# EPF Montpellier 2025 — Data

来源：https://www.kaggle.com/competitions/epf-montpellier-2025/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

We provide a small subset of auctions processed by our SSP during a week. Each auction is described by a set of features defining the context in which the auctions has run.

The target variable we are trying to predict is a boolean defining wether the auction led to a sale or not

## File descriptions

- **train.csv** - the training set
- **test.csv** - the test set
- **testSubmissionFile.csv** - a sample submission file in the correct format

## Data fields

- **auctionId** - a random anonymous id unique to a given auction
- **timeStamp** - the timestamp (in seconds) of the start of the auction
- **placementId** - the id of a zone in the web page where the ad would be displayed
- **websiteId** - the id of the corresponding website
- **refererDeepThree** - the URL of the page where the ad would be displayed, truncated at its 3rd level and anonymized
- **country** - the id of the user's country
- **operatingSystem** - the user's operating system
- **browser** - the user's browser
- **browserVersion** - the user's browser version
- **device** - the user's device type
- **environmentType** - the type of the webpage environment
- **integrationType** - the id of the webpage integration type
- **articleSafenessCategorization** - the categorization of the content of the article

## Target variable

- **isSold** - a boolean variable defining wether the auction led to a sale or not