February 10, 2017Comments are off for this post.

Kontrol for Tesla App: New Ways to Optimize Your Driving Experience, in Style

We at Y Media Labs love Teslas.

We don’t just think Teslas are good for the environment, or that they’re the future of transportation. We also think Tesla cars are redefining drivers’ holistic user experience, comfort, safety and habits.

Tesla’s motto is “not to let the perfect be the enemy of the better.” That may be the case with the company’s new venture into the autonomous car market, but when it comes down to the user experience inside the car, we think we can aim for perfection . . . or at least simplicity.

Or maybe both!

Many developers struggle with finding the perfect balance between simplicity and functionality. In general, most struggle to achieve this noble goal and end up sacrificing one for the other, for good reason! Allowing users to complete a wide variety of tasks while keeping the overall experience simple and intuitive is no small feat.

With Kontrol for Tesla, we really wanted to achieve both – and we are confident that we did.

The Innovation Labs program at YML is responsible for identifying new and exciting ways to leverage existing technologies to make people’s lives better, easier and, yes, more fun! Every month we turn our attention toward inventing or improving a mobile user experience, and releasing the resulting apps for free. This month’s subject is Tesla.

Other Projects: Kontrol for Nest Thermostat | Kontrol for Tesla


Kontrol for Tesla: New app, endless opportunities


Our creative and development teams joined forces to build and launch Kontrol for Tesla, a new mobile application available today in the iOS App Store that Tesla owners all over the world can use to make their driving experience easier, better, more convenient and more efficient.

Kontrol for Tesla delivers all the features already available in the current Tesla app, plus a few more.

And because we’re such huge fans of Tesla, the app is completely FREE of charge for all those Tesla lovers out there to use!


A mobile experience to match the grace of the vehicle


We wanted to design an app that the Tesla community would love. Tesla is an amazing brand with cutting-edge products, so it wasn’t difficult to find a creative direction in line with what the company offers to their customers.

The design was inspired by simply sitting in a Model S and feeling that the app should represent the vehicle it is controlling: it should be sleek, intuitive, and follow clean lines.

We also wanted to give the app a new, modern and uplifting makeover, which is why the app interface looks like this:
When iterating on the UI, we selected a dark color palette. Color was stripped away from the surface to make important information like battery charge levels and temperature controls pop out. The app was designed to be highly functional, yet feel upscale at the same time, just like a Tesla. We wanted to create an app with an easy balance between functionality and modern aesthetics.


What’s new with Kontrol for Tesla: Simple interface, Touch ID car start, smart venting, 3D touch car unlock, honk and battery status


First and foremost, the Kontrol for Tesla app keeps all the current functionalities of the Tesla app it got its inspiration from. If you start using our app, you will not lose access to any of the current benefits of the original version.
Kontrol for Tesla allows you to do all these amazingly cool things that you are already familiar with from Tesla’s own signature app:

  • Check charging progress in real time
  • Change the temperature in your Tesla before driving
  • Locate your car and track its movement
  • Flash lights and/or honk to find your car in a parking lot
  • Vent or close the panoramic roof
  • Lock or unlock car

But why create just a clone of the app? Instead, we wanted to wow you with additional functionalities as well, which is why Kontrol for Tesla gives you access to these new and exciting features only available on our application:

  1. Start your car with Touch ID – you won’t need to type in your password every time.
  2. Smart Climate - remotely heat up your car to your desired temperature before you even leave the house.
  3. Unlock, Honk and Check Battery Status with 3D touch or through the widget. No need to ever log into the app.
  4. Smart vent the car when it gets too hot! We’ll detect the temperature differentials between the internal cabin and the external environment to adjust the sunroof for you (this feature will only be enabled for Tesla models that have a sunroof).


Kontrol for Tesla: Our process for handing best-in-class mobile app security protocols

We take privacy and security very seriously, and we understand that the data we are handling is very sensitive and NOT owned by Y Media Labs.

