Adobe Target

drewb6915421 · 4/3/24

Hello everyone! Looking forward to answering your questions and engaging in discussion around Adobe Target best practices!

Drburns27 · 4/3/24

And also welcoming you from my formal account!

Rajneesh_Gautam_ · 4/3/24

hello everyone - excited to be here today! While I have participated in Adobe Target Q&A Coffee break multiple times to ask questions, this is my first time to be on the other side to answer :). Please feel free to drop your queries here and we will try our best to answer those today!

Gokul_Agiwal · 4/3/24

Hi Everyone - as we're here to ask the questions based on the theme called "Unlocking AI-Powered Personalization"

Here are my few questions -

1) How can businesses effectively combine Adobe Target's AI capabilities with their own customer data to create more accurate and impactful personalized experiences?
2) What are the best practices for setting up and managing AI-powered personalization campaigns within Adobe Target?
3) In what ways does Adobe Target enable marketers to test and optimize AI-powered personalization strategies to ensure maximum impact? Any live use case I can use as reference.

Thanks

Drburns27 · 4/3/24

@Gokul_AgiwalGreat questions! Here are my responses:

1) Adobe Target's AI-powered capabilities, especially Auto-Target and Automated Personalization that evaluates in real-time each individual's profile (or a subset of profile data), utilizes all data made available to Adobe Target, so it automatically evaluates your customer data if brought in through API, Profile Core Services, or as a Destination for Real-Time CDP.

2) Best Practices are well-documented in our Adobe Target documentation. Nurturing of these campaigns depends on if you are looking for quick lift/performance improvement and feel confident in the experience variation choices or if you want to take time to evaluate the performance of the variations built relative to the conversion goal that the model is training on. This will dictate traffic allocation as you ramp up the algorithm to full performance. Also, these activities are very dependent on the location, experience variations and goal of the activity in terms of their performance as well - strategy is key based on your business goals!

3) Adobe.com's homepage is an Auto-Target activity and a good example of the ability to create a fully dynamic lobby experience while reporting on metrics beyond just conversions, including page load performance and many other important KPIs. These activities are automatically tested against a default experience, either random selection or a selected default experience; it is best practice to always test any strategy, manual or automated personalization, to ensure it is improving the experience over a static or default original experience and we provide this OOTB.

Gokul_Agiwal · 4/3/24

Thank you @Drburns27

Surely, I'll take a look on Adobe.com homepage - Thank you for highlighting this as reference.

niocolasmeriel · 4/3/24

Hi all, I wonder if when using Auto-Target it makes more sense to use Target as Reporting source rather than Analytics in order to obtain the 2 additional Reports inside Target? (I assume those reports are not available via A4T?)

Amelia_Waliany · 4/3/24

Indeed it is and thank you @niocolasmeriel for joining! What burning questions do you have for today's hosts? CC @Rajneesh_Gautam_ @drewdrewdrew and @shelbygoff

Drburns27 · 4/3/24

@niocolasmerielHi Niocolas! Good question: I love that I can answer "it depends". Our Insights reports in Adobe Target can be valuable in opening the real-time profile attribute scoring that our random forest ensemble set of algorithms in Auto-Target and Automated Personalization provides. It can show you attributes that are highly predictive relative to delivering different experiences to drive the primary conversion goal, and the segment discovery report shows you combinations of attributes or segments that are predictive. Soooo, if you want to dig into the predictability of the attributes being evaluated, Target reporting would be the way to go. If you want to answer performance impact beyond the conversion goal of Auto-Target activities, then A4T is valuable in more broadly reporting on impact across a customer journey and other factors that are impacted by the Auto-Target activity.

Amelia_Waliany · 4/3/24

Thanks for joining us today @Drburns27 @Rajneesh_Gautam_ and @shelbygoff ! The question below was posted by @Coops

From what I'm reading it appears that in the activity type I don't set the audiences, I just allocate all traffic. Then the algorithm works out which experience each individual customer would prefer based on their attributes. That correct?

Having a debate with someone experienced in using Auto-Target and they say the human determines the audiences and the AI simply works out which pre-defined audience prefers which experience.

Link to Original Question

Drburns27 · 4/3/24

@Amelia_Waliany @Coops I agree that the human can determine the audiences evaluated within an Auto-Target activity, as it evaluates audiences from your audience library, but the random forest ensemble also assembles its own audiences that it discovers as predictive during the course of its evaluation (up to 4 attribute combinations) which it provides in our Target Segment Discovery report.

Amelia_Waliany · 4/3/24

Thanks for joining us today @Drburns27 @Rajneesh_Gautam_ and @shelbygoff This question came directly from the Unlocking AI Powered Personalization Webinar Q&A:

Is the ability to constrain or exclude for a specific activity found within the Target UI?

Rajneesh_Gautam_ · 4/3/24

You can use blockList API (https://experienceleague.adobe.com/en/docs/target-dev/developer/api/models-api/models-api#_blank) however its not available within the Adobe Target UI. I believe its a really good idea to raise under the Ideas section of Experience League

Amelia_Waliany · 4/3/24

@Rajneesh_Gautam_ , @Drburns27 , and @shelbygoff : Here is another question from the Webinar Q&A to share with folks here who might be wondering after watching the 3/12/24 Webinar Recording:

What data is AP using to personalize? Is there a way to customize it?

