Most of the time, we at Datarella deal with the very near future: what will be the most likely thing that individuals want or what they are up to next? We use mathematical models to predict human behavior. But not only human behavior is what Datarella is interested in. Research papers, internal customer data and external data are being used by Datarella to predict probabilities of success of specific products. We detecs patterns, weaknesses and events in behavior and product design and – together with our customers – we define workarounds, optimizations or completely new data-driven products.
We can draw a colorful picture of people’s everyday lives from the data we collect via smartphones. To tell the data-story, we need to translate the raw measurements into meaningful events, like “driving a car”, “strolling in a mall”, or even more intimate, like “being nervous”. We will show how to access the phone’s data, how to derive complex events from the phone’s raw data, and how to bring it into a meaningful story, and how to make it work for businesses.
Cases we’ll show: an app for the automotive industry to support ecological driving, learning about preferences of Chinese passengers at an international airport, and supporting people suffering from osteoporosis to stabelize their condition and maintain mobility.
More on Strata+Hadoop
Today, we would like to announce something special. Something we can’t wait to take place and until mid June it’s going to be tough to sit tight. Please, feel invited to our Wearable Data Hack Munich 2015!
The Wearable Data Hack Munich 2015 is the first hack day on wearable tech applications and data. It will take place right after the launch of Apple Watch – the gadget we expect to rise the tide for all wearables. Withe the Wearable Data Hack Munich 2105, we aim to kick-off app development for the emerging smartwatch and wearable tech market. During this weekend you will have the first occasion to share your views and ideas and jointly gather experience with the new data realm.
Apple calls the Apple Watch “Our most personal device ever”. And with good cause: The data from wearable tech, smartphones and smartwatches are really the most personal data ever. Our mobile devices accompany every step we take, every move we make. A plentitude of sensors on the devices draw a multidimensional picture of our daily lives. Applications of wearable data range from fitness to retail, from automotive to health. There is hardly an industry that cannot make direct use of it. And yet, wearable apps still are in their childhood. The Apple Watch will be hitting the street in April and will get the ball rolling.
THREADS TO BE PURSUED
Developers, data geeks and artists will pursue one or more of these threads:
– Data-driven business models for wearables
– Data-driven wearables
– Smartphone app (Stand alone / combined with smartphone)
– User Experience
– Open Data
– mHealth / Medical Data
So let’s explore what we can do with this data! Let’s play with the possibilities of our wearable gadgets and mobile sensors.
To apply for the Wearable Data Hack Munich 2015, please send us an email with
– your name
– your profession
– your take on wearable data
– 3 tags describing yourself best.
Don’t wait for too long – the number of participants is limited.
For more information, please have a look here! See you at Wearable Data Hack Munich 2015!
Every smartphone user produces more than 20 MB of data collected by her phone’s sensors per day. Now, imagine the sensor data of 2 billion smartphone users worldwide, translated into realtime human behavior, shown on a global map. That is the vision of the Datarella World Map of Behavior.
A typical 2015 generation smartphone sports up to 25 sensors, measuring activities as diverse as movements, noise, light, or magnetic flux. Most smartphone users aren’t even aware of the fact that their phone’s camera or microphone never are really „off“ but that they constantly collect data about the noise level or the intensity of light the user is experiencing.
Actions speak louder than words
Actions speak louder than words – if we want to really know a person we have to know how she behaves, and not only what she says. And that’s not only true for politicians. We all form our opinions on others by looking at their actions, more than their words. Many inter-personal problems result from NOT looking at people’s actions, but focusing on other aspects, such as their looks or their words. Behind superficial distinctions such as physical appearances, over time we often realize similarities with other people based on their and our actions.
