Expand my Community achievements bar.

[AT Community Q&A Coffee Break] 7/8: Rob Hornick, Adobe Target Product Manager

Avatar

Administrator

Join us for our next Adobe Target Community Q&A Coffee Break

taking place Wednesday, July 8th @ 10am PDT

--> REGISTER NOW <-- 

We'll be joined by Rob Hornick aka @Rob_Hornick, Senior Adobe Target Product Manager, who will be signed in here to the Adobe Target Community to chat directly with you on this thread about your Adobe Target questions pertaining to his areas of expertise:

  • Personalization
  • Machine Learning & Artificial Intelligence 
  • Recommendations
  • Auto-Allocate
  • Auto-Target
  • Automated Personalization 

Want us to send you a calendar invitation so you don’t forget? Register now to receive a reminder!

A NOTE FROM NEXT WEEK'S COMMUNITY Q&A COFFEE BREAK EXPERT, ROB HORNICK 

 

REQUIREMENTS TO PARTICIPATE 

  • Must be signed in to the Community during the 1-hour period
  • Must post a Question about Adobe Target
  • THAT'S IT!  *(think of this as the Adobe Target Community equivalent of an AMA, (“Ask Me Anything”), and bring your best speed-typing game)

INSTRUCTIONS 

  • Click the blue “Reply” button at the bottom right corner of this post
  • Begin your Question with @Rob_Hornick 
  • When exchanging messages with Rob about your specific question, be sure to use the editor’s "QUOTE" button, which will indicate which post you're replying to, and will help contain your conversation with Rob

QUOTE BUTTON.png

 

Rob Hornick Headshot.jpg

 

 

 

 

Rob Hornick is the Senior Product Manager for Machine Learning and Personalization with Adobe Target, based in San Francisco. Rob is energized by both building tools to personalize digital experiences and putting advances in machine learning into marketers’ hands. Prior to joining Adobe, Rob was a Manager with Accenture Digital where he helped marketers optimize their processes and technology.

 

Curious about what an Adobe Target Community Q&A Coffee Break looks like? Check out the thread from our last break with Ram Parthasarathy, Principal Product Manager for Adobe...

Topics

Topics help categorize Community content and increase your ability to discover relevant content.

26 Replies

Avatar

Level 1

@Rob_Hornick what are the odds of being able to expand the window of conversion to more than 30 minutes? Financial planning events have a much longer conversion time than e-commerce events.

Avatar

Level 2

@evidana wrote:

@Rob_Hornick what are the odds of being able to expand the window of conversion to more than 30 minutes? Financial planning events have a much longer conversion time than e-commerce events.


Eric, thanks for your question! I can't comment on the likelihood of adding features that aren't on our publicly committed roadmap, but we don't have an immediate plan to add a longer window to Adobe Target-defined conversion metrics. You're welcome to submit this (and any other feature requests) in our Ideas forum: https://experienceleaguecommunities.adobe.com/t5/adobe-target-ideas/idb-p/adobe-target-ideas

 

In the meantime, you may be able to accomplish your goal using our Analytics for Target (A4T) integration along with a conversion metric defined in Adobe Analytics with a longer attribution lookback window. Adobe Analytics conversion metrics are supported for A/B and XT activities, and with our June release, we added A4T support for Auto-Allocate activities. Later this summer, we'll release A4T support for Auto-Target activities.

Avatar

Community Advisor

@Rob_Hornick Apologies for the first question, I was on the wrong account. Any chance that the Recommendations tool can get eligibility at the offer level. There are collections, but I have not seen anything more granular than that. The hypothetical use case will be that I do not want to advertise a lawnmower if you have one in your garage (not necessarily purchased from our store).

Avatar

Community Advisor

@Rob_Hornick do you have any advice on hooking up internal decisioning (algos) to Adobe Target as the last mile of determining eligibility for running experiments?

Avatar

Level 2

@Eric_Vidana wrote:

@Rob_Hornick do you have any advice on hooking up internal decisioning (algos) to Adobe Target as the last mile of determining eligibility for running experiments?


Hi Eric, there are a few options you might consider here for bringing external decisioning data into Adobe Target.

  1. For product and content recommendations based on a key value (like customer ID or current product ID) that can be pre-computed, consider the "Custom Criteria" feature of Target Recommendations, which allows you to upload custom recommendations for each key value. See: https://docs.adobe.com/content/help/en/target/using/recommendations/criteria/recommendations-csv.htm... 
  2. For real-time rules-based targeting based on an external signal, you can call your external system prior to calling Adobe Target, then pass the signal to Adobe Target as a profile or mbox parameter.
  3. You can use Target's Data Providers capability to ingest external data sources: https://docs.adobe.com/content/help/en/target-learn/tutorials/integrations/use-data-providers-to-int...

This is an area of active investment for us. We're currently working on a feature, "Auto-Target with Custom Model", that will enable Target Premium users to bring their own model into Target's Auto-Target feature. If participating in a beta of this feature is of interest to you, please reach out through your Adobe CSM.

