Business travel presents unique challenges for recommendation systems. Unlike leisure travelers who prioritize cost or vacation preferences, business travelers must balance multiple competing factors: corporate travel policies, meeting schedules, expense compliance, and personal convenience. This creates complex decision patterns that are difficult to predict.

This competition challenges participants to solve a **group-wise ranking problem** where your models must rank flight options within each user search session.  Each search session (ranker_id) represents a real user query with multiple flight alternatives, but only one chosen option. Your task is to build a model that can rank these options and identify the most likely selection.

### The Challenge
The dataset contains real flight search sessions with various attributes including pricing, timing, route information, user features and booking policies. The key technical challenge lies in ranking flight options to identify the most suitable choices for each business traveler on their specific route and circumstances. This becomes particularly complex as the number of available options can vary dramatically - from a handful of alternatives on smaller routes to thousands of possibilities on major trunk routes. Your model must effectively rank this entire spectrum of options to enhance the user experience by accurately identifying which flights best match traveler preferences.

### Why This Matters
Flight recommendation systems power major travel platforms serving millions of business travelers. Accurate ranking models can significantly improve user experience by surfacing relevant options faster, ultimately leading to higher conversion rates and customer satisfaction.

Your model will be evaluated based on ranking quality - how well it places the actually selected flight at the top of each search session's ranked list.