affirm applies for a Nevada industrial bank charter | Affirm submitted applications to the Nevada Financial Institutions Division and the FDIC to establish Affirm Bank, an FDIC-insured industrial loan company, with John Marion selected as its president. | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260123233238/en/) | | Jan 14, 2026 | Underwriting adds real-time balance and cash-flow signals | Affirm's underwriting began using account balances and cash-flow trends from linked bank accounts for Affirm Card and Affirm Money Account users; early results showed an average lift of about 12% when purchasing power rises. | [Affirm (Business Wire)](https://www.businesswire.com/news/home/20260114588934/en/Affirm-updates-underwriting-with-enhanced-signals-to-better-reflect-consumers-real-time-finances) | ## Common questions ### Does Affirm use AI to approve loans? Yes. Affirm underwrites each purchase in real time with in-house machine-learning models trained on data from approximately 553 million loans, per its FY2026 10-K. Since September 17, 2026 a transformer model that reads individual credit-report records has fed its decisions for new US users. ### Can Affirm approve people with no credit score? Sometimes. Affirm says its transformer model approved some applicants its previous system would have declined, including people with limited credit histories and no FICO score, and its engineering blog reports the largest ranking gain, about 2.1 times the next XGBoost iteration's, among those thin-file users. ### How does Affirm explain declined applications? Affirm's engineering post says underwriting models must give the principal reasons an application was declined, so it developed a proprietary attribution algorithm for its transformer-plus-XGBoost model, with validation and ongoing monitoring. It has not published the method. The FY2026 10-K lists ECOA and Regulation B among the laws it follows. ### What are Affirm's delinquency rates? Per PYMNTS' report of the June 2026 quarter, 30-plus-day delinquencies on monthly installment loans excluding Pay in X and Peloton were 2.5%, against 2.3% a year earlier, 60-plus-day were 1.5% and 90-plus-day 0.6%. Recent monthly installment cohorts were tracking toward roughly 3.5% ultimate net charge-offs. ### How is BNPL credit regulated in the US and UK? In the US the CFPB's May 2024 interpretive rule treated BNPL lenders as credit card providers, but in March 2025 the Bureau said it planned to revoke it, and state attorneys general opened inquiries in December 2025. In the UK, FCA rules requiring affordability checks for BNPL took effect on July 15, 2026. ## Deeper on Affirm - [How does Affirm use AI across its payment ecosystem?](https://www.bankingnewsai.com/fintech/affirm/payment-ecosystem-ai) - [What is Affirm's role in the digital payments transformation?](https://www.bankingnewsai.com/fintech/affirm/digital-payments-transformation) ## Same question, other companies - [Klarna: credit decisioning ai](https://www.bankingnewsai.com/fintech/klarna/credit-decisioning-ai) - [Block: credit decisioning ai](https://www.bankingnewsai.com/fintech/block/credit-decisioning-ai) - [Amex: How does American Express use AI for fraud detection and credit decisions?](https://www.bankingnewsai.com/banks/american-express/fraud-and-credit-ai) - [BOK Financial: How does BOK Financial use AI against fraud and in credit?](https://www.bankingnewsai.com/banks/bok-financial/fraud-and-credit-ai) - [FNBO: How does FNBO use AI for fraud detection and credit decisions?](https://www.bankingnewsai.com/banks/fnbo/fraud-and-credit-ai) - [MUFG: How does MUFG use AI in credit decisions and against fraud?](https://www.bankingnewsai.com/banks/mufg/fraud-and-credit-ai) - [Pinnacle: How does Pinnacle use AI for fraud detection and credit decisions?](https://www.bankingnewsai.com/banks/pinnacle/fraud-and-credit-ai) - [Sallie Mae: How does Sallie Mae use models and AI in credit and fraud?](https://www.bankingnewsai.com/banks/sallie-mae/fraud-and-credit-ai) - [Western Alliance: How does Western Alliance use AI for fraud detection and credit?](https://www.bankingnewsai.com/banks/western-alliance/fraud-and-credit-ai) --- Canonical page: https://www.bankingnewsai.com/fintech/affirm/credit-decisioning-ai Part of [BankingNewsAI](https://www.bankingnewsai.com/) — a free daily brief on AI in banking, an AI regulation tracker (42 authorities, 245 documents) and AI-strategy profiles of the 120 largest US banks. Markdown versions of every reference page: append `.md` to the page URL; index at https://www.bankingnewsai.com/llms.txt.