Join us for the next Adobe Target Community Q&A Coffee Break!
We'll be joined by Cristinel Anastasoaie (@cristinel) and Brent Kostak (@bkostak) of the Adobe Target Product teams, as well as Timothy Furlow (@TF_L), Target Recommendations Expert & Senior Manager of Personalization & Optimization at Lenovo.
In this AMA (Ask Me Anything)- like event, the experts will be logged in to chat with you over this Discussion Thread, ready to answer any of your questions related to the topics covered in the 2/13/24 Webinar on "High Performance Recommendations"
*NOTE: This is a text-only thread discussion where one participates by posting a Reply to this post.*
WATCH THE WEBINAR RECORDING, and then join us here on 2/28 to bring your related Questions, Best Practices, or Hot Tips to this chat to share and discuss with the experts and your Target Community peers!
Questions / Best Practices / Hot Tips should be geared around topics covered in this Webinar Part 2 , specifically:
Participating is easy:
During the hour, make sure to refresh this Coffee Break page periodically to catch new questions, responses, and recommendations.
**To disable email notifications for this thread, click the Options menu on the top right and select "Unfollow the conversation." This will prevent notifications from being sent to your email every time there is a new reply to the thread or comment.
The Star Contributor opportunity:
Meet the experts:
Brent Kostak, Product Marketing Manager at Adobe
Brent brings data-driven personalization solutions to market that connect global brands to their customers. Adobe enables enterprise marketing and engineering teams to streamline data and create a single, personalized view of their customers to deliver exceptional digital experiences. Brent has over 10 years of experience helping organizations leverage software technologies and services to better compete and serve their mission.
Tim Furlow, Senior Manager of Personalization & Optimization at Lenovo
Tim's team is responsible for driving the test and learn program worldwide. Tim's approach to Target places emphasis on CRO, and is informed by his career in web analytics, marketing technology, and personalization at Fortune 500 companies.
Cristinel Anastasoaie, Senior Product Manager for Adobe Target
Cristinel is focused on machine learning personalization in Adobe Target, Analytics for Target integration, and the product user interface. Before his current Adobe role, Cristinel held product management positions on various content management and digital marketing products focused on consumers.
Add your related questions below ANY TIME prior to or during the Coffee Break on Wednesday, February 28th @8am PT, when you can watch the page and be ready to add follow-up questions and discuss further with other community members!
Curious about past AT Community Q&A Coffee Breaks?
Check out the thread from our latest Coffee Break from 2/7/24, and the ongoing list of all past AT Coffee Breaks
Hey all,
Look forward to your questions on recommendations. Cant wait to hear from you all!
Hi @markcol, you're in the right place! Feel free to post any of your Target Recommendations related questions here in the thread and our team of experts will follow up with you by replying to your question here in the thread.
Hello everyone, thank you for joining in this Coffee Break. Looking forward to your questions!
For the recommendation activity, we have to Feed data to Target, which, if fed in the CSV format, has the first column named "entity.Id" https://experienceleague.adobe.com/docs/target/using/recommendations/entities/entity-attributes.html...
What if we don't have that unique code for us? What can go in that field?
Hi Jyoti! These would be unique single value parameters which are classified internally with an organization and mapped to not just products but could be content components such as movies, articles, etc and predefined for each 'entity.id' attribute value (e.g. unique numeric values)
For popularity-based recommendations, can we use a custom metric? For example, could we build a recommendation algorithm based on a sold-to-view ratio? The metric would be something like product orders/product views.
@jingle77 you would need to build out a custom algorithm and send it into Target. This is quite possible, but nothing in the box in Adobe Target.
For "Bring your own" algorithms, is there a template, particularly in Python, we could refer to if we wanted to try out a custom algorithm?
Hi @jingle77 Thank you for your question! Based on custom templates / scripts, you could use your python algorithm and upload the output in custom criteria configuration as a .csv. You can customized all the OOTB options in the criteria menu to create your own criteria configuration. Note - Custom criteria replace the “offline training” portion of Item-Based recommendations, but behave similarly to Item-Based recommendation algorithms during the online content delivery phase, in that a single key is used for retrieval of recommendations and business rules/filters are then applied.
Hi team!
Is there a product and traffic minimum to use recommendations? Can you layer in user segments into a recipe, such as a “best sellers for those who did X”? Looking to see how granular these recommendations can get, and what other data layers can be added on top.
One way to tackle this would to filter out recommendations based on profile attributes assuming that the profile stores information you need to filter recommendations on. Some more details about this type of filtering can be found on experience league page: https://experienceleague.adobe.com/docs/target/using/recommendations/criteria/dynamic-static/profile...