So here’s what we did to ensure that our beautiful application is completely in line with the best mobile app security practices, giving customers complete peace of mind while using our product:

User Credentials

Our app does not store the user’s credentials (username and password). Instead, this information is stored on Apple’s iOS Secure Keychain. Data stored in the iOS keychain cannot be accessed by other applications installed on the phone.

Additionally, we never use user credentials while communicating with Kontrol for Tesla’s server, unless we are communicating directly with Tesla’s API Server. Even when the app is running, we do not save / store the user credentials. Lastly, the app uses Touch ID authentication before accessing our users’ credentials from iOS’S Secure Keychain.

HTTPS and Apple Transport Security (ATS)

From iOS 9.0 onwards, Apple requires apps to use a technology called Apple Transport Security, which enforces all the client-server communication to be made securely through HTTPS protocols. Our app adheres to this practice.

SSL Pinning

Anytime our application communicates directly with Tesla’s API Server, the server will provide a certificate to the app. To evaluate the legitimacy of the communication we adhere to the following steps:

  • The app first evaluates the certificate provided by the Tesla server to check if the certificate is signed by a Certificate Authority (CA).
  • We check that the certificate provided by the server contains the Tesla API domain in the response.
  • Finally, if these two steps are validated, we match the certificate provided by the server and the certificate shared with our app.
  • If the user's device is jailbroken, we prevent the user from using the app while clearing their credentials, session token and local preferences.

The Road Ahead

More awesome features coming your way on Kontrol for Tesla

Source: Tesla

Did we mention we love Tesla???

We mean it.

We love it so much that we will not stop with the first iteration of our application. In fact, we are already thinking about another helpful feature that we want to build for this app:

  • Tracking personal versus business miles while driving your Tesla

We fully understand that many drivers use their car for both personal and business reasons. For now, there are no integrated features allowing Tesla drivers to easily track miles that are used for business purposes. Through this feature we will remove the hassle of noting down the personal and the business miles. Instead, the app will do it for you.


We are confident that Tesla is the future of driving in the US and abroad, and we are happy to contribute in any way we can to these exciting developments in personal transportation.

Download the Kontrol for Tesla app today to enjoy the free benefits of our apps. You’ve earned it by investing in the automotive innovation of the future.

December 14, 2016Comments are off for this post.

In-Store Analytics with Ad Tracker – Do People Really Like Your Ads and Marketing Displays?

It’s easy to get analytics from videos that are posted online.

However, until today, there was never an easy way to get analytics reporting from an in-store video.

Imagine if you could get actionable data on who watched your video while shopping in your store.

We’re talking about who watched the video, for how long, along with the gender and age of the people watching your video. All of these data points delivered to you, in real time, without collecting any information from the customer.


This is a question I know many decision makers in retail have asked themselves again and again: how can I measure my ad engagement in a way that is meaningful and actionable? Am I showing shoppers what they are looking for? Am I effectively communicating with my customers as they stroll around from one aisle to another, looking for products or inspiration?

What if there was a simple way to get an answer to these questions in real time?

This is why we built the In-Store AdTracker prototype.

To the average consumer, it’s a video that they watch as they shop at their favorite store. To the retailer, it’s powerful information that helps you make better decisions in a way that you couldn’t before.

Here’s how it works.

In-Store AdTracker – A Powerful, Simple Tool to Measure Ad Engagement


We built a simple proof of concept using Google Mobile Vision API. Basically, we created a tracker software that can be installed on any Android device featuring a built-in camera. Smart TVs, monitors, all-in-one computers, tablets, phablets – you name it.

Our proof of concept is simple. You install the In-Store AdTracker on any compatible device and then you play any video in a fullscreen mode on it. Then the AdTracker does what is supposed to do: it measures the level of engagement people have with the ad.

The tracker reports on the average time spent by a user with an ad; it tracks whether people smile while watching the ad, as well as the demographics of the people watching the ad – like age bracket or gender.

Here’s a video of how this works.

