how to do real hyper customization in e-commerce?

“Profiling” matches the user of a website to a typical profile in terms of behaviors such as “the user who comes to buy a single item”, or “the one who is exclusively interested in the world of sneakers”.

Where the “classic” profile relies on user profiles or segments defined by marketing or business teams, hyperpersonalization takes us further. It is now possible, thanks to Artificial Intelligence, for an e-commerce site to create segments directly linked to user profiles and behaviors, covering many more uses.

Additional personalization also gives the user a “unique” experience fully tailored to their needs. One of the best examples of hyperpersonalization is YouTube or Instagram suggestions. They are based on the behavior of the user and others identified with similar interests, to offer more relevant content.

In what contexts is hyper personalization used?

With the advent of machine learning and the explosion of e-commerce, several opportunities have arisen for companies:

  • Machine learning, which now makes it possible to offer real-time data processing as well as relatively simple application implementation by data scientists and technical teams.
  • The evolution of user behavior monitoring solutions that provide access to new data on consumer habits (buying behavior, segmentation, etc.) of retailers.

Hyperpersonalization in e-commerce results in the collection of user data, as well as the collection of interactions between the customer and the articles, respecting privacy (GDPR, etc.). To better take advantage of this data and make it speak, the questions arise: through which channel did the user arrive? How did you interact with the product? What items were viewed, added to cart, purchased? Which categories were consulted? How long it was on the page, etc. ?

The answers to these questions allow you to define what the user likes the most. It is this knowledge that makes it possible to create unique experiences with much more effective engagement funnels (step succession).

Hyperpersonalization in e-commerce is mainly used on two axes: engagement and conversion rate.

By offering relevant articles to users, you can create engagement funnels much easier. The user experience is also considerably improved thanks to a deeper understanding of the “profile”. With a well-categorized dataset, you can know which categories are most meaningful to a customer and therefore build your website journey accordingly. This personalization has a direct positive impact on conversion rate.

What approach to take to do hyper personalization?

The approach most used by e-commerce sites today is relatively simple. It’s about combining interactions between users and articles. Then, based on the number of views, recommend the ones that are most successful. This approach can be easily implemented. However, it will reach its limit very quickly, at several points.

At first, only the most viewed articles will be recommended, creating a self-sustaining loop. Thus, it will be difficult to integrate new products into the system. As for commercial data, they will be biased, rendering the entire process unusable. This approach also excludes the exploratory part, making it possible to bring up so-called “back catalog” articles that are relevant to the user.

It also involves regular updating and maintenance of the relational model leading to a waste of time for teams.

Predictive models are now more powerful than behavioral models used in the past.

This is where Big Data and Machine Learning come into play. In recent years, with the increasing simplicity of technical implementations, machine learning and cloud platforms, it is becoming easier to place a model with much more relevant results.

Where the approach has been limited to upstream creation and analysis (profiling, user pathing and implementation), machine learning will in turn have a data-centric approach whose path is as follows: data definition, creation user segments, model building, and machine learning implementation.

An example that is used in electronic commerce is language models and syntactic construction to suggest articles that may be of interest to users. The method is similar to the text generators we’ve seen for a few years, where thanks to deep learning it’s possible to “predict” the next word in a sentence. When writing, for example, in Gmail “How are you”? or “Did you have a good vacation?” the text editor will ask the user “did you have a good vacation?” “. In other cases, words you can use are scored. “The screwdriver is…” will give a score of 70% for the most likely word, then 50% for another proposition… When using these methods for product recommendation, these approaches lead to better relevance of results, as opposed to a solution based only on statistical data.

Predictive models are now more powerful than behavioral models used in the past.

The predictive model takes on its full meaning thanks to cloud platforms that now offer (for the most part) a range of services that can optimally collect data and exploit it, but also allow you to build and deploy AI and machine learning from all cloud advantages (costs, scalability, high availability).

For personalization, this is also a considerable advantage. Some public clouds like AWS and GCP offer managed services that are easy to configure and require little maintenance (such as “Personalize” on AWS, which uses Amazon and Prime Video’s recommendation engine, or “Recommendation AI”, its GCP equivalent) .

It’s tomorrow ? A homepage in your image!

With the right tools and the right experts, hyper-personalization can happen quickly. Some large groups already use it and use extremely powerful tools to define hyper-directed communication strategies.

For example, the StockX website has added a simple “Recommended products for you” line to its homepage (it uses AWS Personalize to process the data). That simple extra line quickly became the most successful area of ​​their homepage!

One of the main projects underway is creating ultra-personalized user experiences. The objective is to offer spaces that fully correspond to the user’s profile.

Amazon, for example, completely adapts its interface according to the user’s profile. For example, the category list is sorted differently depending on purchase history.

But the challenge today to differentiate is greater. Currently, hyperpersonalization naturally focuses on transforming site visits, but new approaches will emerge. As mentioned earlier, using predictive models can have other impacts: what if we used the predictive model to manage inventory? What happens if we use an e-commerce solution on written content? The playing field is immense and the evolutions are certain.

Leave a Comment