Thank you @BryanSt3 for your question, traffic for a recommendation would depend on your test time to confidence using a statistical calculator. If you have low traffic and cannot meet confidence, I would look at prior data of recommendation interaction and make a trade off as long as your analytics team agrees. Your best bet to understand granularity would be to store profile attributes and to create more of an affinity approach. In addition, you can layer several stacking segments in a recommendation test depending on your use case.
I'd like to hear suggestions on using AI activities when there's a publishing schedule that's shorter than the learning may take to build the model.
Hi @hagarwal thank you for your question! Models to building times within AI activities will correlate to traffic to selected activity locations and conversion rates associated with those success metrics.
For Auto-Target specifically, the personalization activity does not attempt to build a personalized model for a given experience until there are least 50 conversions for that experience. If the model built is of insufficient quality (as determined by offline evaluation on hold-out “test” data, using a metric known as AUC), the model is not used to serve traffic in a personalized manner.
Additional points on model building:
Is it better to optimize recommended for you with content analysis techniques using product description, user reviews, etc and introduce users to new/unexpected items that align with their interests beyond the browsing history?
@AmsaPa thank you for your question I highly suggest a read through of https://experienceleague.adobe.com/docs/target/using/recommendations/introduction-to-recommendations....
Adobe Target recommendations can be used for so many capabilities than products - Travel, Gaming, Videos, Publish, B2B Sales, and more. It will open up so many possibilities on how to utilize recommendations.
Now how you optimize, you have to be willing to take risks on different UI, featuring reviews, and also testing by different locations WW. You may find what works for one country does not work for another.
Hi Team,
Is there any way to dynamically personalize the recommendation algorithm based on user's behaviour and journey or switch the recommendation recipe If existing recipe is not returning any products?
Thank you @Sharma_Manu . Recommendation algorithms could be configured to use dynamic inclusion rules based on user profile attributes or on page context similar to category affinity filtering. Using dynamic rules brings more engagement. More details about available filtering rules could be found on Experience League: https://experienceleague.adobe.com/docs/target/using/recommendations/criteria/dynamic-static/use-dyn...
Thank you @Sharma_Manu appreciate your question. There are a luxury of algorithms from Adobe - I suggest you look into affinity. Target https://experienceleague.adobe.com/docs/target/using/recommendations/criteria/base-the-recommendatio...
If you are out of a product, you can have out of stock filters out of the box in Adobe Target.
Have any users of Adobe Target shown insights regarding how Adobe Target recommendations have impacted product relationships and/or the customer journey? For example, if a site has implemented rec for you, did it cause a significant shift in traffic viewing/ordering a particular set of products?
Thank you for your great question and that would be a great new feature of Target and / or Target + Analytics. So far, the Target reporting data as well as the algorithms co-occurrence scores are not available. Please use the Adobe Target Community Ideas to post this as a feature request and have other community members vote for this feature.
Is it possible to highlight products that were added to the cart but not bought on the homepage for personalized recommendations?
@Ramesh_N yes you would use a profile attribute to signify the visitor has added this item to cart before. If they signed in you could identify the hash as well to be cross device. This would allow for a more personalized algorithm to complimentary items.
Once you have a product in cart, for example a laptop, would it ever make sense to start recommending accessories for that product across the site (rather than just on cart or subseries pages)? So, once a product is added, accessories recommendations take the place of the regular rec for you type recommendations.
@RobBa2 thank you for your question. Yes, what you would need is a custom out of the box algorithm to tie in accessories to products that would depend on a profile scripting activation of the product add to cart to tie into that recommendation spot. This way you can test multiple accessory algorithms and features.
For the rec for you algorithm, I understand that the behavioral data is based on views and orders. Then, in the multi-key retrieval stage, the recs from products a customer has ordered are given double the weight of the recs from products the customer has only viewed. I have two questions based on this logic:
1. Are we able to add other hyperparameter logic? Specifically, could we include a "product added to cart" logic?
2. Could we customize the weights at the multi-key retrieval stage?
Great question, thank you. Would you be able to provide more details on the assumptions you're working with it when trying to add additional parameters or even weight change? While this is not possible at this point with recommendations algorithms, you might want to combine recommendations with Auto-Target activities. For the configurable recommended for you algorithm, please submit a community idea.
Can we dynamically retrieve the top discounted products and showcase them as personalized recommendations on the site?
@Ramesh_N this is very possible in the box in Target. You would have to send that data into target and use a set of filters. By doing this, you would be ready to have personalization recommendations by top discount.
I suggest a friendly read of this as well to help give some background on the potential of feeds. Its where so much creativity can be reached with recommendations - https://experienceleague.adobe.com/docs/target/using/recommendations/entities/feeds.html?lang=en
Event starts:
Feb 28, 2024 - 08:00 AM (PST)
Event ends:
Feb 28, 2024 - 09:00 AM (PST)