【数据科学赛】小微企业数目预测 #时序预测 #$60,000 #Kaggle #GoDaddy

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

GoDaddy - Microbusiness Density Forecasting

举办平台

Kaggle

主办方

GoDaddy（从事互联网域名注册及网站托管的上市公司）

背景

The goal of this competition is to predict monthly microbusiness density in a given area. You will develop an accurate model trained on U.S. county-level data.

Your work will help policymakers gain visibility into microbusinesses, a growing trend of very small entities. Additional information will enable new policies and programs to improve the success and impact of these smallest of businesses.

这个竞赛的目标是预测特定地区的每月微型企业密度。您将开发一个基于美国县级数据训练的精确模型。

你的工作将有助于政策制定者了解微型企业日益增长的趋势。更多的信息将有助于制定新的政策和计划，以提高这些最小企业的成功和影响力。

Part2时间安排

• December 15, 2022 - Start Date.

• March 7, 2022 - Entry Deadline. You must accept the competition rules before this date in order to compete.

• March 7, 2022 - Team Merger Deadline. This is the last day participants may join or merge teams.

• March 14, 2022 - Final Submission Deadline.

Note - your notebooks will be used to predict future data not currently included in the test or train sets.

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

• First Prize: $20,000

• Second Prize: $15,000

• Third Prize: $10,000

• Fourth Prize: $5,000

• Fifth Prize: $5,000

• Sixth Prize: $5,000

Part4赛题描述

Your challenge in this competition is to forecast microbusiness activity across the United States, as measured by the density of microbusinesses in US counties. Microbusinesses are often too small or too new to show up in traditional economic data sources, but microbusiness activity may be correlated with other economic indicators of general interest.

As historic economic data are widely available, this is a forecasting competition. The forecasting phase public leaderboard and final private leaderboard will be determined using data gathered after the submission period closes. You will make static forecasts that can only incorporate information available before the end of the submission period.

你在这场比赛中的挑战是预测美国各地的微型企业活动，以美国各县微型企业的密度来衡量。微型企业通常太小或太新，无法出现在传统的经济数据来源中，但微型企业活动可能与其他的经济指标相关。

由于历史经济数据可以广泛获得，这是一场预测比赛。预测阶段的 public 排行榜和最终的 private 排行榜将使用提交期结束后收集的数据确定。你将进行的预测只能包含提交期结束前可用的信息。

Part5评测标准

Submissions are evaluated on SMAPE between forecasts and actual values. We define SMAPE = 0 when the actual and predicted values are both 0.

Part6提交格式

For each row_id you must predict the microbusiness_density. The file should contain a header and have the following format:

row_id,microbusiness_density
1001_2022-11-01,1.2
1002_2022-11-01,2.3
1003_2022-11-01,3.4
etc.

---