August 4, 2017 at 3:25 PM
Seems like the term Machine Learning is popping up in mainstream media as the next big thing. The fact is, however, that Machine Learning went mainstream a long time ago. You don’t think so? Check your mobile phone. Chances are you’ve been using and benefiting from Machine Learning algorithms all this time without even knowing it.
Read our opinion piece: Machine Learning Is Here To Stay
In this blog post, I go through some of the many apps on your mobile phone that use Machine Learning algorithms to make recommendations, get you to your destination quickly and safely, improve your photos, tell you what song you’re listening to and more. You’ll see, Machine Learning is not so far away. It’s already in the palm of your hand.
If you want to know what machine learning is, read our blog post on What is Machine Learning? And Other FAQs We Get...
Soundhound and Shazam
Music recognition apps like Shazam and Soundhound use machine learning to recognise the song you’re listening to. By analysing millions of songs and extracting features that are characteristic of each song and then storing it in a database, it is then able to compare the characteristics of the song you’re are listening to and compare it to the songs it has in its database until it finds a match. The more versions of the song it listens to (acoustic, instrumental, etc.) the better it becomes at identifying - to the point where it can even identify a song by someone simply humming it.
Spotify and Pandora
Music streaming sites like Pandora and Spotify use machine learning in a similar way that Amazon use it for cross-selling. By analysing the listening behaviour of millions of users and finding people with similar listening behaviour, machine learning is able to then able to make recommendations and compile personalised mixes based on the preferences, behaviour and compiled mixes of similar users.
Google Translate uses machine learning to translate over 100 languages into natural text with good syntax and grammar. How it learns to do this is by analysing millions of translated documents from the web to learn vocabulary and identify patterns in the language. When it comes time to translate, it takes what it has learned and picks the most probable translation.
What’s even more impressive is that through its recent introduction of Google Neural Machine Translation, the neural network system now powering Google Translate, it can learn to translate between two languages it has never translated by taking what it has learned already from translating between other languages and either of those two languages.
So, if it already knows that “Si” in Spanish means “Yes” in English and that “Yes” in English means “Oui” in French, then it will logically determine that “Si” in Spanish means “Oui” in French despite it never having translated between Spanish and French before.
Tinder, the online dating app, uses machine learning to help you get more swipes to the right (agree to a connection) versus swipes to the left (decline a connection) by the choosing your best profile photo to display. Through A/B testing - swapping photos displayed to other users to see which one elicits more swipes to the right - Tinder's algorithm not only learns which photo will get you more connections, but also in general which photo attributes tend to be perceived as negative, e.g. wearing hats or sunglasses and covering part of your face are a no-go, photos with friends or group photos and not smiling in a photo all tend to get fewer swipes right.
Also, the algorithm chooses which of your photos to display based on other users' specific behaviour. For example, if a user tends to swipe left on photos showing other users with cats or dogs, it will swap your photo with Fluffy or Fido - even if it's your preferred profile photo - with another one in your collection.
Siri, Cortana, and Google digital assistants
Apple, Google, and Microsoft’s digital assistants use machine learning for voice recognition and to respond intelligently to your requests. By listening to the requests being spoken into mobile phones by their millions of users worldwide and responding with what they think are the best answers or responses they learn through positive or negative reinforcement each time based on users’ actions, e.g. repeating or re-phrasing of request or not. So, the more you engage with your digital assistant the more it learns and gets to know you and becomes better at responding to your particular requests.
Pinterest, Instagram, Facebook and LinkedIn
All of these social networks use Machine Learning to increase the relevance of feeds by prioritising the most relevant posts on a user’s home feed. By tracking “likes” and “shares” from users, the machine learning algorithms continually learn what posts users like and then prioritises similar posts - listing them first on a user's feed - to increase user engagement.
Machine learning is also being used to detect spam users and spam or offensive content, predict ad performance and relevance, to determine which emails to send to users, and to predict and prevent churn.
Google Photos’ Suggested Sharing feature uses machine learning to suggest sharing certain photos with certain people based on who is in the photo, where the photo or video was taken, or who was with you at the time. Of course, this also means that machine learning is being used for facial recognition to detect the users in the photo whom it thinks you should share the photo with. Radical!
But that’s not all. Google Photos’ also automatically creates albums for you from a collection of photos taken during a specific period and uses machine learning to automatically populate it with only the “best” photos selected by its algorithm as being in focus and well-composed. And one more thing, Google Photos’ machine learning can also recognise over 255,000 landmarks in your photos – from the real Eiffel Tower in Paris to the mock Eiffel Tower in Vegas.
Snapchat - the mobile app that allows users to capture and share temporary videos and photos that disappear after a few seconds - uses machine learning algorithms to detect people’s faces and apply a fun filter on a face.
The algorithm has learned how human faces are constructed – with the eyes, nose, mouth and other features all usually being in the same place in relation to each other. It can then superimpose the filter onto your face pretty accurately.
Snapchat are also using machine learning for ad targeting, or Goal based Bidding, by predicting which users are most likely going to respond to an ad.
Uber and UberEats
Uber uses machine learning algorithms to predict the ETA (estimated time of arrival) of your ride. By analysing information from millions of trips, it is able to estimate the time it typically takes for a car to reach your destination from its point of departure at any given point in the day. Plus, by analysing data from millions of pick-up experiences, Uber’s machine learning algorithms will suggest walking to a “low friction” pick-up point like a nearby corner where there are no problems stopping to improve the pick-up experience for both rider and driver.
Uber is also using a similar algorithm for UberEats – its food delivery service - but taking it one step further to improve the accuracy of its predicted food delivery time. By analysing historic data of previous orders taken and adding on the typical food preparation time required once an order is taken, UberEats’ delivery time estimates are getting more accurate every day and allowing it to offer cool new features like displaying 30 minute delivery options and popular options near you based on past orders and details like time of day and delivery location.
Google says, that about 50 – 70% of the messages Gmail receives are spam. Thank goodness it’s been using machine learning for years to analyse spam and detect patterns that it can now use to identify and eliminate 99.9% of that spam before it reaches your inbox.
Google Maps and Waze
Google Maps and Waze (owned by Google) navigation apps are running on millions of mobile devices at any given time sending users’ location and driving speed to a central server to predict driving times as well as alternate routes. Waze encourages users to drive with the app open even if they are not using it to calculate average speeds, check for errors, improve layout and learn road and turn direction. Waze collects data for every route driven with the app open, learns these routes and is able to suggest optimal routes based on what it’s learned from observing all users driving similar routes.
Whether you realise it or not, you are already using or benefiting from Machine Learning algorithms every day in various real-world and digital world ways. But I hope the above mobile app use cases bring machine learning now closer to home for you – to the palm of your hand - and get you thinking of the many cool ways you could apply machine learning to improve the profitability of your business and experience for your customers.
If you’re interested in bringing in some of that machine learning magic to your business, please get in touch to hear what our team of data scientists could do for you or learn about our Machine Learning as a Service for businesses, Genius.