1.02026 INFORMS Analytics+ Conferencehttps://meetings.informs.org/wordpress/analyticsabodenheimerhttps://meetings.informs.org/wordpress/analytics/author/abodenheimer/rich600338<blockquote class="wp-embedded-content" data-secret="im1Luskgvl"><a href="https://meetings.informs.org/wordpress/analytics/speaker/upsana-raval/">Upasana Raval</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://meetings.informs.org/wordpress/analytics/speaker/upsana-raval/embed/#?secret=im1Luskgvl" width="600" height="338" title="“Upasana Raval” — 2026 INFORMS Analytics+ Conference" data-secret="im1Luskgvl" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); </script> At American Airlines, we're transforming how flight schedules are planned and evaluated through a cutting-edge platform developed in collaboration with Palantir. This "one-stop shop" empowers planners and schedulers to assess flight schedules in minutes—balancing operational feasibility, profitability, and robustness.A key component of this platform is the engine that predicts flight-level revenue, enabling analysts from crew and network planning teams to assess the profitability of flight schedules dynamically with respect to changes. The engine uniquely leverages concepts from optimization, econometrics, and machine learning to provide flight revenue prediction with 95% accuracy. In this session, we’ll walk through our end-to-end engine development and deployment journey—from training ensemble CatBoost models and interpreting results using SHAP, to leveraging Palantir Foundry for scalable experimentation and deployment, and packaging the core logic for seamless integration across platforms and applicationshttps://meetings.informs.org/wordpress/analytics/files/2025/06/2026_Analytics_Conference_logo_400.png400400