Let’s go through a specific example and see what type of information you could automatically have access to.

Let’s say you’re a store that sells celebrity merchandise. T-shirts, mugs, posters, original autographs, etc. In this business, as you know, stars rise and fall overnight. Hit songs dictate who is in the spotlight and what people are talking about at any given time. Of course, you can always look at Billboard 100 and figure out who is at the top, but the question remains: in your city, among your customers, who is the most popular star? What type of merchandise should you stock for?

Our AdTracker can give you this answer without you lifting a finger.

Let’s suppose that the top five songs on Billboard 100 this week are the following:

  1. Rihanna - Needed Me
  2. Ariana Grande - Into You
  3. Adele - Hello
  4. Taylor Swift - Blank Space
  5. Sia - Cheap Thrills

If you want to only stock merchandise for two of these five stars and get the biggest bang for the buck, how would you do it?

Let’s say you will play each of these videos in your store on the same screen on a loop and you want to see how engaged your in-store shoppers are.


1. The AdTracker can aggregate the number of people who watched each video

The type of report you could get in your inbox looks something like this:


If you looked at this graph based on the number of people who watched the videos in the last hour, you could conclude that Sia and Taylor Swift are probably the best stars you should get merchandise for.

But if you wanted to know a little more about the people who stopped and watched the videos, you can get that, too. Are they males or females?


2. The gender of the people watching an ad


In this example, you can see that more males than females stopped and watched the videos. So make sure you stock your inventory appropriately!

As we all know, the age of a consumer impacts what they buy, the price tag they’re able to afford, and how often they return to a retail store. Which brings us to the next question you may have...


3. The age brackets of users watching an ad


Not surprisingly for a celebrity merchandise store, in this example, we see that the most engaged users were within the 16-20 bracket. They also have the lowest budget across all age brackets. So you better stock up on lower-end-priced merchandise!

A big indication of user engagement is the time they spend interacting with a digital product, whether that’s a site, a video, or an ad. And this brings us to the next thing we can automatically determine with our AdTracker...


4. The average time a user spends watching an ad


How cool is this? Now you know that the largest number of people watch Cheap Thrills and Blank Space and that the same users spend the largest amount of time on these videos. That is a recipe for success: number of people + engagement level.

Lastly, you may be interested in learning at what time of day people are most engaged with your in-store videos. That allows you to prioritize what videos are broadcast when and whether you want to run any time-sensitive promotions.

The AdTracker can capture that information as well!


5. Hourly views breakdown


By now, you’ve seen what this simple AdTracker is capable of. In summary, it can track any of the following:

  • How many people are watching your ads
  • The gender of the people watching your ads
  • Age brackets
  • Level of engagement by time spent on ad
  • Hourly views breakdown

But if you’re not in the celebrity merchandise business, you may still be a little skeptical, wondering how this can benefit your business.

How can retail companies leverage the AdTracker?


Traditionally, the primary markets for video ads are TV and online sites where users must watch the ads before interacting with the content on the page.

But these are not the only places where video ads can be consumed. In fact, various companies small and big have found alternative channels and social contexts in which ads are being served, like:

  • Inside a store
  • Airport lounges
  • Waiting room for doctor’s appointments
  • While waiting in line at a store or food chain
  • Some bars have even installed monitors above urinals

No matter what situation customers may find themselves in, quite often there is “dead time” when distractions of any kind – including video ads – are more than welcome.

With the AdTracker, marketers can begin leveraging video ads and start collecting critical data about who watches these ads, for how long, and how the audience reacts to these video ads.

No more walking in the dark.

No more guessing.

No more uncertainty.

With the In-Store AdTracker, marketers can tell for sure if their efforts are working or not. You can easily determine how effective your strategies are and if your customers like what you are showing them.

And the coolest part? With our in-store AdTracker, all data is updated in real time and available to you on your phone, laptop or desktop.

November 22, 2016Comments are off for this post.

