BigML Integrations

Do you want a quick way to make a prediction from data added to a Google Sheets spreadsheet? Create a suitable BigML model to handle your data and prediction objective, setup this integration, and whenever you add a new row to the spreadsheet, a new prediction will be created in your BigML account. This is the easiest way to integrate your source of data with BigML.

How this Google Sheets - BigML integration works

1. Someone adds a new row to your Google Sheet
2. Zapier creates a prediction on BigML using that data.

What you need

• Google Sheets
• BigML

If you use Slack to communicate inside your team, this Zapier automation allows you to share any new predictions that are created in BigML with your coworkers. For example, this could be the latest prediction about the outlook of a given stock option.

Note: This does not necessarily need to be a prediction. You could share whatever kind of resource you want, for example, the latest version of a given model, so all of your coworkers know.

How this BigML-Slack integration works

1. A new prediction is created in your BigML account
2. Zapier sends the prediction outcome to a Slack channel

What you need

• BigML
• Slack

When someone fills out your Google Forms form or survey, create a BigML prediction using that data. For example, if you send your customers a survey about their food preferences, you can use a BigML model to predict the likeliness they might buy a given product. The BigML model would be created by collecting your data about previous customers' food preferences and whether they bought that product.

Note: This Zapier integration doesn't include a ready-made BigML model to use for your predictions. You can build the model using the BigML Dashboard using your available data.

How this Google Forms-BigML integration works

1. Your customer completes the Google Forms survey
2. Zapier creates a BigML prediction with the customer responses using the model of your choosing

Apps involved

• Google Forms
• BigML

It's often helpful to classify emails based on their content. For example, you could have a generic support@acme.inc address that receives emails intended for any department in the company (e.g., sales, finance, marketing, tech support, etc.) If you let BigML learn from your email archive which traits to use for distinguishing emails directed to the different departments, you can use it in this Zapier integration to process any new incoming Gmail email message and forward it to the relevant department.

Note: This Zapier integration doesn't include any ready-to-use BigML model to classify your emails. You can train one such model with the BigML dashboard using your email archive.

How this Gmail-BigML integration works

1. A new email is received on your Gmail account
2. Zapier classifies your email based on its content using your BigML model
3. Zapier uses the predicted email address to forward the email to the most relevant department

Apps involved

• Gmail
• BigML

Note: This integration will only work if you have a Business Gmail account - these have custom domains. Free consumer Gmail accounts cannot be used with this integration. Read Help docs here.

For each new order received through Amazon Seller Central, create a recommendation to suggest your customer other products they could be interested in. Use this Zapier automation to leverage all sales information you have to predict which products your customers can be interested in buying.

Note: This Zapier integration doesn't include a recommending system tailored to your business. You can create one using your past sales information with the BigML Dashboard.

How this Amazon Seller Central-BigML integration works

1. A customer places an order on Amazon Seller Central
2. Zapier creates a recommendation using BigML based on the order data

Apps involved

• Amazon Seller Central
• BigML