Sign up

Max Mara seminar

Let me just get started by introducing myself. My name is Fabrizio Fantini, and I am the Founder and CEO of Evo, formerly Evo Pricing. You may be asking yourself what someone from a pricing and supply chain logistics company could say that would interest leaders in the fashion world, but we have a lot to learn from each other.

I’m from Italy, born in a province called Pesaro, which is closely tied to major fashion brands like Max Mara, both culturally and geographically. Growing up in this environment where fashion was a way of life formed the foundation that would later help me build my company. While we may not have set out to specialize in the pricing and logistics for the fashion industry, it quickly became evident that we were a perfect fit.

While this upbringing may have been what sparked Evo’s eventual success, my company certainly wasn’t built overnight. An American author Robert Kiyosaki is famous for saying in one of his books, “My advice to the average investor? Don’t be average!” When I read this, I was inspired to build a life that avoided being average.

I started my career with 10 years as a McKinsey consultant, assuming that as industry leaders they would stay far away from average. Unfortunately, years of applying standard formulas in massive PowerPoint spreadsheets showed me that my quest to avoid average was still just out of reach. I decided to search for an above-average solution when getting my PhD in applied mathematics.

It’s easy to assume, therefore, that my quest to discover a non-average solution became a purely academic pursuit, irrelevant to the real world of tangible goods, but the opposite is true. Retail is an incredibly fast-paced and competitive market. Any progress made to help companies perform above their average has a massive impact on those companies’ bottom lines— and survival.

My PhD thesis became an algorithm to more accurately predict customer demand and behaviour, and that algorithm became a company: Evo. Evo delivers consulting and software to help businesses beat the average, and it’s working. Our first big successes came in partnership with Italian fashion group Miroglio. Our partnership was written up as a Harvard Business School case study in 2019 and also published in Business of Fashion.

So how do we get these results for our partners? We help them make better decisions with real-time, more accurate numbers.

At Evo, we spend our days analyzing data. We give partners the numbers they need to optimize prices, discounts, and balances. We also sift through the data to ensure an efficient supply chain, helping partners make better decisions throughout the supply chain, including purchasing, planning, inventory allocation, replenishment, and transfers. All this technical information is delivered to partners in an easily understandable and actionable format, so even though we live in the numbers, our partners don’t have to.

All of these decisions may seem somewhat removed from the factors that actually affect customers and thus somewhat less important to fashion brands. In reality, these are all key elements of customer experience.

Customers today are more demanding than ever. With quickly evolving trends and the immediacy of social media, companies must be able to deliver the exact right product in the exact right location at the exact right price in order to satisfy customer demand. This has become too complex for traditional methods of making pricing and supply chain decisions.

That’s how Evo can make above-average decisions possible. We use our database of over 2 billion customers to expand the data informing decisions and our AI to quickly analyze this massive amount of data and deliver clear insights on what it’s showing us. In the highly competitive world of fashion, this makes all the difference. Instead of depending on your internal historical data, companies have access to trends in over $100 billion worth of transactions. This makes the analysis possible by smaller companies just as powerful as that done by giants like Amazon.

The fashion world has changed because the customer has changed. While we once were in a “push” market where customers would buy whatever trusted brands offered, the digital economy has empowered customers to demand exactly what they want, right down to the perfect size, style, and colour. “In this “pull” market, customers won’t settle for an alternate product; they’ll go online and search elsewhere for their perfect match.

This change makes it almost impossible for fashion companies to deliver upon customers’ exact demands using standard methods. We not only get the wrong answers, but we’re also asking the wrong questions in the first place. Despite improvements in how quickly we can make calculations, most companies are essentially using data in the same way they did in the 1950s. These methods bet on past behaviour to make their best guess as to what consumers will need in the future. “Average” performance is inherently built into the system. In fact, it’s the desired outcome.

Evo’s goal is de-averaging. That is, we want to stop companies from assuming that their best bet is to treat every store the same, disseminating the same mix from their collections to all stores at the same time and hoping that the average performance across the entire network will be good enough to outweigh problems like overstocks and sellouts at individual stores. Evo instead uses data at the granular level, drilling down to allow companies to easily make decisions at the level of individual products at individual stores.

Rather than attempting to optimize the system as a whole and falling short, Evo can use its algorithm to actually optimize the performance of each product and each store. We de-average to improve individual product performance and in turn, improve overall returns for above-average results. This is a revolutionary turnaround for our partners.

It’s easy to feel confused by this concept because of the technical nature of forecasting, as well as the added complexity introduced by new ideas like artificial intelligence and machine learning. That’s why we often compare ourselves to GPS. Why? First of all because of how our technology works. The GPS device itself is incredibly complex. It uses cutting-edge technology and complicated logic that the average person would struggle to understand, but the user interface is incredibly simple. Anyone can use it. In addition, GPS gives you an ever-adjusting path to reach your destination. It tells you if you have to go straight or to the left or right. You get an alert when you need to change your route because road conditions change. This is basically what Evo does. We take large amounts of data and rather complex algorithms to give management simple directions on the best paths to reach their goals.

As a “GPS for business decisions”, Evo can pinpoint and prevent problems coming before they would usually be seen. Take markdowns, for example. Typically, these are a sign of a problem. There is an overstock, and the store discounts the merchandise to get rid of it. Usually, discounting decisions are made somewhat arbitrarily across the board. First, products are marked down 20% or 30% for a few weeks. Whatever isn’t sold is later further discounted, leading to markdowns of 50% and then perhaps even more. These markdowns rarely maximize profits.

Evo, on the other hand, can look at a potential overstock long before it occurs and adjust to maximize profit and eliminate waste. This often can mean adjusting inventory allocation to prevent it in the first place. Other times, we can suggest a strategic discount for every item that will be unique in every store based on data-based simulations. Instead of a desperate bid to eliminate unneeded inventory, markdowns become a way to maximize the profit on those items without waste. This may mean a less standard approach and a mix of sales rates, but it delivers better results. Ultimately, Evo gives companies novel approaches to standard practices for more modern and less average results.

Most importantly in this GPS analogy, the companies themselves are still the drivers. Our partners take the information and advice that Evo’s technology gives them and decide when and to what extent to apply these suggestions. This allows human insight and instinct to continue to drive the company behaviour. For example, if the algorithm suggests different discounts in different stores, a brand may decide this inequality isn’t in line with their image. This suggestion can be rejected and an alternative method will be used to optimize results instead.

Our partners use the Evo algorithm to maximize returns and make the most informed decision. Ultimately though, they are in the driver’s seat and the technology adjusts to their behaviour to give optimal decisions going forward with actual choices of the company in mind. A GPS can give you directions and maybe even someday drive the car, but it will never be able to tell you where you should travel. So too, Evo can give you the best strategic options for reaching your goals, but never define those goals or ultimately who you are as a company.

Through my work with Evo, I believe I’ve finally fulfilled my dream of helping businesses stop being average. We empower our partners to make better decisions. Now all that’s left is to discover which companies are ready to leave average behind.

About the author

Fabrizio Fantini is the brain behind Evo. His 2009 PhD in Applied Mathematics, proving how simple algorithms can outperform even the most expensive commercial airline pricing software, is the basis for the core scientific research behind our solutions. He holds an MBA from Harvard Business School and has previously worked for 10 years at McKinsey & Company.

He is thrilled to help clients create value and loves creating powerful but simple to use solutions. His ideal software has no user manual but enables users to stand on the shoulders of giants.

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