TABLE OF CONTENTS

Overview


This model looks at products that your customers have been browsing and recommends very similar products of different shapes, sizes, and brands to help them find a product very similar to the one they have browsed earlier.


You can configure this model to create various recommendation strategies based on:

  • Customer events such as page view and add to carts

  • Assigning varied importance to product attributes such as brand, color, and category.


Configuration Examples


Example 1: 

Sample Model Configuration

Customer event:  Page view

Product Attribute(s) 

Assign maximum importance to color

Assign the least important to brand



Result: 

Recommend products similar to those viewed by the customer with similar colored products appearing first, followed by similar brands' products. For example, if the customer has viewed a red dress of H&M brand, then the configured strategy would recommend more similar dresses in the following order:


  1. Red dresses of H&M brand

  2. Red dresses of varied brands

  3. Varied colored dresses of H&M brand

  4. Varied colored dresses of varied brands


Example 2: 

Sample model configuration

Customer event: Add to carts

Product Attribute(s)

Assign maximum importance to color

Assign medium importance to brand

Assign low importance to pattern

Business rule: Price >  20


Result:

Recommend products of price >  $20 similar to those added to the cart to by the customer with similar colored products appearing first, followed by products of a similar brand followed by products of a similar pattern. For example, If a customer has added to cart a red-colored, floral dress of the H&M brand, then the configured strategy will recommend more similar dresses, all of the prices greater than $20 in the following order.


  1. Red-colored, floral dresses of H&M brand

  2. Red-colored, floral dress of various brands

  3. Red-colored, varied patterned dresses of H&M brand

  4. Red-colored, varied patterned dresses of varied brands

  5. Varied colored, varied patterned dresses of varied brands


The recommendations are typically based on data browsed in the last X days.


Configure Inspired by Browsing History 

  1. Choose Assets > Strategies from the top navigation bar.
  2. Click New Strategy.

  3. Choose Journey-aware > Inspired by browsing history. The Manage Strategy page is displayed.

  4. Click to configure model parameters. 

  5. Click + to add a new event type and choose an event from the drop-down. The default event types considered by the model are Add to Cart and Pageviews. You can choose one of the following event types from the drop-down:


Note: You can also delete an event type by clicking on the trash icon.


Event Type

Description

Add to Cart

On choosing Add to Cart, the model recommends products similar to those added to the customer's cart in the last X days.

Pageview

On choosing Pageview, the model recommends products similar to those viewed by the customer in the last X days.


Note: You can also add multiple event types to configure the model to multiple event types.

  1. Click + to add a Product Attribute and choose an attribute from the drop-down. Indicate on a slider how important the attribute is to the model,  with values ranging from -1 to 1. Note: Click Reset to Default to restore model parameters to default values. 

  2. Click Next

  3. If you want to include business rules optionally, click Add a new business rule. 

  4. Click Done.