{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/4fd15a15a548408098a4f6f4f594e2ed\" 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/4fd15a15a548408098a4f6f4f594e2ed-bc0d75457b271fbc.gif","duration":203.125,"title":"Optimizing Roof Area Estimates from Public Data 📏","description":"In this video, I outline our approach to generating internal roof area estimates using public data like building footprints and aerial imagery, which helps risk analysts avoid costly vendor reports. I recommend starting with a paper comparing our estimates to existing vendor reports for three hotels, aiming for a 5% accuracy on straightforward roofs, which we need to define clearly. We also need to confirm that our deliverable is square footage only, as costs for replacement are outside our current scope. Escalation criteria are crucial; we should escalate on certain cases regardless of confidence scores to avoid being confidently wrong. I urge you to consider these definitions and criteria as we move forward."}