Uber vs Lyft – Who is loved more? A deep dive analysis using Google’s Sentiment Analysis API

Have you taken a rideshare in America in the last 3 years?

If so, chances are good that it was with either Lyft or Uber. The two companies — both launched in the San Francisco Bay area — are monopolizing the ridesharing industry across most U.S. markets, and are constantly competing with each other for customers’ attention, retention and loyalty.

What if I told you there’s a (fairly) simple way to see how Lyft and Uber’s customers feel about them? That we can track loyalty and user satisfaction with each of these brands, can do so with a high degree of confidence, and that we're not talking about spending hundreds of hours collecting and analyzing every single opinion that's out there on the internet?

We’re also not talking about physically stopping people on the street and asking for their feedback. We’re talking about using actual data that can be easily extracted and analyzed to see how customers rate pretty much any company out there.


Are you intrigued?

We certainly were when we decided to embark on this quest!

Instead of looking at anecdotal evidence about Uber and Lyft, we decided to use the power of Google’s recently released Sentiment Analysis API. We cannot overemphasize how powerful this API really is. Without it, this analysis would have taken us tens of hours (or more!), enormous amount of resources and would have cost a fortune!

Google’s Sentiment Analysis API allows us to extract and analyze people’s views on Lyft and Uber through a single API call. If there was ever a “the future is here” moment, this is it.

I don’t like to keep people waiting, so let’s dive right into the results. After the charts, we'll dive deeper into how it was done (read: technical)

I also need to state the obvious. Just because one company is more loved than another doesn’t mean that their business is inferior to the other, or that it's not doing as well.

Don’t shoot the messenger!

The results. Here's who's loved more.

We began our analysis of the Lyft vs Uber sentiment by looking at the latest reviews that customers left for the respective mobile applications on iTunes. Since both companies are primarily operating through their mobile apps, it sounded like the logical place to start. So what exactly did we do ? We extracted the 500 most recent reviews from iTunes and assigned a sentiment value for each review. Note that the cool part about the Google API is that it assigned a sentiment value based on the actual content of the review, not the number of stars a user gives to an app.

This is how the sentiment towards Uber looks based on these parameters:


What do we learn from this? First, the overall ratings for Uber have been on a downward projection. At its best, Uber’s customers are “OK” with the service, giving it an average of 2.7 out of 5 starts. Second, we can see that the overall trend is not going in the right direction and that — at least based on the small sample we collected — Uber’s users are becoming more and more frustrated with the service, rating it lower and lower.

Now, how do things look for the Lyft application, using the same parameters?


As we can see, Lyft users have a much better opinion about the app than Uber users. We also notice two other critical things. First, Lyft’s ratings over the last five hundred users have been getting better and better over time. Second, Lyft’s ratings are more stable and show a lot less variation in the overall sentiment ratings than Uber. As a side note, it’s interesting to note that Lyft’s lowest average score across the 500 most recent reviews correspond to Ubers highest score during the same time period.

After we saw what people thought about Lyft and Uber in the app store we thought, "Hey, why not looking at the sentiment people exhibit towards the two companies on Twitter?" We had two reasons for choosing Twitter as a platform from which to extract information via the Google Sentiment Analysis API.

First, Twitter allows a larger number of data points to be extracted than iTunes, which provides more accuracy to the overall analysis and statistical model.

Second, customers often use Twitter to communicate with businesses when they have issues with them. Twitter serves as a public “naming and shaming” platform, where customers often expect to get some sort of reaction from the business they’re interacting with. How companies respond to the public naming and shaming shapes how often other people will engage with the brands through social channels.

Here’s what Lyft and Uber’s customer sentiment looks like on Twitter, based on the Google API analysis of the last 8000 tweets published on the platform using the @uber and @lyft hashtags.



