Recommender System: Who knows You Better Than Yourself?


As Steve Jobs once said, “people do not often know what they want till they see it”. Nowadays we are the target of innumerable messages which “advise” us goods or service acquisitions we would have never made had they not been pulled under our nose, therefore pushing us to new needs or waking up latent ones.

Some concrete examples*:

  • Two thirds of films watched on Netflix are suggested to users by the famous video streaming platform
  • Google News: 38% of click-throughs are originated by links suggested by the web giant’s algorithms
  • Amazon generates a good 35% of its sales from suggestions to users

(*) Source: Netflix

Behind these focused suggestions there are systems which can be most complex: the recommender systems. These systems have the following objectives:

  • Maintain customer’s loyalty
  • Increase service users’ traffic volume
  • Provide a user experience (UX) as focused on expectations as possible
  • Widen market limits

But, above all, make people buy what we want to sell. From a more technical point of view, the problem a recommendation engine faces is developing a mathematical model or an “objective” fuction which can foresee how much a user will desire a product or service. Reccomended System definition

For every “u” user, it is necessary to choose the “i” element which maximizes the “objective” function. content-basedfiltering_ collaborativefiltering

There are several recommendation typologies:

  1. based on content: “you have read a book, I suggest similar books”
  2. based on correlation among users with similar characteristics in their purchase model

And it is right here artificial intelligence joins the game: the recommender systems which take advantage of artificial intelligence were born with the aim to advising users about objects they had never bought before! Similarity among users can be calculated in various ways:

  • social network: the assumption is that two «friends» on a social network should have common interests
  • past valutations: certain particular patterns are “discovered” from the analysis of past users’ valutations

How is it possible to know whether a recommender system works?
Here below some valutation meters:

  • Precision: Which is the difference between a real rating and its prevision?
  • Diversity: How diverse are recommendations?
  • Coverage: Which is the space percentage for user elements that can be recommended?
  • Serendipity: How surprising are pertinent recommendations?
  • Novelty: How surprising are recommendations in general?
  • Relevance: How relevant are recommendations?

That said, we cannot not consider the fact that recommender systems have a tremendous potential in supporting omnichannel sales, anticipating customers’ wishes.

Le persone al centro
Maurizio Bovo
Hardware maintenance: how to guarantee Business Continuity
Learn more
People·Service Desk
Barbara Bettin
Aton’s Service Desk is not a Help Desk
Learn more
Fashion · Prosperity·RFID
Tania Bertolin
The Source Experience Room: a journey in the company of RFID and NFT
Learn more
Retail · Retail management
Cristiano Negri
Master Data Management: the death of silos
Learn more
Giuseppe Brando
Aton’s solutions for the LPG market
Learn more
Retail · Retail management
Alberto Canova
Cegid’s Innovation Store: the new retail challenges
Learn more
Ecco alcune delle nostre esperienze

Gruppo Poli

Retail Vendite Omnichannel
Poli has combined tradition and innovation in its way of doing business with a focus on employees, customers and the local area. In Aton, it has found a…
Discover more


Food & Consumer Goods Vendite Omnichannel
Cattel S.p.A, a leading company in Northern Italy in the distribution of food products in the Ho.Re.Ca channel has profoundly transformed the order collection by adopting the Aton .onSales B2B solution.
Discover more


Industrials Supply Chain Solutions
All projects, whether successful or not, have stories to tell. A difficult uphill start, a start full of hope, repeated twists and turns where the viewer is swept away by…
Discover more


Fashion Service Desk
Aton ServiceDesk is also behind the scenes in the first Boutique entirely dedicated to the Moncler Enfant collection, opened at the historic premises in Milan, Via della Spiga 7, which has been…
Discover more


Food & Consumer Goods Omnichannel Sales
A real-time photography of the Mass Market Retailers’ world to measure Trade Marketing activities efficacy in points of sale in Italy, France and Spain: with this target in mind, Aton,…
Discover more


Food & Consumer Goods Omnichannel Sales
Managing their customers often takes up the whole of sales people’s time. Just caring about relationships with already acquired customers (also defined as nurturing) is not enough to achieve growth objectives,…
Discover more