[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-macro-forecasting-model-that-doesnt-cheat-on-its-test":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},2614,"a-macro-forecasting-model-that-doesnt-cheat-on-its-test","A Macro Forecasting Model That Doesn't Cheat on Its Test","MACROCAST is a time series model built to forecast economic data without ever training on information a real-time forecaster wouldn't have had.","A new forecasting model claims to be the first of its kind that genuinely can't peek at the future.\n\nResearchers introduced MACROCAST, a lightweight time series foundation model designed for real-time macroeconomic forecasting. The core problem it addresses is data leakage — a subtle but serious flaw in how most such models are trained. Existing models suffer from two forms: temporal contamination (the model has seen values it's supposed to predict) and revision bias (training on fully revised economic data that wouldn't have existed at forecast time). MACROCAST sidesteps both by pretraining on purely synthetic data, then fine-tuning on vintage-specific releases from the ALFRED database — the exact data snapshots a forecaster would have had access to at each point in time. Each fine-tuning run takes nine minutes on a single GPU.\n\nThis matters because economic data gets revised — sometimes significantly — after initial release. A model trained on final, polished figures is essentially studying from the answer key, which flatters benchmark scores without reflecting real-world forecasting conditions. MACROCAST beats a standard AR(1) benchmark on about 80% of tested series-horizon pairs and matches or outperforms Chronos-2, currently the strongest available model in this class, in a genuinely clean out-of-sample test.\n\nThe honest benchmark is a harder bar to clear than most published models bother with — which says something about how the field has been measuring itself.","[\"machine learning\",\"economics\",\"forecasting\",\"research\"]","2026-06-30T04:00:00.000Z","2026-06-30T09:25:33.575Z","2026-06-30T09:25:36.541Z","published",null,[],"ai",[26,27,28,29],"machine learning","economics","forecasting","research",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.28670",0,{"sections":36},[37,41,46,51,56,61,66,71,76,81,86,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":87,"slug":88,"count":84,"latest_published_at":89},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]