Back in stock

This is for:

Developer

In this article, we will look at the Back In Stock model and how it is used to predict visitor behavior. We will provide an overview of how this model is built, its data requirements, and the predictions it can make. We will also provide details of use cases showing how this model can be integrated into your personalization efforts.

In particular, we will cover:

  • What our model predicts

  • What it uses to make that prediction

  • Some potential use cases

  • How you can reach out to Qubit should you be interested in using the model to power your experiences

We presume that you have already familiar with Derived Datasets, the Qubit product used to action this model.

Intro

The Back In Stock model is a Derived Dataset model designed to identify when a product is back in stock and the visitors that previously interacted with it when it was out of stock.

Input data

The model uses the QProtocol fields indicated in the table below. One or both of product_productId and product_sku are required to identify products:

Event Field Example Required

event_ecProduct

meta_serverTs

2017-08-12 11:27:03.931 UTC

Yes

event_ecProduct

context_id

86gvhz7zdu0-0j6dwpc7w-gnk1dts

Yes

event_ecProduct

product_productId

PROD17339

Depending on QP implementation

event_ecProduct

product_sku

SKU34911

Depending on QP implementation

event_ecProduct

stock

2

Yes

event_ecProduct

eventType

detail

Yes
Note

The events detailed above are valid for the ecommerce vertical. For the equivalent fields for other verticals, refer to the docs site.
Warning

If one or more of the feature fields are missing or invalid, the model will often continue to operate, but with less input information, which can lead to lower accuracy.
Note

This model uses recent visitor views and transactions and so does not require a long history of data. The model depends on the stock of products being accurately captured by the product_stock QProtocol field.

Model

Unlike some of our other models, this model not use any machine learning, simply business logic and behavioral data.

We find the products that a visitor recently viewed when the product was out of stock. Of these products, we find those that are now back in stock. For example, a visitor on a fashion website may have recently browsed a new coat, but it was out of stock. If the coat is now back in stock we may want to remind the visitor about it.

The threshold for what stock level the model should use for a product to be considered back in stock can be configured based on your specific business logic. Your strategist will work with you to find the best configuration for the model.

Predictions

The output of the model is the products that are now back in stock and the corresponding visitors that have previously shown interest in those products when out of stock. This output is available through Derived Datasets and can be used directly in experiences or segments. The output is updated on a regular schedule that can be configured as necessary.

Example use cases

The Back In Stock model can be used to power Qubit experiences to nudge visitors to re-engage with back in stock products. Use cases include:

  • Indicate back in stock products when a visitor returns to the site

  • Email products to visitors when they come back in stock

  • Badge products when they come back in stock

For example, a fashion brand could use this model to display a carousel of these visitor-specific, back in stock products on the home page when the visitor returns to the site.

Getting started

To start using Qubit experiences powered by Derived Datasets, contact your account strategist and ask for the early access submission form. Submit this form specifying the model name as the project you’re interested in.