Personalization has always been a key aspect in almost all kinds of digital experiences. Some examples of commonly found personalization use cases are: allowing users to customize their dashboards or user interfaces, showing content based on explicit user-defined criteria, showing content based on implicit criteria or even that based on user behavior. All these required complex personalization systems, with processing and rules engines for creating and managing personalization rules. As a result, it has always been a non-trivial exercise to implement personalization in a resource-effective way. Artificial Intelligence (AI) and Machine Learning (ML) techniques have evolved and it is now much easier than ever to use these to implement personalization now. At a very simplistic level, personalization is about “predicting” what a user will like to see and then offering that to the user. You can make this prediction based on a complex hierarchy of rules or use historical data to make this prediction. The latter is exactly what machine learning-based techniques can do for you.
Delivering Right Content to the Right People
Consider this common scenario: You want to show content that is relevant to the user. For example, let’s say you run an events site and want to show events that are relevant to the user. To do this, you could create multiple rules such as rules that match a user’s and event’s locations, or show events based on user interests and so on. This works great, with maybe 5 rules. But consider a scenario where your users have 100s of profile and behavioral attributes and your events also have a similarly large number of attributes. So as you come up with more criteria, this rules-based business becomes really messy and difficult to manage. But with machine learning-based techniques, you now have alternatives. Plus you no longer have to procure sophisticated personalization systems. Instead, you can start writing very simple programs that can help you predict what kind of events a user would like to view depending on the events that other users with similar profiles viewed. You could use the same logic to display targeted news, movie recommendations or books. Some of these machine learning techniques are really simple and you can get started very easily. Here’s another example for the same events web site. As an event organizer, you create a new event but are not sure what kind of pricing would work best. Again, if you think of this problem as a prediction problem, as in “predict the price of new event given pricing of past events”, you could again use a simple prediction algorithm to recommend pricing based on pricing data for past events. Instead of events, you can use the same logic to price your new offerings or whatever. In addition, you can use this new data point as another input for your next prediction.
Start Small and Experiment
In addition to personalization, Digital Experience Management use cases can have several aspects for which you can start using machine learning. And there is no need to wait for your vendors to start offering additional AI/ML capabilities. Almost all programming languages provide APIs and libraries for all kinds of machine learning algorithms for clustering, classifications, predictions, regression, sentiment analysis and so on. The key point is that AI and ML have now evolved to a point where entry barriers are really low. You can start experimenting with simpler use cases and then graduate to more sophisticated use cases, once you are comfortable with basic ones.