Help Center

Deliver 1:1 Product Recommendations Use Case

Using BlueConic to deliver 1:1 product recommendations

Both eCommerce managers and product marketers alike are challenged with devising strategies to engage online shoppers and generate sought-after revenue through increased order values. You can use BlueConic personalized product recommendations to engage and retain your customers, creating rich digital experiences that deliver the right merchandise at the right time. Increased engagement with shoppers online can lead to higher average order values, decreased cart abandonment, and higher lifetime values of customers.

Value-Based Outcome

All BlueConic use cases are associated with one or more Value-Based Outcomes, which are defined areas of focus that help you measure the value of a CDP to your overall business. This use case can be closely related to the Value-Based Outcome of Smarter Customer Engagement, which focuses on communicating with customers in smarter, more actionable ways that are creative and dynamic.

Case Studies

Before You Begin

Before you begin implementing smarter product recommendations, make sure you are familiar with what a CDP use case is and all of the components that will make yours more successful. Once this is done, you can start defining your “Before You Begin” requirements, which includes identifying key stakeholders and target audiences, gathering data sources and credentials, and defining what success looks like.

For this use case, your starting requirements may look something like this:

Key stakeholders: Ecommerce managers, email marketing team, and merchandising teams
Target audience: All visitors to your shopping channels
Data types: Product information
Platforms: Online shopping platforms, product information management (PIM) system
Measurement and ROI: Conversions, clicks, and clicks-to-views ratios

Use Case Configuration Steps

Gather data sources

Upload product catalog

If you have a limited number of products in your catalog, you may prefer to upload product information using a flat file rather than a Product Collector connection. For details refer to:

Creating a Product Collector Connection
Importing CSV data via the SFTP Connection

Create a Product Collector connection

1. To create a Product Collector connection, select Connections from the main BlueConic menu and click the Add connection button. Search for “product collector” and create the connection.
2. To set up the connection, select "Collect data from your channels" in the left-hand panel. Then select the channel(s) to collect content data from. You can optionally define URL rules to specify which areas of the sites to collect content data from.
3. Next, manage which data is collected by pasting a product page URL into the Test URL field, and click 'Test' to review the metadata that would be collected for your content. For more information on the metadata BlueConic collects, refer to this article on Configuring the Product Collector to collect items for recommendations.
4. Once everything looks correct in the test, set the algorithm time frame. Some recommendation algorithms are based on a look-back time frame (for example, Viral products or recent high CTR). For details on how each recommendation algorithm operates, see BlueConic recommendation algorithms.
5. Optionally, you can set request headers to collect product recommendations from web pages that are under development or behind a login or paywall. Click "Add request header," choose a channel, and add the custom header name and value used to access the content.
6. Finally, you can configure how products are detected in the shopping cart and within orders. Options for this functionality include:
  - Add shopping cart data to profile properties by storing the number of unique products in the customer's shopping cart. You can choose an existing profile property or create one.
  - Implement a JavaScript shopping cart event to let BlueConic know which products the customer adds to or removes from the cart, and when the cart is emptied. Use this data in dialogues for recommendations.
  - Implement a JavaScript order event to let BlueConic know which products the customer ordered. Use this data in dialogues to improve recommendations, using the "bought items" algorithm and collaborative filters and algorithms for order data.

Activate data with BlueConic Dialogues

Create a Dialogue

Note: Before creating a product recommendations dialogue, make sure you have the Product Recommendations toolbar plugin added to your tenant by going to Plugins in the main Settings menu. If it is not already listed, click the Add plugin button, search for “Product Recommendations,” and click the green plus button.

Now, go to Dialogues in the main menu and click the Add dialogue button.
Choose the Content dialogue from the pop-up window and when the new page opens up, name your dialogue and click Save.
To set up the dialogue, configure the following settings:
- Who: For this use case, leave this setting as the “All visitors” segment for the widest impact.
- When: Again, leave this setting as the default option. However, if you wanted to adjust when or how often this dialogue is shown to visitors, you would do so here.
- Where: In this setting, define the channel(s) you want the dialogue to appear on. For product recommendations, this will be whatever channel houses your product catalog.
- What: This is where you will define what your dialogue will look like on your website with the Product Recommendations toolbar plugin.
  - Inside your dialogue, select the content editor to insert a content placement based on a recommendation algorithm of your choosing at the place of the cursor.
  - To add a recommendations placement, edit an interaction and select Insert object > Product Recommendations from the content editor toolbar.
  - When you select "Product Recommendations" BlueConic adds a placeholder placement to the content editor. Hovering over the placeholder makes it light up in blue. Click and edit or double click the placeholder to open the product recommendation pop-up for configuring the products that get recommended and how they appear to customers. In this pop-up, you can configure:
    - Collector: Set this as the Product Collector connection you set up earlier.
    - Layout: Click the dropdown menu to choose a template to display your recommendations -- for example, in a list of links, or a list with images, etc. You can also choose to edit your own template for recommendations.
    - Frequency cap: You can choose to exclude items after the user has seen them a set number of times and not clicked on them.
    - Recommendation sets: Choose the number of products you'd like to include in the recommendations that are displayed. Add new sets of recommendations with different algorithms and filters that select the recommended content.
    - Enable fallback: You can set a fallback algorithm so if the recommendation set(s) you've defined don't deliver enough results to fill a set, you can fill the empty space with other items. If you choose to enable fallback recommendations, products that don't already appear in the recommendation set and also match the configured algorithms and filtering options are used to fill any empty spots in the recommendations area.
  - Why: You can leave this setting as the default option or you can choose to configure a unique conversion moment for your dialogue here.
  - Once your dialogue is configured correctly, switch the toggle at the top of the page to “On” and remember to Save.

