Viewed Together
  • 07 Feb 2024
  • 1 Minute to read

    Viewed Together


      Article Summary

      Overview

      This algorithm recommends items by finding similar products to the products visited by the user. It generates recommendations based on the products visited in the same sessions and the same locale during the past 30 days. After generating recommendations, the algorithm orders the results based on their visit frequency (popularity). Thus, users can reach complementary or substitute products for the product that they are currently viewing. This increases discovery rates and the chance to grab users’ attention when they don’t have a target product. This type of algorithm works best on product pages.

      Endpoint

      GEThttps://recommendation.api.useinsider.com/v2/viewed-together

      Query Parameters

      ParameterSample ValueDescriptionData TypeRequired
      partnerNamemybrandPartner Identifier which is assigned by Insider. You can use PartnerID as well.StringYes
      localeus_USLocale of requested product catalog.StringYes
      platformwebRequested platform. Web comes by default.EnumNo
      currencyUSDRequested currency of the products. If no value is set, the default currency in your settings is used.StringYes
      productIdABC0123Base product id.StringYes
      size50Required number of items in response. Valid values are 0 to 100.IntegerNo
      categoryList[“Clothes”, “Skirts”]Category filter of the productsArray (of string)No
      filter
      Smart Recommender filtering. There can be more than one filter parameter.StringNo
      detailstrueAdds details to the products of the response.BooleanNo
      shufflefalseShuffles the products of the response.BooleanNo
      getGroupProductsfalseShows variant products under the products of the response.BooleanNo
      groupProductsFields
      Adds these fields to the variant products’ details.StringNo
      excludeVariantstrueExclude variants from response.BooleanNo
      userId
      a1b2c3d4
      User identifier which is assigned by Insider.
      StringNo
      excludeViewDay
      30After how many days should viewed products be excluded.
      IntegerNo (Can be used only with userId)
      excludeViewItem
      100How many viewed products should be excluded.
      IntegerNo (Can be used only with userId)
      excludePurchaseDay
      30After how many days should purchased products be excluded.
      IntegerNo (Can be used only with userId)
      excludePurchaseItem
      100How many purchased products should be excluded.
      IntegerNo (Can be used only with userId)
      hpfalseMakes affinities affect products of the response.
      BooleanNo

      Sample Example

      Sample Request

      POST https://recommendation.api.useinsider.com/v2/viewed-together?locale={Locale}&productId={ProductID}&currency={Currenct}&partnerName={PartnerName}

      Sample Response

      {
          "success": true,
          "total": 10,
          "types": {
              "mvop": 10
          },
          "data": [
              "QAZ-7890",
              "XYZ-1234",
              "QAZ-7899",
              "XYZ-1233",
              "QAZ-7898",
              "XYZ-1243",
              "QAZ-7891",
              "XYZ-1223",
              "QAZ-7892",
              "XYZ-1342"
          ]
      }

      Fallback Algorithms

      If the products come from Viewed Together are not enough to fill the response data, some fallback algorithms below fill it:

      • Most viewed of category
      • Most viewed of category without excluding right most item in the categoryList
      • Most viewed of Partner

      Was this article helpful?

      ESC

      Eddy, a super-smart generative AI, opening up ways to have tailored queries and responses