AI News, How we grew from 0 to 4 million women on our fashion app, with a vertical machine learning approach

How we grew from 0 to 4 million women on our fashion app, with a vertical machine learning approach

Three years ago we launched Chicisimo, our goal was to offer automated outfit advice.

We saw how a collaborative filtering tool transformed the music industry from blindness to totally understanding people (check out the Audioscrobbler story).

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.

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 (*Nir Eyal’s book Hooked: How to Build Habit-Forming Products discusses a framework to create habits that helped us build our model);

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).

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).

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.

Python programming for beginners: What can you do with Python?

Python Programming Language: What can you do with Python? Get discount here: Read article: ..

Why you should make useless things | Simone Giertz

In this joyful, heartfelt talk featuring demos of her wonderfully wacky creations, Simone Giertz shares her craft: making useless robots. Her inventions -- designed ...

Challenges and learnings of building for the next billion users (Google I/O '18)

Building products and services that work for everyone regardless of where they live, what language they speak, which devices they use, or the network they're ...

Steve Jobs' amazing marketing strategy - MUST WATCH

Steve Jobs shares his amazingly different approach to marketing and how he used it to build Apple into one of the largest companies in the world. * Join my ...

Customize Material Components for your product (Google I/O '18)

Take advantage of Material's new expressiveness and adaptability by learning how to customize Material Design Components and quickly build beautiful ...

Build great Material Design products across platforms (Google I/O '18)

Come learn how to streamline your cross-platform development with Material Design's new tools and open-source code—for Android, iOS, web, and Flutter.

UX and APIs that developers and users love (Google I/O '18)

Delight is a key principle of Firebase product development. From automatically creating user audiences with Predictions, to receiving emails on bugs that ...

Getting started with App Actions (Google I/O '18)

App Actions can help you increase discovery and reengagement for your Android apps by allowing you to signal their useful capabilities and content to users of ...

How to Crack any Software

This is just for learning. Softwares used: W32Dasm HIEW32 My New Tutorial Link - (Intro to Crackin using OLLYDBG) ...

Actions on Google: Building Apps for Assistant

We've updated the Facts about Google sample to use Cloud Functions for Firebase instead of Cloud Functions as Sachit shows in the video. FYI: API.