# Digital Turbine's Auction Bid Price prediction — Data

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

采集时间：2026-10-19T07:40:29Z

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
2. `winBid` is the label of the bid price prediction task and the goal of the competition
3. `c1`, `c2`, `c3`, `c4` are anonimyzed columns