CROSS-SELL - What could be a/b tested first?

All the elements of the “What to start with?” list could also be used in a/b testing. The list here-after provides additional Best Practices that can be quickly tried.

Group

Name

Short description

Group

Name

Short description

1

Product & Content Context (PCC)

Context Products > Often Bought/Viewed/Basketed Together

Context Products > Collaborative Filtering Bought/Viewed/Basketed Together

Promote products often bought together with the products already in the basket (alternative with viewed in same session and added to the basket in same session)

(first practice with statistics, second variant with AI Collaborative Filtering)

2

Product & Content Context (PCC)

Context Products > Discovery Tags

Context Products > Defining Tags

Promote products or content with Discovery Tags matching the products already in the basket.

Each product gets a list of Discovery Tags representing the most common search terms used to find a product.

Each product gets a list of Defining Tags representing which is a subset of the product attributes values that have been identified as important in the selection of a product

3

Product & Content Context (PCC)

Context Products > End-up Buying

Products which are often bought in the same session after viewing the products already in the basket

4

Product & Content Context (PCC)

Context Products > Value Flags

Promote products or content with the same valuable value flags as the products already in the basket (5 stars, best-seller, novelties, recent discounts, staff pick of the week, …)

5

Product & Content Context (PCC)

Context Products > Low/High End

Promote products or content in the same Price Quadrant as the products already in the basket.
Each product is connected to a price percentile according to its group (e.g.: category), lower percentiles (e.g.: <20%) are labeled Low-End while top percentiles (e.g.. >80%) are labeled High-End.

6

Visitor Journey Personalization (VJP)

Viewed Category, Brands & Landing Pages

Used Facets Values

Used Price Range

Previous Search(es)

Related Search(es)

Promote products matching the

  • viewed top product-listing pages (category pages, brand pages, campaign landing pages, …)

  • used facets values or price range (search / product listing filtering options)

  • slightly higher price range than previously used

  • prior searches (or related to the prior searches) of the visitor.

7

Visitor Journey Personalization (VJP)

Views > Product Attributes

Promote products or content with attribute values matching previously viewed products

8

Customer Journey Personalization (CJP)

Purchases > Product Attributes

Promote products or content with attribute values matching previously bought products

9

Customer Journey Personalization (CJP)

Exclude Recently Purchased Products

Exclude products the customer has recently purchased

10

Product & Content Statistics (PCS)

Product Views & Engagement Trends

Most viewed or baskested items within different time frames

11

Product & Content Statistics (PCS)

Widget Display $Value Self-Learning

Promote products based on the self-learning of the Widget click/display score, either directly on the amount of clicks or on the conversion, average bought value or margin generated by the clicks

Display = visual impression detected on the screen of the user before, during and after scrolling on the page

12

Product & Content Context (PCC)

Segmented Widget Display $Value Self-Learning > Context Products

Segmented Widget Display $Value Self-Learning > Context Products Attribute

Promote products based on the self-learning of the Widget click/display score segmented per context products or attributes, either directly on the amount of clicks or on the conversion, average bought value or margin generated by the clicks

Display = visual impression detected on the screen of the user before, during and after scrolling on the page

13

Customer Journey Personalization (CJP)

Purchases > Rebuyable products

Promote products the customer has already bought which can be repurchased

Each product can be automatically labelled as rebuyable if enough people bought it several time, or if it belongs to a category you know to be rebuyable or doesn’t belong to any category which you know to be not-rebuyable .