Zuradigital — Recommendation Webhook Marketo LPs
Business Objective: The objective is to recommend the relevant articles for leads, based on their preference.
Problem Statement: Preference and relevance are subjective, and they are generally inferred by items users have consumed previously.
Content AI and Web Personalization of Marketo: I have used both of them in Marketo. The major drawback in both modules is that we don’t have access to the algorithm and the information is not tracked on leads one of the main metrics is what article they have previously viewed.
Both modules don’t work if the lead’s browser has opted for “do not track” which is becoming by default feature in the corporate setting and in all browsers.
Another problem which almost all recommendations system have is known as user cold start, in which it is hard to provide personalized recommendations for users with none or a very few numbers of consumed items, due to the lack of information to model their preferences.
Solution: So keeping this in mind, we have written a webhook that looks for the last view article by the lead and shows other articles that are most relevant to the business in the next subsequent visits.
We created a smart campaign that triggers “call to webhook” and “interesting Moment” whenever known lead visits the Marketo LP for the tracking purpose.
Below is the webhook call which we are making: Which gets triggered whenever someone visits one of the targeted landing pages.
Each visit provides different recommendations for each user.
Visit 1.
Webhook based Recommendation Engine Marketo
Visit 2
Webhook based Recommendation Engine Marketo
Visit 3
Webhook based Recommendation Engine Marketo
In the above use case, the list of content is managed by the client itself and we only provide the webhook that provides the recommendation. This can be a great start to track the lead’s interest and increase clicks in the blog posts at no extra cost if you compare it with other paid solutions.
To know more follow the link.