Sign up

AI will not replace humans, collaborating the two is winning

The Turin startup Evo Pricing reveals a new innovation frontier based on big data

December 8, 2016

Are clothing stores retailers able to predict future sales based on big data systems? This may well be a “miracle” that tempts any business throughout the year, not just at Christmas time and during sales period.

An Italian startup has developed a winning formula: a combination of artificial intelligence and human experience, which proved that even in retail, it beats any computer system. Past data feeds complex algorithms, which allows the system to learn about the future, by observing the past. Users can use their own past experience to quickly formulate hypotheses about the future. In a dynamic world, such as fashion, in which speed is crucial, the algorithm alone is therefore less powerful when human intuition is missing.

Evo Pricing is well aware of this; the predictive analytics Turin-based startup, established in 2013 is today serving retailers all around the world thanks to a team of business experts, data scientists and researchers from prestigious universities, such as Harvard and MIT.

Every week over 300 people in Italy alone contribute to Evo Pricing’s system – including retailers and store managers – thanks to a structured input system, based on non-monetary incentives and a simple process.

“The intuition was born from my many years of work at McKinsey alongside top managers from all over the world, watching the untapped potential inside each company” – explains Fabrizio Fantini, Evo Pricing’s founder and CEO – “we are proud of our system today, the human intuition improves the results of artificial intelligence, their combination reduces 40 percent of errors, so decisions become more accurate and sales grow by more than 10 percent.”

Variables such as past sales, geographical area, climate and product’s characteristics are used for the initial data-based prediction. Thanks to a real “borsino”, the stores can change their forecast, to the extent of exchanging their goods directly, if profitable, improve their inventory management, promotions and marketing strategies. It is not sci-fi: just like in the famous movie Next – inspired by the short story “The Golden Man” by Philip K. Dick – Nicolas Cage says: “Here is the thing about the future. Every time you look at, it changes, because you looked at it, and that changes everything else.” This cycle of lifelong learning is just what Evo Pricing helps to automate.

“In Turin, for example, seasons are different from Palermo” – tells the store staff – “It’s easy to describe, but with so many shops it becomes impossible for the head office to take it carefully into account. So, in the spring, when the padded warmer jackets aren’t selling in warm regions any more, the flexibility of this new system allows us to take advantage of this information and to stock up to satisfy our real big demands. The results are excellent.”

Another example is Novara, which tested for the first time in their history, the demand for beach products: when the small initial sample has sold out quickly, the system has discovered the opportunity and learned of a tendency unknown until now, developing it further.

“We are publishing our results with Harvard University, demonstrating that the demands of the “Borsino” can approximately forecast the performance of supply-demand binomial eight week in advance” – ensures Giuseppe Craparotta, senior data scientist at Evo Pricing – “this is a one of kind work, based on effective measures of product popularity for which the human contribution is essential. Many retailers are surprised when they discover that their daily contact with the public and their product is the decisive factor: the algorithm’s soul”.

Download PDF: English / Italiano

For press-related queries please contact press@evopricing.com

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