Automating outfit advice

Chicisimo is building the infrastructure to automate outfit advice, and is shipping it to people via its consumer app. In order to do this, we’ve built three assets: a data platform which is connected to a live environment, our app, and an IP portfolio that protects all of the above.

Chicisimo’s main asset is its Social Fashion Graph, a data platform that receives and interprets the clothing habits of each individual. It classifies any type of input (expression of taste) into understandable data, and captures correlations among inputs (how descriptors, outfits and people interrelate). On top of this clean and correlated data, we’ve built a system to deliver outfit ideas in a meaningful way, using discovery, search and recommendation technologies. We are working on personalizing content based on personal characteristics, and on exposing the reality of street clothing trends.

The backbone of the Social Fashion Graph is our ontology. It is a list of the what-to-wear needs, as expressed by people.

Chicisimo’s consumer app captures what clothes women have in their closet and their clothing habits. It is helping us identify what are the required elements to create the “Spotify of fashion”: what’s the correct interface to capture input? how does output need to be provided? what are the algorithms and incentives to manage content? The more transparency we provide to ourselves and the better our internal tools become, the more we understand the data. And that’s how all of the above evolves.

We are a team of 8, 100% remote, with large experience in automation, data classification and consumer behaviour.  

The Social Fashion Graph

The objective of the Social Fashion Graph is to provide structure to the data generated by people. And the objective of this structured data is to enable automated and personalized services.

The Social Fashion Graph has two fundamental tasks: (i) classify input: it converts any expression of taste into structured data, regardless of how the input was expressed; (ii) capture correlations among data: it captures how needs, outfits and people interrelate.

As a result of the above, the Social Fashion Graph produces clean and correlated data, a well curated and growing clothing dataset that learns from the real world. This structured data is an enabler of services. As of today, we have built a search engine for outfit ideas, and recommender engine powering a number of features. We are also working on personalizing content based on personal characteristics.

The Social Fashion Graph also collects the reality of street clothing trends, as expressed by people. This is unique data that only exists offline. We are now starting to expose this data in our internal tools. Also, by talking with players in the industry, we are starting to understand where this needs to be, a couple of years from now.

The backbone of the Social Fashion Graph is our ontology of the world’s what-to-wear needs. It summarizes and gives structure to what to wear needs, as expressed by people.

We think the ontology is pretty unique, and here is why: The traditional fashion taxonomies are a list of tags describing garment characteristics. This approach is understandable, because it is looking at clothes through the lense of other products it has worked on before (songs, books, electronics…). These other lines of products had pre-defined databases, obvious matching systems, and a type of metadata much closer to the way people describe those products.

We have learnt that what to wear needs go well beyond garment-related metadata, and of course these needs are expressed in very different ways. In the age of deep learning and substancial algorithmic advances, next generation fashion taxonomies are transparent and capture the world through the eyes of people, not through the eyes of the industry.

This social, bottom-up approach contributes to smarter algorithms. It also expands the discovery experience: it empowers shoppers to look at each other to decide what to wear and what to buy, instead of having to look at the traditional gatekeepers.

Thanks for creating this fashion app, it helps me enjoy my clothes, great outfit planner
I love fashion, and feeling pretty makes me feel stronger. This wardrobe app helps me getting there
I totally love helping other women with my selection of fashion ideas

Creating the interface for people to provide their input

In our opinion, one of the obstacles towards personalization in fashion, is product related. How can we create interfaces for people to provide their input?

This is one of the most important objectives of our mobile app: to build the right interface where people can provide their input, and then receive a relevant output. Interestingly, interfaces are 100% dependant on the technology and data behind the content, and obviously on the ability to truly understand the user problem.

In our case, the interface evolves rapidly together with the possibilities provided by our ontology and Social Fashion Graph. And we build the two by exclusively focusing on the very specific problem that our users need to solve.

If you haven’t, play with our app with this in mind.

Obviously, we love the feedback we receive, and how we are regularly featured by Apple as App of the Day in more than 60 countries, and being Android’s Best App in 2015 and 2016.

We are creating a high-quality, vertical dataset, by digitizing offline data

The data required to understand people is, today, mostly offline. What I have in my closet, what I am wearing now, what my context is. This data is also very disconnected to how fashion describes clothes.

At Chicisimo, our effort consists on digitizing this data, and making it available online.

The evolution of the music sector can explain the future of fashion

The way we enjoy our clothes and find new ones is going to change. The fundamentals of this change can be explained by looking at the music sector.

In the old days, we used radiocassettes to listen to music. We did not have an online service that could understand our taste and help us find new music. “Discovery” was limited. Years later, Audioscrobbler was born and built a mechanism for us to express our taste, by tracking the songs we played. These data we started to produce was then matched against online databases of songs that were also being built then. This new data allowed product builders to create new discovery experiences, giving birth to online music as we know it today.

Availability of people’s taste, and classification of content. At Chicisimo, we love how the future looks on top of this new understanding.

“I need ideas to wear this violet sweater to class tomorrow”

Did you know that most people combine violet sweaters with black pants, black boots or black blazers? Also, violet sweaters are more common during fall/winter than during spring/summer. And they tend to be worn during casual settings rather than formal.

Data is cool. But being able to recommend the right outfit for the violet sweater you have in your closet, requires a deeper understanding of what someone likes and needs, and the ability to match input to output. It also requires creating the right environment for people to express their needs, where inspiration and discovery can take place.

The above is specifically what we are building.

Fashion. 10 years from now

A decade ago, we did not have Spotify. A decade from now, we will have several “Spotify for clothes”. Closet apps that have strong meaning for us, and help us in very specific ways. There are some specific use cases we like, that fit well together:

  • Automating outfit adviceAmazon, Alibaba, Chicisimo
  • Image understanding (Most ML efforts are here)Wide-Eyes,, ViSenze
  • Systems to match outfits and shoppable productsInstagram, Pinterest, Amazon, Chicisimo
  • Discovery of clothesAmazon, Zalando, Asos, Chicisimo

If the above makes sense to you, please

We use our own and third party cookies to offer you a better user experience. When you use our services, we understand that you accept the use we make of cookies.