Avatar

Community Advisor

@Rob_Hornick I will do just about anything to get the 50 profile param limitation on AT 2.3 removed. Thoughts?

Avatar

Level 3

@Rob_Hornick why is AP and AT not an activity type of it's own i.e. and currently "inside" the A/B Test flow?

What is the difference between AP, AT and Recommended for you? Are all 3 using the same algorithm?

How would I be ablecable to use AT or AP together with a propensity score (hopefully from AA)? Any examples or tips how to achieve this?

Can you share some examples of websites that sucessfully use AP, AT or Recs.?

How do I use Recs. within a Single Page Application? Trigger Views?

Merci beacoup!

Nicolas

Avatar

Level 2

@Nicolas_Swisscom wrote:

@Rob_Hornick why is AP and AT not an activity type of it's own i.e. and currently "inside" the A/B Test flow?

What is the difference between AP, AT and Recommended for you? Are all 3 using the same algorithm?

How would I be ablecable to use AT or AP together with a propensity score (hopefully from AA)? Any examples or tips how to achieve this?

Can you share some examples of websites that sucessfully use AP, AT or Recs.?

How do I use Recs. within a Single Page Application? Trigger Views?

Merci beacoup!

Nicolas


Nicolas!  Great to connect with you and hope all is well in your neck of the globe!  Automated Personalization (AP) is its own activity type, but Auto-Target (AT) is embedded within the testing activity workflow for ease of "one-click" personalization, evaluating each individual's profile for determining the next best experience to deliver.  It makes it easier to consider utilizing personalization when considering traffic allocation to different experiences (when you are in the 2nd step of our 3-step testing activity workflow), and to consider leveraging our algorithms for dynamically decisioning for each individual (equivalent of taking action off of hundreds of tests in a single moment) 

 

A good reference for the underlying algorithms is our Automation Infographic: https://wwwimages2.adobe.com/content/dam/acom/en/marketing-cloud/target/pdf/54658.en.target.infograp...

 

Here is more information on our Recommended For You algorithm and use cases, written by Rob: https://theblog.adobe.com/delivering-dynamic-personalized-experiences-with-adobe-targets-new-user-ba...  

 

AT.js, our javascript library, is built for integrations within Single Page Applications.  This enables leveraging triggerviews for delivering experiences discretely within an SPA experience.  

Avatar

Employee

@drewb6915421 wrote:

@Nicolas_Swisscom wrote:

@Rob_Hornick why is AP and AT not an activity type of it's own i.e. and currently "inside" the A/B Test flow?

What is the difference between AP, AT and Recommended for you? Are all 3 using the same algorithm?

How would I be ablecable to use AT or AP together with a propensity score (hopefully from AA)? Any examples or tips how to achieve this?

Can you share some examples of websites that sucessfully use AP, AT or Recs.?

How do I use Recs. within a Single Page Application? Trigger Views?

Merci beacoup!

Nicolas


Nicolas!  Great to connect with you and hope all is well in your neck of the globe!  Automated Personalization (AP) is its own activity type, but Auto-Target (AT) is embedded within the testing activity workflow for ease of "one-click" personalization, evaluating each individual's profile for determining the next best experience to deliver.  It makes it easier to consider utilizing personalization when considering traffic allocation to different experiences (when you are in the 2nd step of our 3-step testing activity workflow), and to consider leveraging our algorithms for dynamically decisioning for each individual (equivalent of taking action off of hundreds of tests in a single moment) 

 

A good reference for the underlying algorithms is our Automation Infographic: https://wwwimages2.adobe.com/content/dam/acom/en/marketing-cloud/target/pdf/54658.en.target.infograp...

 

Here is more information on our Recommended For You algorithm and use cases, written by Rob: https://theblog.adobe.com/delivering-dynamic-personalized-experiences-with-adobe-targets-new-user-ba...  

 

AT.js, our javascript library, is built for integrations within Single Page Applications.  This enables leveraging triggerviews for delivering experiences discretely within an SPA experience.  


Here is a nice article illustrating the difference between AP and AT for your reference: https://docs.adobe.com/content/help/en/target/using/activities/auto-target-to-optimize.html#section_... 

Avatar

Level 2

@Nicolas_Swisscom wrote:

@Rob_Hornick why is AP and AT not an activity type of it's own i.e. and currently "inside" the A/B Test flow?

What is the difference between AP, AT and Recommended for you? Are all 3 using the same algorithm?

How would I be ablecable to use AT or AP together with a propensity score (hopefully from AA)? Any examples or tips how to achieve this?

Can you share some examples of websites that sucessfully use AP, AT or Recs.?

How do I use Recs. within a Single Page Application? Trigger Views?

Merci beacoup!

