PCC - Context Products > Discovery Tags

Owned by Sylvain Paillard
Last updated: Nov 24, 2021
7 min read

Introduction

Boxalino Discover Tags can play a critical role in the definition of what makes products similar from the perspective of your customers.

Especially on the Product Detail Page (PDP) and in particular when they are coming from Google Shopping, your customers want to have a very quick view on what are relevant alternative to the product they clicked on from Google Shopping.

Now how to define similarity? Of course, you can use simple approaches like https://boxalino.atlassian.net/wiki/spaces/BPKB/pages/393117943 and define weighted similarities using the categories, the brand and other attributes. While this is important to consider, it might not be enough nor the most precise way to do so.

Another approach is to use similarities in the text or to find product with similar looking pictures. These options are also supported by Boxalino Winning Interactions platform, so you can configure them too!

But, multitudes of A/B tests done on the Boxalino Winning Interactions platform have shown that other articles with the same Discovery Tags (Context Products > Discover Tags) are the most efficient way to provide suggestions that feel relevant to your customers.

What is it?

Discovery Tags are product attributes which are generated by Boxalino Data Science platform, you can therefore consider them as an enrichment Boxalino does on your product data.

Discovery Tags represent the most important search terms made by your customers on your web-site which leads to customers finding (through clicks) and buying (through attribute click orders) a product. So you can consider them as “the most important search terms for each product”.

Your best-sellers might appear on top of many searches results lists, but only a few of these searches represent the majority of the clicks and purchases on these products. These searches are therefore much more important to discover the product. This is why we call them Discovery Tags.

 

This best practice is about using the Discovery Tags of the product to suggest other products having the same Discover Tags.

Best Practice Strategy

This is a case of smart similarities between products. Instead of selecting specific attributes to do the similarities, we consider the calculated Discovery Tags of each product. It consists of promoting products (or content) with Discovery Tags matching the ones of the main product of the Product Detail Page (PDP).

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

Configuration Use Cases

WPOS

Use Cases

Mode

Requirements

WPOS

Use Cases

Mode

Requirements

UP-SELL, CROSS-SELL

https://boxalino.atlassian.net/wiki/spaces/BPKB/pages/387088686

SCORER*

You will need at least 3 months of search statistics

* the Use Cases configuration is provided as SCORER with a default weight of 500. You will need to adjust the weight to have the desired strength in the results or change the Mode to RANKER or FILTER if you want the returned suggestions to always match this Best Practice.

Variables

  • none

How to configure it?

You can import the JSON below directly in the Admin (use the Import button on the top right), as in this screen-shot, you will need to select a field (product attribute)

You can use the search icon on the right of the field parameter to get help to select the right field and value.

 

[ { "useCaseModelSource": "library", "useCaseModelId": 20, "useCaseModelVersion": 1, "useCaseModelSubVersion": 1, "name": "Same Product Attributes", "order": "8", "orGroup": null, "fromIndex": -1, "toIndex": -1, "maxWeight": null, "variant": "", "scope": "local", "overwriteLevel": 1, "overwriteLabel": null, "globalTargetTags": [], "active": true, "parameters": [ { "name": "field", "value": { "format": "FieldParameterValue", "value": "bq_search_tag" }, "scope": "global" }, { "name": "operator", "value": { "format": "StringParameterValue", "value": "matches exactly" }, "scope": "global" }, { "name": "required", "value": { "format": "BooleanParameterValue", "value": false }, "scope": "global" }, { "name": "orCondition", "value": { "format": "BooleanParameterValue", "value": false }, "scope": "global" }, { "name": "boostFilter", "value": { "format": "BooleanParameterValue", "value": true }, "scope": "global" }, { "name": "boostWeight", "value": { "format": "StringParameterValue", "value": "500" }, "scope": "global", "startval": {}, "schema": "" }, { "name": "role", "value": { "format": "StringParameterValue", "value": "mainProduct" }, "scope": "global", "startval": {}, "schema": "" } ], "segmentationIds": [], "segmentationUniqueKeys": [], "CPOInitiativeId": null, "notes": null, "options": { "status": null, "includeWidgets": null, "excludeWidgets": null, "allWidgets": null, "conditionalSegments": null, "conditionalProductSelections": null, "ordering": null, "parameters": [ { "name": "system", "values": [ "false" ] } ], "allLinkedAccounts": null, "accounts": null }, "icons": { "strategy": { "value": "cpo_sales.png", "tooltip": "SALES OPTIMIZATION" }, "level": { "value": "L1", "tooltip": "LEVEL 1 - ONLINE CONVERSIONS" }, "initiative": { "value": "fa-folder", "tooltip": "EFFECTIVE CONTEXT" }, "character": { "value": "", "tooltip": "" }, "mode": { "label": "", "value": "", "tooltip": "" } }, "sections": [ { "id": "main", "label": "Values", "active": true }, { "id": "advanced", "label": "Advanced", "active": false } ], "status": true, "isSelected": true } ]