Sign up

Help Evo improve fashion forecasting!

Evo is excited to work with students at the Politecnico di Torino to develop a new algorithm that optimises trend forecasting in fashion. We have partnered with the CLIK innovation lab at the Politecnico to put on a business challenge for a competition called CHALLENGE@PoliTo. Our challenge is “A.I. 4 fashion trends”, which will focus on improving fashion companies’ ability to accurately forecast style trends at an earlier stage and thus plan production better.

This challenge was originally planned for Spring 2020, but was delayed due to Covid-19 closures. Now the challenge is being relaunched for the fall/ winter semester. It will be a bit different than past challenges, but our team is happy to work with these students in this new normal, regardless of the structure.

From October 2020 to January 2021, teams of Master’s students from engineering and data science programs will work together to identify the primary factors that influence purchasing behaviour in fashion and the types and sources of data that will reveal trends in these factors. Then, each team will create a working algorithm that will analyse and accurately forecast trends.

Applications to participate have reopened for new and previously shortlisted teams and will close by the end of the day on September 13th. Anyone interested can learn more online or by reaching out to CLIK at clik@polito.it. We are excited to see who will meet the challenge!

What will “CHALLENGE@PoliTo – A.I. 4 fashion trends” participants be doing?

If you decide to participate on a “CHALLENGE@PoliTo – A.I. 4 fashion trends” team, it is going to be a busy but rewarding few months. After developing a working solution over the course of the competition, students will pitch their ideas to a team of judges (including our Evo experts!). The team with the best idea will win and be celebrated at a virtual or, if possible, in-person reception hosted by the Evo team. Whether you win or lose, you will receive academic credit for your efforts worth 8 curricular or extracurricular hours.

In addition to working on their own, teams can use Evo as a supportive resource. We will host the teams virtually for a visit during the project, when we can show them how we work— and how much fun it is to develop innovative solutions for our clients as a career!

Why focus on fashion forecasting?

It may seem odd to have students in technical fields devote their time during this competition to predicting what styles are going to be in fashion next, but fashion forecasting is serious business. Thanks to social media and other factors, demand in the fashion industry has become incredibly volatile. This makes it almost impossible for companies in this industry to effectively allocate resources to plan production. Retailers end up creating unnecessary waste that is bad for the environment and the bottom line.

The fashion industry is turning to AI to better anticipate demand. Companies like Evo are able to deliver more accurate demand forecasts and eliminate inefficiencies in the supply chain. Students can learn a lot by innovating new ways to predict trends in an incredibly volatile market. After all, the biggest challenge for data scientists today is not getting enough access to data. It is identifying the right data and data granularity to predict trends accurately.

We know the students at the Politecnico di Torino are up to the task. We cannot wait to share their successes throughout this process as we find a better solution together.

About the author

Kaitlin Goodrich is Evo’s main storyteller who helps communicate Evo’s message to the world.
Kaitlin received her BS in International Affairs and Modern Languages at Georgia Tech and then an LLM in International Trade Law from the University of Turin. She worked in Latin America doing education outreach for U.S. binational centers and has since worked as a content writer for international clients.
In her free time, she likes to travel or curl up with a good book.

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