# Click-Through Rate Prediction — Data

来源：https://www.kaggle.com/competitions/avazu-ctr-prediction/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>File descriptions</h2>
<ul>
<li><strong>train</strong> - Training set. 10 days of click-through data, ordered chronologically. Non-clicks and clicks are subsampled according to different strategies.</li>
<li><strong>test</strong> - Test set. 1 day of ads to for testing your model predictions. </li>
<li><strong>sampleSubmission.csv</strong> - Sample submission file in the correct format, corresponds to the All-0.5 Benchmark.</li>
</ul>
<h2>Data fields</h2>
<ul>
<li>id: ad identifier</li>
<li>click: 0/1 for non-click/click</li>
<li>hour: format is YYMMDDHH, so 14091123 means 23:00 on Sept. 11, 2014 UTC.</li>
<li>C1 -- anonymized categorical variable</li>
<li>banner_pos</li>
<li>site_id</li>
<li>site_domain</li>
<li>site_category</li>
<li>app_id</li>
<li>app_domain</li>
<li>app_category</li>
<li>device_id</li>
<li>device_ip</li>
<li>device_model</li>
<li>device_type</li>
<li>device_conn_type</li>
<li>C14-C21 -- anonymized categorical variables</li>
</ul>