Primary competition visual

Adbot Ad Engagement Forecasting Challenge

Helping South Africa
$500 USD
Completed (over 1 year ago)
Forecast
451 joined
113 active
Starti
Apr 04, 24
Closei
May 19, 24
Reveali
May 19, 24
About

The data provided contains the daily ad records for 185 clients from the Adbot platform. Each record contains information related to the ads including the cost, number of impressions, as well as the number of keywords used in the ads.

The data provided also contains the calls clients receive as a result of hosting ads on the platform. These detail the daily number of received/missed calls as well as the duration of each call.

The objective is to accurately predict the “clicks” a client’s ad receives, one and two weeks into the future. Winning solutions will further be required to submit a description of the variables that had the most significant impact on engagement (number of clicks). It is therefore important that the models you build are not only accurate but also interpretable.

Files
Description
Files
This file contains the target. This is the dataset that you will use to train your model.
Shows the submission format for this competition, with the ‘ID’ column containing all client IDs and date for the test set and the clicks column containing your forecasts for the number of clicks. The order of the rows does not matter, but name of the item ID needs to be correct.