【数据科学赛】Curriculum Recommendations #多标签分类 #$55,000 #Kaggle
CompHub 实时聚合多平台的数据类(Kaggle、天池…)和OJ类(Leetcode、牛客…）比赛。本账号会推送最新的比赛消息，欢迎关注！
更多比赛信息见 CompHub主页
以下内容摘自比赛主页（点击文末阅读原文进入）
Part1赛题介绍
题目
Learning Equality - Curriculum Recommendations
举办平台
Kaggle
背景
Every country in the world has its own educational structure and learning objectives. Most materials are categorized against a single national system or are not organized in a way that facilitates discovery. The process of curriculum alignment, the organization of educational resources to fit standards, is challenging as it varies between country contexts.
Current efforts to align digital materials to national curricula are manual and require time, resources, and curricular expertise, and the process needs to be made more efficient in order to be scalable and sustainable. As new materials become available, they require additional efforts to be realigned, resulting in a never-ending process. There are no current algorithms or other AI interventions that address the resource constraints associated with improving the process of curriculum alignment.
简言之，各国的教育体系不一，教材的分类体系也不一，希望通过AI来帮助curriculum alignment这一过程。
Part2时间安排
December 15, 2022 - Start Date.
March 7, 2023 - Entry Deadline. You must accept the competition rules before this date in order to compete.
March 7, 2023 - Team Merger Deadline. This is the last day participants may join or merge teams.
March 14, 2023 - Final Submission Deadline.
All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.
Part3奖励机制
Leaderboard Prizes
-
1st Place - $ 12,000
-
2nd Place - $ 8,000
-
3rd Place - $ 5,000
-
4th Place - $ 5,000
Efficiency Prizes
-
1st Place - $ 12,000
-
2nd Place - $ 8,000
-
3rd Place - $ 5,000
Please see Efficiency Prize Evaluation for details on how the Efficiency Prize will be awarded. Winning a Leaderboard Prize does not preclude you from winning an Efficiency Prize.
Part4赛题描述
The goal of this competition is to streamline the process of matching educational content to specific topics in a curriculum. You will develop an accurate and efficient model trained on a library of K-12 educational materials that have been organized into a variety of topic taxonomies. These materials are in diverse languages, and cover a wide range of topics, particularly in STEM (Science, Technology, Engineering, and Mathematics).
简言之，目标是要将每个教材内容打上正确的标签。
Part5评测标准
Submissions will be evaluated based on their mean F2 score. The mean is calculated in a sample-wise fashion, meaning that an F2 score is calculated for every predicted row, then averaged.
Part6提交格式
For each topic_id in the test set, you must predict a space-delimited list of recommended content_ids for that topic. The file should contain a header and have the following format:
topic_id,content_ids
t_00004da3a1b2,c_1108dd0c7a5d c_376c5a8eb028 c_5bc0e1e2cba0 c_76231f9d0b5e
t_00068291e9a4,c_639ea2ef9c95 c_89ce9367be10 c_ac1672cdcd2c c_ebb7fdf10a7e
t_00069b63a70a,c_11a1dc0bfb99
...