## Can we predict if a visitor, in a session, will add item(s) to the cart?
The [Google Merchandise Store](https://www.googlemerchandisestore.com/shop.axd/Home) sells Google branded merchandise, a real ecommerce store. Using obfuscated Google Analytics data on each visitor session, you will use BigQuery ML to try and build a model that predicts whether each session will result in the visitor performing an action to add an item to the cart.
## Where's the data?
The data is split into two public tables on BigQuery: You will use the **training data** to build your model, and **testing data** to make your predictions using your model.
Go to the [data](../data) page for more information on the tables.
## How to create your first model and make your submission:
### Step 1.
Launch one of the notebooks below on AI Platform Notebooks:
- 
Starter Notebook [Python]
- Starter Notebook [R] Note: Select "R" under "Advanced Options" > "Environment".
If you'd like to only use SQL instead, you can follow the [instructions on using the BigQuery Console UI](https://www.kaggle.com/c/online-retail-store-20201008/overview/can-i-just-use-the-bigquery-console-ui)
### Step 2.
Upload your CSV submission file to Kaggle via "Submit Predictions"
This is the home page of the competition. You don't need a subtitle here. The competition sub-title will appear above. This is where you introduce the problem. You can upload images using the "Insert Photo" icon on the bar that displays above this textbox when in edit mode.
If you are copy-pasting from another application, like Word or your browser, you may need to clean up the markdown or html for things to display properly.
Here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).
## Can we predict if a visitor, in a session, will add item(s) to the cart?
The [Google Merchandise Store](https://www.googlemerchandisestore.com/shop.axd/Home) sells Google branded merchandise, a real ecommerce store. Using obfuscated Google Analytics data on each visitor session, you will use BigQuery ML to try and build a model that predicts whether each session will result in the visitor performing an action to add an item to the cart.
## Where's the data?
The data is split into two public tables on BigQuery: You will use the **training data** to build your model, and **testing data** to make your predictions using your model.
Go to the [data](../data) page for more information on the tables.
## How to create your first model and make your submission:
### Step 1.
Launch one of the notebooks below on AI Platform Notebooks:
- Starter Notebook [Python]
- Starter Notebook [R] Note: Select "R" under "Advanced Options" > "Environment".
If you'd like to only use SQL instead, you can follow the [instructions on using the BigQuery Console UI](https://www.kaggle.com/c/online-retail-store-20201008/overview/can-i-just-use-the-bigquery-console-ui)
### Step 2.
Upload your CSV submission file to Kaggle via "Submit Predictions"
This is the home page of the competition. You don't need a subtitle here. The competition sub-title will appear above. This is where you introduce the problem. You can upload images using the "Insert Photo" icon on the bar that displays above this textbox when in edit mode.
If you are copy-pasting from another application, like Word or your browser, you may need to clean up the markdown or html for things to display properly.
Here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission)