---
title: "ORBIT: Optimal Recommendation Framework for Boarding with Interpretable Timelines"
authors:
  - "Joonseong Kang"
  - "Seung Ha Hwang"
  - "Jaehun Bang"
  - "Jiyoung Ko"
  - "Subeen Park"
  - "Jeffrey Gennari"
doi: "10.24963/ijcai.2026/971"
url: "https://ijcai.org/proceedings/2026/971"
pdf: "https://ijcai.org/proceedings/2026/0971.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8423-8426"
track: "Demo Track"
keywords:
  - "AI: Multidisciplinary Topics and Applications"
  - "AI: Planning and Scheduling"
---

# ORBIT: Optimal Recommendation Framework for Boarding with Interpretable Timelines

Joonseong Kang, Seung Ha Hwang, Jaehun Bang, Jiyoung Ko, Subeen Park, Jeffrey Gennari

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8423-8426. DOI: [10.24963/ijcai.2026/971](https://doi.org/10.24963/ijcai.2026/971)

## Abstract

Determining when to leave for the airport is a complex problem shaped by flight delay risk, traffic, weather, airport congestion, and passenger-specific constraints. Existing services rely on isolated delay estimates or simple travel time calculations, failing to capture real-time context. We propose ORBIT, a decision-support system that generates personalized leave-by recommendations by integrating predictive models with real-time operational signals. The system combines user input normalization, real-time data acquisition, Transformer-based delay prediction, and LLM-based reasoning to jointly account for statistical forecasts and dynamic factors like congestion, previous-leg propagation, weather, traffic, and airport processing times. Instead of a standalone delay estimate, ORBIT produces an actionable and interpretable departure plan. We implement ORBIT as an interactive system and demonstrate its applicability. A video demo is available at https://youtu.be/fZX42jceIM4.