How we grew from 0 to 4 million women on our fashion app, with a vertical machine learning approach
My name is Gabriel Aldamiz-echevarría, and I’m the CEO and co-founder of Chicisimo. We launched three years ago, our goal was to offer automated outfit advice. Today, with over 4 million women on the app, we want to share how our data and machine learning approach helped us grow. It’s been chaotic but it is now under control.
Our thesis: Outfits & closets are the best assets to understand people’s taste. Understanding taste will transform online fashion
If we wanted to build a human-level tool to offer automated outfit advice, we needed to understand people’s fashion taste. A friend can give us outfit advice because after seeing what we normally wear, she’s learnt our style. How could we build a system that learns fashion taste?
We had previous experience with taste-based projects and a background in machine learning applied to music and other sectors. We saw how a collaborative filtering tool transformed the music industry from blindness to totally understanding people (check out the Audioscrobbler story). It also made life better for those who love music, and created several unicorns along the way.
With this background, we built the following thesis: online fashion will be transformed by a tool that understands taste. Because if you understand taste, you can delight people with relevant content and a meaningful experience. We also thought that “outfits” and “our own personal closets” were the assets that would allow taste to be understood, to learn what people wear the everyday occasions they dress for, and what style each of us like.
Online fashion will be transformed by a tool that understands taste. Because if you understand taste, you can delight people. “Outfits” and “personal closets” are the assets that allows taste to be understood
We decided we were going to build that tool to understand taste. We ended building the infrastructure to automate outfit advice: (i) a consumer app storing the clothes in your closet, and an interface focused on capturing the right input and providing the right output; (ii) a data platform that automates the jobs of interpreting incoming data (taste) and providing the correct output to the delivery mechanisms; (iii) a dataset that reflects what people wear, what people own in their closet, and how people think, when they think about clothes; (iv) and an IP portfolio protecting all of the above.
1st Step: Building the app for people to express their needs
From previous experience building mobile products, even in Symbian back then, we knew it was easy to bring people to an app but difficult to retain them. So we focused on small iterations to learn as fast as possible.
We launched an extremely early alpha of Chicisimo with one key functionality. We launched under another name and in another country. You couldn’t even upload photos… but it allowed us to iterate with real data and get a lot of qualitative input. At some point, we launched the real Chicisimo, and removed this alpha from the App Store.
We spent a long time trying to understand what our true levers of retention were, and what algorithms we needed in order to match content and people.
Three things helped with retention:
(a) identify retention levers using behavioral cohorts (we use Mixpanel for this). We run cohorts not only over the actions that people performed, but also over the value they received. This was hard to conceptualize for an app such as Chicisimo. We thought in terms of what specific and measurable value people received, measured it, and run cohorts over those events, and then we were able to iterate over value received, not only over actions people performed. We also defined and removed anti-levers (all those noisy things that distract from the main value) and got all the relevant metrics for different time periods: first session, first day, first week, etc. These super specific metrics allowed us to iterate;
(b) re-think the onboarding process, once we knew the levers of retention. We define it as the process by which new signups find the value of the app as soon as possible, and before we lose them. We clearly articulated to ourselves what needed to happen (what and when). It went something like this: If people don’t do [action] during their first 7 minutes in their first session, they will not come back. So we need to change the experience to make that happen. We also run tons of user-tests with different types of people, and observed how they perceived (or mostly didn’t) the retention lever;
(c) define how we learn. The data approach described above is key, but there is much more than data when building a product people love. In our case, first of all, we think that the what-to-wear problem is a very important one to solve, and we truly respect it. We obsess over understanding the problem, and over understanding how our solution is helping, or not. It’s our way of showing respect.
This leads me to one of the most surprising aspects IMO of building a product: the fact that, regularly, we access new corpuses of knowledge that we did not have before, which help us improve the product significantly. When we’ve obtained these game-changing learnings, it’s always been by focusing on two aspects: how people relate to the problem, and how people relate to the product (the red arrows in the image below). There are a million subtleties that happen in these two relations, and we are building Chicisimo by trying to understand them. Now, we know that at any point there is something important that we don’t know and therefore the question always is: how can we learn… sooner?
Talking with one of my colleagues, she once told me, “this is not about data, this is about people”. And the truth is, from day one we’ve learnt significantly by having conversations with women about how they relate with the problem, and with solutions. We use several mechanisms: having face to face conversations, reading the emails we get from women without predefined questions, or asking for feedback around specific topics (we now use Typeform and its a great tool for product insight). And then we talk among ourselves and try to articulate the learnings. We also seek external references: we talk with other product people, we play with inspiring apps, and we re-read articles that help us think. This process is what allows us to learn, and then build product and develop technology.
At some point, we were lucky to get noticed by the App Store team, and we’ve been featured as App of the Day throughout the world (view Apple’s description of Chicisimo, here). On December 31st, Chicisimo was featured in a summary of apps the App Store team did, we are the pink “C.” in the left image below 😀.
