# Digital Turbine's Auction Bid Price prediction — Data

来源：https://www.kaggle.com/competitions/digital-turbine-auction-bid-price-prediction/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

This section contains important information about the dataset provided. It describes the files we provide you, their format, and the data columns that will be relevant for this competition.

**Each record represents an auction **


## Files

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

## Columns

* `eventTimestamp` - request timestamp, in milliseconds, epoch time
* `unitDisplayType` - ad slot type (e.g. banner, rewarded, ...)
* `brandName` - device brand name
* `bundleId` - external app Id (official bundle Id - taken from the app store - Google Play / Apple iOS Store)
* `appVersion` - external app version (official version)
* `correctModelName` - specific model device
* `countryCode` - 2 digit country code, e.g. US
* `deviceId` - hashed user Id
* `osAndVersion` - device OS and device OS version, combined into a single column
* `connectionType` - device connection type
* `c1` - an anonymized column
* `c2` - an anonymized column
* `c3` - an anonymized column
* `c4` - an anonymized column
* `size` - ad size (e.g. 320x50)
* `mediationProviderVersion` - mediation SDK version
* `bidFloorPrice` - 2 decimal bid floor price we exposed to DT bidders (e.g. 0.01)
* `sentPrice` - the bid we send into the auction. 2 decimal places (E.g. 1.23)
* `has_won` - a flag indicating (1) is that DT Exchange won, 0 otherwise
* `winBid` - the bid that had won in the auction eventually. **Note: This is the target**

### Notes:
1. `has_won` and `winBid` are not part of the test set <br>
2. `winBid` is the label of the bid price prediction task and the goal of the competition <br>
3. `c1`, `c2`, `c3`, `c4` are anonimyzed columns <br>