Use Open-Time Email Recommendations

Alternatively, you can use the Open-Time Email Recommendations feature to deliver dynamic, individualized product recommendations via email based on up-to-the-minute customer data.

Test and launch your recommendations

Create test segments

For most product recommendation dialogues, you will want to use the “All visitors” segment for the highest impact. However, for reporting purposes, you may want to create two new segments that track how many visitors view and click on your new dialogue.

Do this by going to Segments and clicking the Add segment button. Name your new segment “Views of [Product Recommendations Dialogue Name]” and hit Save. After creating your segment, you will define the appropriate conditions by going to the Drill down condition section and opening the Select condition dropdown list. For the dropdown list, select profile property to open a pop-up window.

Once in the pop-up window, use the Search function and type “variants” into the field. Of the results, select Variants viewed and choose “Variant A” of your Product Recommendations dialogue. Click Save to finalize your segment settings.

To create the second segment named “Clicks of [Product Recommendations Dialogue Name]”, repeat the above steps. For the profile property, use Variants Clicked to isolate visitors who not only saw your content recommendations, but also clicked on them.

A/B testing

After you have created your Product Recommendations Dialogue and it is live on your channels, you may want to set up A/B testing to optimize its performance.

You can do this by opening up the original dialogue you created and creating new variants of the same dialogue. To create new variants, select Optimization in the top right corner, click Add variant under the existing variants in the Optimization tab of the Dialogues menu.

You can create as many variants as you would like to test out different types of content recommendations and algorithms. Once your variants are created, in the Optimization tab, you can choose the desired distribution for each variant, but we recommend an even split.

Now you can allow your dialogue to run, automatically rotating through the variants, and collecting feedback on which one has the best clicks to views ratio.

Measure your ROI

Product Recommendations Insight Dashboard

Create a new BlueConic dashboard for this use case by going to More > Insights in the main navigation menu and clicking the Add dashboard button. Enter a name for your dashboard that correlates with your use case and click Save.
After the dashboard is created, you can click the Add insight button to choose which insights you want displayed that will measure the success of your content recommendations. A few suggested insights include:
- Dialogues Table
  - Using the Search box, search for the Dialogues Table. To configure this insight, select the dialogue you created and choose the position that represents your product recommendations placement.
  - Next, click the Table columns option, and select the metrics you’d like to view. Check off the options for Conversions, Views, Clicks, and Clicks/views ratio. Click OK.
- Profile Property
  - Using the Search box, search for the Profile Property Insight and add two of them to your dashboard. To configure the first Profile Property Insight, select the profile property for Page views (All Visits) and select the radio button next to Use segment. Search for the name of the segment you created that tracks clicks of the product recommendations dialogue. Click OK.
  - Repeat the same steps for the second Profile Property Insight on your dashboard. Except for this insight, search for the name of the segment you created that tracks views of the product recommendations dialogue.
- Top recommended items
  - Using the Search box, search for Recommendations: Top Items Insight. To configure the insight, select the Product Collector connection you created and whether you want to see results displayed in views or clicks. Click OK.
  - The insight then shows a scrollable list of the top 50 personalized product recommendations for your Product Collector connection with the number of views or clicks recorded.

Google Analytics 4

In addition to using BlueConic insights to report on the click-through rate of your product recommendations dialogues, you can also use Google Analytics 4. To do this, set up a Google Analytics 4 Connection within your BlueConic tenant.
Then you will want to instrument the hyperlink <a></a> tags of your content recommendations templates with Google Analytics 4 event tracking similar to the following:
- <a href="{{URL}}" title="{{name}}" onclick="ga('send', 'event', 'bc_dialogue', 'bc_recs', 'bc_name_of_dialogue');">{{name}}</a>
In this code, bc_dialogue will refer to the fact that the click was generated from a BlueConic dialogue, bc_recs will refer to the fact that the click was for a content recommendation, and bc_name_of_dialogue will refer specifically to the name of the dialogue in question.
With this level of click detail in Google Analytics 4, you will not only be able to attribute clicks from BlueConic dialogues (in general) but also from product recommendations down to the dialogue that generated the click.

Next Steps

Set up Open-Time Email Recommendations
Create your own personalized product recommendations template
Play around with different BlueConic recommendations algorithms

Vertical Use Case Ideas

Top CDP Use Cases for Retail