What we see from these charts is that both Lyft and Uber are struggling on Twitter. Both companies’ overall scores have been  decreasing steadily over time. There are various factors that could explain this trend:

  • Recent app releases have inadvertently impacted users’ perception of the app. This is often correlated with production bugs or a sluggish app performance.
  • Neither company allocates enough resources to support their Twitter feeds and get in touch with unsatisfied customers in order to solve whatever issues they’re reporting on Twitter.

If we take a bird's eye view of both Lyft and Uber across the last 1000 tweets and the last 500 reviews, a clear pattern starts to emerge. Let’s look at them:


The conclusion is pretty straightforward: Lyft gets significantly better reviews and sentiment ratings across platforms than Uber does.

Where it's true that Uber is more profitable and popular across most markets where it directly competes with Lyft, the latter’s ability to keep its customers more satisfied could pay off in the long term. It's certainly something the Lyft management tries to promote – the idea that when customers join Lyft, they’re not simply joining another ridesharing company — they’re joining a community. So far — from what we can tell — this strategy is translating into significantly better sentiment ratings for Lyft.

One of the other things we noticed about the Google Sentiment API is that businesses that operate internationally can watch trends happening across the world, and use country-specific breakdowns for sentiment analysis.

Let’s look at Uber’s and Lyft’s international presence and their respective ratings:


Uber operates in multiple countries, so extracting regional data for it was fairly simple (more details on the technical implementation below!)

As we can see, Uber’s average sentiment hovers around 2 out of 5 points on the sentiment scale, with India and Singapore constituting Uber’s biggest detractor and enabler markets.

For Lyft, we could only pull data from the U.S. and Singapore, where Lyft operates through a partnership with the local ridesharing agency.

Comparing how customers look at Uber and Lyft in the countries where Lyft operates shows that in both cases, Lyft has the upper hand in terms of users’ perceptions and reviews towards its ride-sharing services.

To sum up, even when you look at data points for specific countries where both companies operate, Lyft still has the overall upper hand in terms of users’ perceptions, attitudes and sentiments.

The technical analysis behind: How we arrived at the results

Now that we've looked at data points about people’s perceptions of Lyft and Uber, we're sure you're interested in figuring out exactly how we go to the datasets we showed.

Let’s dive right in and learn how to use Google Sentiment API.

The API currently supports three kinds of analysis of text.

  1. Entities
  2. Syntax
  3. Sentiment


Entities API documentation gives this description

Finds named entities (currently finds proper names) in the text, entity types, salience, mentions for each entity, and other properties.

To understand its capabilities, let’s try passing in a sample tweet to this API.

It clearly identifies many entities in the statement. It even links to Wikipedia articles.


Apple, Y Media Labs : ORGANIZATION


This can be applied to some really good use cases. Let’s say we want to create a trending topics list. We can pass text through entity API to generate topics of interest and create trending categories. We can group related content and present suggestions.


Advanced API that analyzes the document and provides a full set of text annotations, including semantic, syntactic, and sentiment information.

We have come a long way in contextual understanding of a sentence. This has been going on for over 50 years and we have finally managed to have arrived at a technological breakthrough where we can identify the contextual information at a much higher degree. To give you an example of how advanced this is, let’s add a grammatically correct sentence and see how the API breaks it down.

Time flies like an arrow; fruit flies like a banana

Flies was correctly identified based on context. Verb in first context and Noun in the second. ?

This API can be used to identify verbs, nouns and run specific analyses on words. If we're looking at generating stats on how those affect an article, then this is useful. From use case perspective, it's not quite as strong for analyzing our sentence and see if it's correctly inferring the context.

Sentiment Analysis

Advanced API that analyzes the document and provides a full set of text annotations, including semantic, syntactic, and sentiment information.

Sentiment analysis is quite powerful. API can deduce sentiments from arbitrary text. The API itself is straight-forward. Let’s take this ambiguous review for Uber.

It’s clear that the person loves Uber, but rated it 1 star. That’s painful for Uber. Let’s try and fit this through Google sentiment analysis.

Sure enough, it gives a great rating. Here's the rating chart.[2]

Apple iTunes provide RSS of customer reviews for apps in json format.