Nicolas


Hi Nicolas! Adding to what Drew mentioned: 

  • Auto-Target and Automated Personalization use a similar ensemble method combining random forest and Thompson sampling approaches, with one major difference. While Auto-Target builds one model per experience to predict the likelihood of conversion for a visitor, Automated Personalization builds one model per offer to predict the likelihood of conversion for a visitor. Auto-Target is useful for choosing a single experience among up to tens of experiences while Automated Personalization can select multiple offers among up to ~200 offers to compose a unique experience.
  • Recommended for You uses a very different algorithm based on collaborative filtering techniques performed with respect to items in the user's viewing and purchasing history. Rather than selecting from offers, it selects items from your business' Recommendations product or content catalog. Recommended for You is capable of choosing from among up to millions of potential items.
  • To leverage a propensity score in AT or AP, ensure that the propensity score is in the Adobe Target profile for each user. AT and AP automatically ingest all profile attributes for consideration in decisioning.
  • Recs can be used in a SPA at.js application using the TriggerViews function. Be sure to pass entity.id values for product/content views as appropriate.

Avatar

Adobe Champion

Hello - how can I get into the Conversation? first timer here - already registered, not seeing the link.  thanks.

Avatar

Community Advisor

Ha. I have a similar question. I think you are in it. AMA. Forum style.

Avatar

Level 2

@ActiveMitchell wrote:

Hello - how can I get into the Conversation? first timer here - already registered, not seeing the link.  thanks.


You are in the conversation/discussion thread - post your question and we'll respond as quickly as we can!

Avatar

Employee

@drewb6915421 wrote:

@ActiveMitchell wrote:

Hello - how can I get into the Conversation? first timer here - already registered, not seeing the link.  thanks.


You are in the conversation/discussion thread - post your question and we'll respond as quickly as we can!


Welcome @ActiveMitchell !

  • Click the blue “Reply” button at the bottom right corner of this post
  • Begin your Question with @Rob_Hornick 
  • When exchanging messages with Rob about your specific question, be sure to use the editor’s "QUOTE" button, which will indicate which post you're replying to, and will help contain your conversation with Rob

Avatar

Administrator

HI @ActiveMitchell ! Welcome As long as you are able to post in this thread, you're in the Conversation! Feel free to post a Question to Rob, with your message beginning with " @Rob_Hornick " - hope this helps, and we're looking forward to your questions!

Avatar

Level 2

Hi all! Looking forward to answering your questions today.

Avatar

Employee

Hi @Rob_Hornick, this question was posted in the community by @anils5920589:

 

Had a question on how Target derives reward probabilities for the MAB algorithms implemented for Auto Allocate, Auto Target and Automated Personalization activities.


Was going through your docs and found out that there are three ways of feeding data into Target:

  • mbox parameters
  • Profile parameters/attributes
  • Server side APIs for profile updates.

Since MAB algorithms need reward probabilities of each experience/variant as an input which change over time as more visitors participate in an activity, does Target derive the reward probability from the data supplied using the above methods ?

Avatar

Level 2

@surebee wrote:

Hi @Rob_Hornick, this question was posted in the community by @anils5920589:

 

Had a question on how Target derives reward probabilities for the MAB algorithms implemented for Auto Allocate, Auto Target and Automated Personalization activities.


Was going through your docs and found out that there are three ways of feeding data into Target:

  • mbox parameters
  • Profile parameters/attributes
  • Server side APIs for profile updates.

Since MAB algorithms need reward probabilities of each experience/variant as an input which change over time as more visitors participate in an activity, does Target derive the reward probability from the data supplied using the above methods ?


Hi @anils5920589

The Auto-Allocate multi-armed bandit feature is a non-contextual bandit so does not leverage the aforementioned attributes to derive a reward probability; instead it solely examines prior behavior at the aggregate level.

 

The Auto-Target and Automated Personalization feature act as contextual bandits and, as you've correctly inferred, leverage the provided profile and contextual (mbox) parameters to derive an estimated probability of conversion (per experience for Auto-Target and per offer for Automated Personalization). To learn more, see: https://docs.adobe.com/content/help/en/target/using/activities/automated-personalization/ap-data.htm... and https://docs.adobe.com/content/help/en/target/using/activities/automated-personalization/uploading-d...l .

Avatar

Administrator

Hi @Rob_Hornick this question was previously posted in the Community by @ambikaTewari_ATCI

 

Hi Experts,

As per help doc, Entity attribute values expire after 61 days. This means that you should ensure that the latest value of each entity attribute is passed to Target Recommendations at least once per month for each item in your catalog.

does this mean if the same value for an entity attribute is updated then attribute will not expire. ? or should it have new value for entity attribute not to expire?

Avatar

Level 2

@Amelia_Waliany wrote:

Hi @Rob_Hornick this question was previously posted in the Community by @ambikaTewari_ATCI

 

Hi Experts,

As per help doc, Entity attribute values expire after 61 days. This means that you should ensure that the latest value of each entity attribute is passed to Target Recommendations at least once per month for each item in your catalog.

does this mean if the same value for an entity attribute is updated then attribute will not expire. ? or should it have new value for entity attribute not to expire?


@ambikaTewari_ATCI (love the user name!), you do not need to change the value. Sending the same value will still let us know that the product data should not expire.