REQUIREMENTS TO PARTICIPATE
Moses Maxen, Senior Adobe Premier Support Consultant: Moses is an Adobe Senior Solutions Consultant specializing in Adobe Target. He brings a depth of knowledge from his years of experience working closely with global brands on their optimization and personalization strategies from both a strategic and technical perspective. Additionally, Moses has extensive experience working with Adobe Target’s automation capabilities and loves talking with organizations on Target's Sensei features.
Curious about what an Adobe Target Community Q&A Coffee Break looks like? Be sure to check out the thread from our latest 8/3/22 Adobe Target Coffee Break with Adobe Target Expert @rbooth115
with extra support from @kaimotoyama of Adobe Technical Support Engineering.
Topics help categorize Community content and increase your ability to discover relevant content.
Hi @MaccGizzle - That's a fantastic question. While there is some overlap in the two features in that they are both powered by machine learning and AI to deliver relevant content to the customer, they have unique benefits depending on the use case. Automated Personalization is a full factorial approach where Target will create N number of total experiences based on the sets of offers that are added to the activity and will choose what the best overall experience is for each customer. It uses the Random Forest algorithm.
Recommendations on the other hand allows you the ability to deliver relevant and personalized product or content recommendations based on many different algorithms and criteria, for example, based on most popular content / products, top sellers, recently viewed, content similarity, and past purchase and browsing behavior to name a few.
@mosesmaxen and @shelbygoff do Automated Personalization activities look at different inputs to decide what to display to a given visitor than what Recommendations considers? I understand that Recommendations allows marketers to weight certain levers, but does the AI/ML in Automated Personalization consider the same triggers (i.e. recently viewed pages, what others viewed, top sellers, content similarity, etc.)
Hi @MaccGizzle - great follow-up question! Auto Personalization leverages most of the data in the Target profile for decisioning, for example mbox and profile attributes, profile scripts, Target and Experience Cloud segments. Recommendations is powered more on entity attribute data associated to products and content in your catalog. We do have Recommended For You algorithm that is user personalized and looks at past purchase history and past browsing behavior. There is only slight overlap between the data attributes that power Recs and Automated Personalized. With Recs it is important to call out you can still filter recommendations or weight the algorithm based on certain attribute data of your choosing, so there would be some slight overlap there as well.
Hi @MaccGizzle thanks for reaching out here! We host these Q&A Coffee Break chats in the Adobe Target Community Discussion threads on a monthly basis, where you can feel free to join to post your related questions and receive an answer from a team of Adobe Target experts in real-time 😊
Feel free to raise any follow up questions with @mosesmaxen and @shelbygoff today, and check out some threads from our most recent Coffee Breaks (8/3/22, 6/29/22, and 5/25/22). Thanks so much for joining us today!
Target Community Member @KMarchewa has a question:
I have implemented the triggerView functionality on my organization's SPA. I can add CSS, basic HTML, and other changes to a particular view in the VEC. However, I have not been able to successfully add Custom Code (specifically a JS script); the script simply does not execute. I have tried multiple combinations: adding to head/not adding to head, various scripts including simple console.logs, etc. To be clear, I am very familiar with adding custom JS to "normal" (not using triggerView()) Experiences to through the VEC, even to the same SPA that is not working with the triggerViews.
Is this a known issue? Specifically, is it even possible to add custom JS to a particular view via the VEC? If not, any suggestions as to what may be going wrong?
Target Community Member @ml19 has a question:
I have an experiment I have been working that is showing the SRM issue.
Is an A/B test with 50/50 split targeting 100% audience.
I relaunched the experiments few times, always trying different setup, but the SRM issue still appears and in some cases, happened 2 weeks after relaunching it.
Any idea of what the cause could be?
Hi @ml19 - Thank you for your question. If the test is in the initial stage after launch and the numbers are small, you might see an unequal split. However, as the traffic increases the split should be as you have set manually in Target. Example, for a low traffic page (100 Visitors per page) you might not see an equal split initially. The overall period for the split to converge depends on traffic, and not so much on days for which the experiment has been live. So you may just need to wait a little longer for the data to normalize based on traffic levels.
Another point to consider, Visitors in an A/B test will stay in their initially-assigned experiences. The traffic change impacts new entrants only.
Hi @mosesmaxen thanks for joining us today!
This Question was posted by Target Community member NicholasDrzewiecki :
Hey Target community.
I'm following up on a post from @BrendanJaffary a few years ago.
I manage a catalog of 200,000+ products and am looking for a way to mass-remove products that are no longer available and have thus 404d.
If I could simply export our entire Target catalog and compare it against our Target feed in something like Excel, then I could easily identify products that are no longer available, and run a Delete Entities API call on them.
@RobHornick has noted that there is a Catalog Search API that's close to what I'm looking for. But unfortunately, it's limited to 500 products.
To be honest, it seems like even the Delete Entities API call has a limit of 100 or so entities at a time.
Does anybody have any updated suggestions on cleaning up Target catalogs with entities in the hundreds of thousands?
Would it be possible to do something like the following?
Thanks in advance.
Hi @NicholasDrzewiecki, thank you for your question. By default, any entities that are not updated via API or through the Target request in 61 days will be automatically purged from the catalog. If you are doing a manually deletion of entities via API, the recommendation is to delete the corresponding entities and work with our support team to refresh the catalog in the back end.
While trying to create an A/B test, I am trying for layout test for contents on page, by resizing container on one of the container and moving other using 'Layout' option. However any change gives me an error on modification pane as - 'Action could not be applied due to missing or invalid mbox name'.
Also I tried to go ahead and save the experience [even with error] and then test it using QA URL but just the default experience and not the test version.
Can you please help me to find the cause behind this error and fix it.
Hi @NeelabhParmar, thanks for your question. I've seen this error appear for a number of reasons bust mostly it has been a known UI bug. First I would ask, does this modification you make work in production? Also the Adobe Target VEC Helper Extension has been known to help clear this error. However, I would recommend opening a ticket with Adobe Target Support to troubleshoot this.
I've successfully published one segment to experience cloud. But this segment cannot be found in target audience. Could anyone please advise the reason?
Hi @leo14, thanks for your question. I have seen this come up when the integration between Target and AAM is not enabled. Please open a support ticket for this so we can confirm the integration is set up properly.