For example, Lyft iOS app, whose app id is 529379082, the RSS of customer reviews json can be found at : https://itunes.apple.com/rss/customerreviews/id=529379082/json

Similarly, we got the RSS of customer reviews for the Uber app, whose app id is 368677368 through: https://itunes.apple.com/rss/customerreviews/id=368677368/json


We wrote small Go code to parse the json body. For each of the reviews we called the Google sentiment analysis API to get the polarity and magnitude.

In our analysis, we were able to compare Lyft vs Uber by looking at the breakdown of reviews for specific countries where both companies operate. To fetch the RSS of customer reviews for Uber in different countries, replace the country code as specified in ISO_CODE_FOR_COUNTRY at “sg” in below url:


For example, to get United States based reviews, the country code is “US” and the url will be :


So how is Google sentiment analysis different from just App Store ratings? Google sentiment analysis overcomes the user’s bias in giving star ratings and only considers the true description. We can also combine this with Twitter feeds sentiment analysis, along with other forums and internet feeds, to get overall sentiment from everyone. Then, instead of rating for just an app, we can obtain a rating for a Brand!

Twitter Stream ---> Google NL API ---> Google BigQuery ---> Google Data Studio [3]

If we set up architecture as shown above, we can easily generate sentiment analysis on brands, which is much more valuable.

Links to get you started with the Google API:


In this article we took a deep dive into the Google Sentiment Analysis API by leveraging its capabilities to compare two popular American ridesharing companies.

As we saw, this amazing API can provide lots of interesting and useful information for company executives. Knowing your brand engagement across markets and geographical regions, as well as your users’ and customers’ overall perception towards the brand, is critical to the overall success of any digital business.

The overall opportunities for Language Processing and Machine Learning platforms are endless. Across the board, companies receive a tremendous amount of feedback through various channels. Google Sentiment’s API is paving the way for developers and business executives to become aware of the overall sentiments their current or prospective users have towards their brand, products and services.

September 23, 2016Comments are off for this post.

Introducing DISKOURSE: The New Social Platform Connecting Trump and Clinton Supporters

REDWOOD CITY, Calif., Sept. 23, 2016 /PRNewswire/ -- Y Media Labs today announces the launch of Diskourse, a new social media platform that instantly connects Hillary Clinton and Donald Trump supporters for civilized, one-on-one discussions on the issues that matter most in the volatile 2016 U.S. presidential election.

Now that the live presidential debates are here, technology can help the supporters of the two major party candidates to finally listen, and hopefully learn, from one another.

The Diskourse app can also alleviate what has become an all too common occurrence on Facebook: a post goes up about a hot-button issue like immigration or gun control and suddenly friends, co-workers and complete strangers are involved in nasty back-and-forth debates. Names are called. Insults are traded. No one wins. No one learns.

Diskourse wants to change that.

Don't stay trapped in your social media echo chamber; with Diskourse you'll meet people who want to hear the other side of the story.

You can engage with others, ask questions, and write thoughtful responses. The idea is to find consensus -- or politely agree to disagree.

Millennials represent one-third of the electorate. For them, personal opinions are more valued than news reports; 86% of Millennials report seeing diverse opinions on their social media feeds, according to the Media Insight Project.

"With all the toxic political rhetoric in this presidential campaign, Y Media Labs has leveled the playing field by creating an innovative platform where Donald Trump and Hillary Clinton supporters can safely connect. The Diskourse app encourages honest, one-on-one debate for all: Millennials, GenXers, Baby Boomers and the Greatest generations. After all, we could all use a little civility," said Robbie Abed, Director of Product Strategy, Y Media Labs.

Diskourse app is available on iOS for FREE on the App Store. Log-in via Facebook or email; only your first name appears, no other personal information is revealed or shared.

Simple. Safe. Civil. It's Diskourse.


Make a Lasting Impact.

All rights reserved.
Y Media Labs