Overview

Promote purchase behavior patterns found by Boxalino’s Deep Learning: Neural Collaborative Filtering based on products bought together with the main product of the PDP (UP-SELL WPO) or with the products already in the basket (CROSS-SELL WPO).

WPOS	Use Cases	Mode	Requirements
UP-SELL, CROSS-SELL	Context Items Correlation	RANKER*	You need to have enough purchases in your overall history with more than one product

* the Use Cases configuration is provided as SCORER with a default weight of 100000. You will need to adjust the weight to have the desired strength in the results or change the Mode to SCORER 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 can define a max value if you want to display no more than a fixed number of products from this recommendations

The weight which will be applied goes from 100% to 10% of the defined weight depending on the position of the product (first product gets 100%, second 90%, etc.)

Use-Cases (JSON) - click copy on the top right

[
  {
    "id": 3,
    "useCaseModelSource": "library",
    "useCaseModelId": 264,
    "useCaseModelVersion": 1,
    "useCaseModelSubVersion": 1,
    "name": "Context Items Correlation",
    "order": 3,
    "fromIndex": -1,
    "toIndex": -1,
    "variant": "",
    "scope": "local",
    "active": true,
    "parameters": [
      {
        "name": "type",
        "value": {
          "format": "StringParameterValue",
          "value": "bought_together"
        },
        "scope": "global"
      },
      {
        "name": "topWeightNbValuesMaxThreshold",
        "value": {
          "format": "StringParameterValue",
          "value": "0"
        },
        "scope": "global",
        "startval": {},
        "schema": ""
      },
      {
        "name": "sourceField",
        "value": {
          "format": "FieldParameterValue",
          "value": "id"
        },
        "scope": "global"
      },
      {
        "name": "role",
        "value": {
          "format": "StringParameterValue",
          "value": "mainProduct"
        },
        "scope": "global",
        "startval": {},
        "schema": ""
      },
      {
        "name": "required",
        "value": {
          "format": "BooleanParameterValue",
          "value": false
        },
        "scope": "global"
      },
      {
        "name": "origin",
        "value": {
          "format": "StringParameterValue",
          "value": "boxalino_std"
        },
        "scope": "global",
        "startval": {},
        "schema": ""
      },
      {
        "name": "topWeightMinThreshold",
        "value": {
          "format": "StringParameterValue",
          "value": "0"
        },
        "scope": "global",
        "startval": {},
        "schema": ""
      },
      {
        "name": "boostWeight",
        "value": {
          "format": "StringParameterValue",
          "value": 100000
        },
        "scope": "global",
        "startval": {},
        "schema": ""
      }
    ],
    "conditions": [],
    "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": ""
      }
    },
    "options": {
      "parameters": [
        {
          "name": "system",
          "values": [
            "false"
          ]
        }
      ]
    },
    "sections": [
      {
        "id": "main",
        "label": "Values",
        "active": true
      },
      {
        "id": "advanced",
        "label": "Advanced",
        "active": false
      }
    ],
    "status": true,
    "isSelected": true
  }
]

PCC - Context Products > Collaborative Filtering Bought Together

Overview

Variables

How to configure it?

0 Comments