Sign up

Il Sole 24 Ore

Evo from Turin, the artificial intelligence that wants to compete with Amazon

The software, developed in the incubator of the Polytechnic University of Turin, examines the fashion choices and draws data that anticipates market choices. So far, around 20 companies have benefited from his predictions. And the ambitions are growing.

Turin, October 12, 2019
by Natascia Ronchetti

The first to believe in Evo was the Miroglio group, which includes eleven brands, such as Elena Mirò, Oltre, Motivi, and Caractere. The group based in Alba (Cuneo), wanted to understand how to design collections, to manage purchases and to plan production facing demand volatility. Miroglio best practice has become a case study in the US, at the Harvard Business School.

Since then, Evo and its software, based on artificial intelligence, have helped about twenty fashion houses make the right choices. For example, to understand why in the fashion industry the Milan market is very different from Bologna or Paris ones; if a t-shirt sells well in Milan does not mean it will receive the same success in Bologna or Paris. Above all, they have learned to anticipate the trend of demand, with predictive analysis.

Evo is a young company. It grew up in the incubator of the Polytechnic University of Turin, and today it has two offices – one in Turin, one in London – and has 35 collaborators, almost all of them are data scientists. “Predicting demand overall, in the end, is not difficult – says Fabrizio Fantini, Evo’s Founder -. But if we limit ourselves to this, we do nothing but follow the story of Trilussa’s half chicken, an old story about statistical averages. And consumers have changed, they no longer buy what they find but buy what they want”.

This is how Evo breaks down and unpacks, with algorithms. It transforms products into “functional attributes” (type of sleeve, type of neckline, and so on) and into “style attributes”, which concern, precisely, the style, starting from a database that maps 1.2 billion consumers. Then the software “processes” the market data that filled based on the clients. Prices, products. But also, the characteristics of the main competitors. In the end, Evo transforms the data into predictive signals of market trends, to allow the clients to make systematic and profitable decisions.

Fantini is a management engineer with a doctorate in applied mathematics and a master’s degree in business administration from Harvard University. He addressed himself in the world of fashion, he explains, when “I discovered that for companies operating in the fashion sector inventory management is one of the main problems”. Today the system developed, taking into consideration many variables – from the historical sales to the geographical area to reach the climate – is able to support fashion houses in production planning, in stock allocation choices, in prices and promotions decisions, by combining advanced machine learning methods to statistics.

“Our dream now – says Fantini – is to allow companies to compete with global giants like Amazon, which have a huge availability of data”. Not only, however, in the fashion industry, which today is the core business of Evo. The next challenge will be the application to large-scale retailers to avoid food waste.

Hey! Was this page helpful?

We’re always looking to make our docs better, please let us know if you have any
suggestions or advice about what’s working and what’s not!

Send Feedback