The app got viewed by 957,437 uniques thanks to this feature, for a total of 1.3M times. In our case, app features have a 0,5% conversion rate from impression to app install (normally: impression > product page view > install); ASO has a 3% conversion, and referrers 45%. BTW, we also built a method for growing through ASO, and published a related post on Alexa Skills SEO — Amazon Alexa Skills Store Optimization.
In the video below, you can view an iteration of our iOS app. It shows one of the mechanisms to add clothes to your personal closet, and how the system provides immediate ideas for your clothes.
2nd step: Building the data platform to learn people’s fashion needs
Our apps are built to allow people to express a what-to-wear need, from objective (type of garment, color, fabric, print…) to subjective (styles, occasions, age…). By accessing this information, we can do a better job at suggesting outfit ideas. The simple act of delivering the right content absolutely wows people.
Chicisimo content is 100% user-generated, and this poses some challenges: the system needs to classify different types of content automatically, build the right incentives, and understand how to match input and output.
We soon saw that there was a lot of data coming in. After thinking “hey, how cool we are, look at all this data we have”, we realized it was actually a nightmare because, being chaotic, the data wasn’t actionable. This wasn’t cool at all. But then we decided to start giving some structure to parts of the data, and we ended inventing what we called the Social Fashion Graph. The graph is a compact representation of how needs, outfits and people interrelate, a concept that helped us build the data platform. The data platform creates a high-quality dataset linked to a learning and training world, our app, which therefore improves with each new expression of taste.
We thought of outfits as playlists: an outfit is a combination of items that makes sense to consume together. Using collaborative filtering, the relations captured here allow us to offer recommendations in different areas of the app.
There was still a lot of noise in the data, and one of the hardest things was to understand how people were expressing the same fashion need in different ways, which made matching content and needs even more difficult. Lots of people might need ideas to go to school, and express that specific need in a hundred different ways. How do you capture this diversity, and how do you provide structure to it? We ended up building our ontology — a multilevel list of all descriptors that are needed to define an a fashion product or an outfit, and the relations among all these descriptors. It allows us to automatically classify content according to many factors, to easily match different catalogues, and for the team members to have a common language.
We now understand that an outfit, a need or a person, can have a lot of understandable data attached, if you allow people to express freely (the app) while having the right system behind (the platform). Structuring data gave us control, while encouraging unstructured data gave us knowledge and flexibility.
While users provide input and respond to output, the entire experience encourages them to provide further input. Input comes in the form of (i) expressed taste, such as expressing what type of style they like, expressing what occasions are relevant to them in terms of clothing, what type of clothing they like or own. Input also comes in the form of (ii) categorizing content, such as grouping outfits into described albums, tagging outfits, establishing correlations among items, providing relevant queries, etc. This input supplies our team with feedback to build more effective interfaces and accumulates data so we can respond to more complex inputs with it.
The end result is our current system. A system that learns the meaning of an outfit, how to respond to a need, or the taste of an individual.
3rd Step: Algorithms
Back when we built recommender systems for music and other products, it was pretty easy (that’s what we think now, we obviously didn’t think that at the time:). First, it was easy to capture that you liked a given song. Then, it was easy to capture the sequence in which you and others would listen to that song, and therefore you could capture the correlations. With this data, you could do a lot.
However, as we soon found out, fashion has its own challenges. There is not an easy way to match an outfit to a shoppable product (think about most garments in your wardrobe, most likely you won’t find a link to view/buy those garments online, something you can do for many other products you have at home). Another challenge: the industry is not capturing how people describe clothes or outfits, so there is a strong disconnect between many ecommerces and its shoppers (we think we’ve solved that problem. Also Similar.ai and Twiggle are working on it). Another challenge: style is complex to capture and classify by a machine.
Our ontology solved this problem. On top of it, our system converts fashion products into meta-products, which are abstractions of specific products of any catalog or closet. A fashion product is ephemeral, but its descriptors are not, so the system retains the value. A meta-product is the most basic yet relevant description of a product, and one of the first tasks of our infrastructure is to convert any incoming fashion product into a meta-product.
Why are Google, Amazon and Alibaba getting into outfits? There is a race to capture a $123b market
Outfits are a key asset in the race to capture the $123 billion US apparel market. Data is also the reason many players are taking outfits to the forefront of technology: outfits are a daily habit, and have proven to be great assets to attract and retain shoppers, and capture their data. Many players are introducing a Shop the Look section with outfits from real people: Amazon, Zalando or Google are a few examples.
Google recently introduced a new feature called Style Ideas showing how a “product can be worn in real life”. Same month Amazon launched its Alexa Echo Look to help you with your outfit, and Alibaba’s artificial intelligence personal stylist helped them achieve record sales during Singles Day.
😕 UPDATE: In Dec 2019, we announced we run out of cash 😕
I am editing this post to communicate that, sadly, we have not been successful as a business. You can read about what happened in this post: How to proceed when you run out of cash, but you still believe?
Email me if you want to say hi: email@example.com