# 2.21.22🛒Shop — Data

来源：https://www.kaggle.com/competitions/22122shop/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

See [Online Shoppers Purchasing Intention](https://archive.ics.uci.edu/ml/datasets/Online+Shoppers+Purchasing+Intention+Dataset) dataset in UC-Irvine ML Repository for more information. The original dataset has been augmented for the competition. There are 18 variables with 10 quantitative and 7 categorical input features, 500K observations (one row or web session per online user) in a tabular format with the first 50K rows missing the `Rev` revenue flag (1 for purchase intent and 0 otherwise). Your task is to predict the intent for the first 50K online users. The data was collected for the period of 1 year. 

Features description (from the dataset authors): 

1. Administrative (**Adm**), Informational (**Inf**), Product Related (**Prd**): counts of different page types viewed by the user in that session. Values are derived from the URL information of the pages visited by the user and updated in real time when a user takes an action, e.g. moving from one page to another. 
1. Administrative Duration (**AdmDur**), Informational Duration (**InfDur**), and Product Related Duration (**PrdDur**): total time spent on the page of the specified type.
1. Bounce Rate (**BncRt**): %visitors who enter the site from that page and then leave ("bounce") without triggering any other requests to the analytics server during that session. Measured by Google Analytics
1. Exit Rate (**ExtRt**): %visitors that were the last in the session. Calculated as for all pageviews to the page. Measured by Google Analytics.
1. Page Value (**PtVal**): average value for a web page that the user visited before completing an e-commerce transaction. 
1. Special Day (**SpclDay**): closeness of the site visiting time to a specific special day (e.g. Mother’s Day, Valentine's Day) in which the sessions are more likely to be finalized with transaction. The value of this attribute is determined by considering the dynamics of e-commerce such as the duration between the order date and delivery date. For example, for Valentine's day, this value takes a nonzero value between Feb 2 and Feb 12, zero before and after this date unless it is close to another special day, and its maximum value of 1 on Feb 8. 
1. Operating system (**OS**) of the user's PC
1. Browser (**Bsr**): web user's web browser
1. Region (**Rgn**) of the web user
1. Traffic type (**TfcTp**): TBD
1. Visitor type (**VstTp**): returning or new visitor
1. Weekend (**Wknd**): whether the page view event took place on weekend
1. Month of the year (**Mo**): the month of the page view event