[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-how-a-japanese-bank-profiles-millions-of-users-without-per-user-ai":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},6787,"how-a-japanese-bank-profiles-millions-of-users-without-per-user-ai","How a Japanese Bank Profiles Millions of Users Without Per-User AI","A new pipeline profiles transaction patterns instead of individual users, cutting AI inference calls by nearly 1,000x at a major Japanese bank.","A bank-scale AI system now profiles tens of millions of customers by studying spending patterns instead of scanning each customer's full transaction history.\n\nResearchers built a three-stage pipeline called Resolve, Profile, and Tag. Resolve turns cryptic item names into readable descriptions, using web lookups when needed. Profile runs one large-language-model call per frequent spending pattern, rather than per person, and outputs category labels, free-text attributes, and prevalence estimates. Tag then clusters those free-text attributes into a searchable database. On the public Open e-commerce dataset, the resulting profiles matched the accuracy of a model that reads each user's raw history directly.\n\nThe trick is arithmetic: transaction volume grows with users, but the number of distinct spending patterns doesn't grow nearly as fast. That is why the same accuracy came at close to a thousandth of the inference cost, letting a Japanese bank run this at the scale of tens of millions of accounts. It is a template for any company sitting on transaction data too large to profile one LLM call at a time.\n\nThe paper does not say what the bank does with these profiles: underwriting, marketing, or fraud screening. That gap is worth watching as 'efficient categorization of millions of people' moves from research paper to deployed product.","[\"llm-inference\",\"banking\",\"user-profiling\",\"japan\"]","2026-09-18T04:00:00.000Z","2026-09-18T16:42:45.723Z","2026-09-18T16:42:59.335Z","published",null,[],"ai",[26,27,28,29],"llm-inference","banking","user-profiling","japan",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.19928",0,{"sections":36},[37,40,44,49,54,58,62,67,71,76,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",4017,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",653,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":18},"Hardware","hardware",155,{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",121,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":18},"Dev Tools","dev-tools",77,{"name":72,"slug":73,"count":74,"latest_published_at":75},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]