{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/2a9973c34b834732b792e1d615e4da77\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/2a9973c34b834732b792e1d615e4da77-f91259dcdf1f960b.gif","duration":1716.415,"title":"Building an Insurance Forecast Model From Scratch","description":"This Loom walks through building an end-to-end health insurance forecasting model in Excel from a blank spreadsheet. The presenter notes they had hit a 25,000 Dalupa call cap for the month, so they used Dalupa metadata and then ran the model build using available data to forecast PNL through four years of Oscar history. They describe how membership and per-member per-month trends were learned automatically, forecasting disaggregated p.m./members without manually setting growth rates, and then discussing forecasting medical loss ratio and medical expense as a percent of revenue. They reference a prior 2022 negative 15 percent gap margin tied to subscale, and explain how scale shifted results with scale reaching about $19 billion and a target low 80s MLR, supporting medical positive gross profits and eventually positive operating income and free cash flow. "}