Rajneesh_Gautam_ · 4/3/24

Adobe Target uses multiple data points collected by Adobe Target, Adobe Experience Cloud tools (AAM, RTCDP) and external data uploaded via Customer Attributes and RTCDP. The page below provides a comprehensive list of all data-points used: https://experienceleague.adobe.com/en/docs/target/using/activities/automated-personalization/ap-data

You can ask Adobe Target to exclude some of the attributes/features from personalisation-models using the blockList API: https://experienceleague.adobe.com/en/docs/target-dev/developer/api/models-api/models-api#_blank

Amelia_Waliany · 4/3/24

@Rajneesh_Gautam_ , @Drburns27 , and @shelbygoff Below is a helpful clarifying question from the Webinar Q&A:

Is there any way to use only particular segments to use the test instead of blockList?

Rajneesh_Gautam_ · 4/3/24

You can block specific attributes/feature or entire feature-sources e.g. AAM, GEO but not the specific segments.

niocolasmeriel · 4/3/24

In the new Target UI there is checkbox that allows to filter on "Auto Target with Custom Model". What is this and where can I find more information on this?

Drburns27 · 4/3/24

@niocolasmerielI will need to dig into this! We do have the ability to ingest a custom model with Auto-Target, but it is not an out-of-the-box feature so I will need to dig into how this is done. Stay tuned!

Gokul_Agiwal · 4/3/24

Hi - Quick question on AT implementation. - Sorry below question is not related to webinar but wants to check with @Drburns27 @Rajneesh_Gautam_

Adobe Target with Google Analytics 4. - Can we use Adobe Target TnT ID for audience segmentation purpose based on web behavior data? If yes, how this works when profile lifetime 14 days (by default) and extendable up to 90 days. What are the ways to re-target user after 90 days and show the personalization activities? And use of TnT is a best practice?

Rajneesh_Gautam_ · 4/3/24

hi @Gokul_Agiwal - thanks for the question! If Adobe Target is the only tool you are using (this means you do not use Experience Cloud service) then using TnTId is the best practice. Please use Adobe Target as first-party-cookie. As long as TnTId is used, you should be able to use all profile related features, including profile-lifetime.

For retaining visitors' profile beyond 90 days of inactivity, I will recommend exporting the data and upload in Customer Attributes.

Gokul_Agiwal · 4/3/24

Yes, not using ECID but as you suggested will see Customer Attribute and also thinking to look into profile API. Thank you @Rajneesh_Gautam_

jingle77 · 4/3/24

Our team has run a few auto-target and auto-perso campaigns with mixed success. I understand that you need a minimum 5% CTR for whatever the goal metric is. I've found that trying to increase clicks can be redundant and does not necessarily increase revenue. I believe it has been mentioned previously that revenue can be set as a goal metric. My question is: Can revenue be set as a goal metric, and is there some minimum threshold such as RPV?

Rajneesh_Gautam_ · 4/3/24

hi @jinjin6 -thanks for your question! Yes, you can use RPV as goal-metric. While using any goal-metric has some traffic + conversion requirements, RPV is bit more restrictive. Here's a screenshot of these requirements from Adobe documentation: https://experienceleague.adobe.com/en/docs/target/using/activities/auto-target/auto-target-to-optimi...

TiphaineJE · 4/3/24

Hi everyone, i have a few questions but i am new, and i am not quite sure it fit well the subject here.
Actually, i'm doing a master thesis in which i try to understand the impact of Ai-powered personnalization on conversion and retention stategies for b2b SaaS.

1. From your experience, what are the key factors that B2B SaaS companies should consider when customizing AI models within Adobe Target to drive conversion and retention? How do you tailor these models to reflect the complex customer journeys typical of B2B engagements?
2. In B2B SaaS, customer journeys can be lengthy and involve multiple stakeholders. How can Adobe Target’s AI-powered tools adapt to these dynamics to deliver relevant experiences at each stage of the customer journey?
3. Data privacy is a critical concern, especially in the B2B SaaS sector. How does Adobe Target ensure that its AI-powered personalization respects and upholds data privacy and security standards?
4. What are some common pitfalls B2B SaaS companies encounter when implementing AI-powered personalization strategies, and what best practices can you recommend to avoid them?

TiphaineJE · 4/3/24

Last one : Could you provide any data highlighting the significant differences, especially in terms of conversion and retention rates, between traditional personalization strategies and AI-powered personalization (if possible, within the B2B SaaS marketing context)?

Gokul_Agiwal · 4/3/24

Hi -

1) How can we ensure that automated personalization aligns with our brand's messaging and customer experience goals while adapting to individual user preferences?
2) What are the potential challenges or considerations to keep in mind when implementing automated personalization, and how can they be addressed effectively?

Adobe Target

☕[AT Community Q&A Coffee Break] WEDNESDAY 4/3/24, 8am PT: Unlocking AI-Powered Personalization Webinar Follow-up Qs (P3 of Personalization Maturity Series), w/ Target Community Advisor Rajneesh Gautam and Drew Burns of the Adobe Target Product team

AI Tools

Auto-Allocate

Auto-Target

Automated Personalization

Target

Learn

Documentation

Community

Support

Resources

Adobe account

Adobe