Use Cases

Personalized Recommendations with AI

Recommend the right products, services and discounts to your customers with Artificial Intelligence (AI)


Personalized recommendations has several denominations : predictive marketing, hyperpersonalization, individualized marketing...It consists in improving user journey and increasing conversions by showing to customers service/product/content recommendations that are relevant to them.

In Machine Learning terms, this is called a recommender engine.

Recommender engines are not only used in marketing. We have experience in developing recommender engines for other use cases.


Whether in B2B or in B2C, predictive marketing is becoming more and more common for companies that have large pools of products or customers. Hyperpersonalization is about promoting the right product or service to the right customer at the right time.


  • Increase cross-sell: Cross-selling is the action or practice of selling an additional product or service to an existing customer. AI can help you increase the value of a customer or customer basket by recommending new products to an existing customer.

  • Increase upsell: Up-selling is the practice of encouraging customers to purchase a comparable higher-end product than the one in question. AI can help you increase cross-sell to certain customer segments or markets.

  • Improve customer journey and retention: Studies show that customers are looking for personalization in their journey. Helping a customer find something that she/he may like, through relevant product recommendations, increases customer satisfaction and retention.

  • Develop new business models: What if you could use product recommendations to provide additional services to your clients, suppliers, or partners? This is the case for some companies who develop new business models or extend their business model so they can find an additional lever for their data.


Kantify has developed a performing AI model and solution that can be tailored for several use cases.

Its specificity is that it can enable "algorithmic serendipity". "Algorithmic serendipity" helps to propose new suggestions to customers, that are not in their usual customer profile.

In other words, we avoid that the customer falls in a "filter bubble" where he would not discover products that are out of his usual comfort zone.


One of our latest case studies is a recommender engine for a lunch benefit company, Monizze. Monizze is a growing Belgium scaleup, part of the Up Group, that uses technology as a vector of its growth and competitive advantage.

  • Challenge: The challenge was to create a solution to provide the users of the Monizze mobile application with relevant restaurant recommendations at all points of the day and in the whole of Belgium.

  • Solution: Kantify has developed a personalized recommender engine that can define in real time what will be the relevance of a restaurant for a specific user.


Are you curious to explore how you can use personalized recommendations to improve your marketing?

Just get in touch, we will be back to arrange a call.