# AIKC Course 2025 Final Competition 2 — Data

来源：https://www.kaggle.com/competitions/aikc-course-2025-final-competition-2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

*   train.csv – the training set. Each row contains information about a video game, including its title, description, an image URL, and the list of genres (target labels).
*   test.csv – the test set. Same format as train.csv, but without the genres field. Your task is to predict the genres for each game in this file.
*   sample_submission.csv – a sample submission file in the correct format. Use this as a template for formatting your predictions.

## Format and Columns

*   ID – a unique identifier for the game.
*   title – the game's title (short text).
*   description – a textual description of the game (can be multiple sentences).
*   image – a URL pointing to a representative image (screenshot or cover) of the game.
*   genres – (train only) a string of one or more genre labels, separated by commas. This is the multi-label target you need to predict.