Our vision of a World Map of Behavior
At Datarella, our vision is to show the actions of people around the world on a global map. By displaying the actions of people of all continents, we want to tell stories about the differences and similarities of global human behavior – to draw a picture of human co-existence. There already are snapshots of global behavior, provided by data focused companies, such as Jawbone, who map sleep patterns worldwide. From that we know that Russians get up latest, and Japanese get the least sleep in total . And there are different behavior-related maps, showing the world’s most dangerous places, defined by the number and seriousness of crimes or actions of war.
Co-operation & Participation
To create the World Map of Behavior is our ambitious project for 2015 that we won’t complete alone. We need your support: if you are an expert in the field of mobile sensor data or if your company already focuses on collecting and interpreting mobile sensor data in the fields of mobility, finance, health or transport and travel. If you are interested to play a role in this project, please send us an email with a brief description of how you would like to contribute. We are looking forward to hearing from you!
Datarella now provides an API for our app ‚explore‘, that allows every user to access the data collected and stored by the app.
An Application Programming Interface, in short API, is an interface for accessing software or databases externally. Web-APIs giving us access via the internet, have become the principle condition for most businesses in the web. Whenever we pay something online with our credit card, the shop system accesses our account via the API of the card issuing company. Ebay, Amazon, PayPal -they all provide us with their APIs to automatize their whole functionality to be included in our own website’s services. Most social networks offer APIs, too. Through these we can post automatic messages, analyze data about usage and reach, or control ad campaigns.
The ‚explore‘ app was developed by Datarella to access the smartphones internal sensors (or probes), and to store the data. It is however not just about standard data like location, widely known because of Google Maps. ‚explore‘ reads all movements in three dimensions via the gyroscope, accelleration, magnetic fields in the environment. Mobile network providers and Wifis in reception are also tracked. From these data we can learn many interesting things about ourself, our surroundings and environment, and about our behavior. To set the data in context, the API also gives out data from other users. For the sake of privacy and information self-determination, this is aggregated and averaged over several users, so that identification of a specific person is not possible.
With our API, Datarella commits to open data: We are convinced, that data has to be available for users.
➜ Here is our API’s documentation: explore.datarella.com/data_1.0.html
➜ Here the download-link for ‚explore‘: play.google.com
We are excited to learn, what you will make from the data.
Around 2010, Lisa Gansky coined the term Sharing Economy, or Mesh companies, offering their customers efficient shared access to their products instead of selling their products to them. Recently, it’s being called Collaborative Consumption or Collaborative Economy. It’s all about finding ways to make better use of valuable resources that have remained unused. Convenient access is being made affordable to people who can’t afford different products, or simply don’t need to own those products since they would only use them infrequently.
Typical mesh businesses like AirBnB, LendingClub or Cookening, demonstrate the power of sharing in very different ways: AirBnB is on the way to pass Hilton as the world’s largest hotelier in 2015, that is 7 years after its inception. The US peer-to-peer lending company Lending Club has originated over 4 billion USD in loans – it was originally founded as a Facebook app in 2006. The typical Mesh business runs a stylish app with a high usability. It’s service is new, easy to use and affordable. But all that does not fully explain the tremendous speed they conquer one market after the other. Who is the driver behind the Sharing Economy and it’s success?
It’s the user.
It’s the user. The user offers and asks for private overnight stays on AirBnB, the user provides and lends money on LendingClub. Even with services like Zipcar, when the product is provided by a company, the user „uses“ a product instead of buying and owning it. He has to rely on other users‘ good maintenance of Zipcars, since if there were too many ‚abusers‘ the company had to raise rates and the product would become unaffordable for most people. The same is true for AirBnB and others: users have to be sure that landlords don’t sell cubbyholes to them, whereas – vice versa – landlords have to trust their guests not to steal the TV or destroy the flat. So, the user has to use the service and she has to behave in an orderly manner – this is the foundation for a properly working and successful Sharing Economy.
Image: The Sharing Economy, Latitude
Now let’s adopt the principles of the Sharing Economy to the individual who shares her statuses with her social graph on Facebook, discusses the latest news on Twitter and shares her preferred fashion designs on Pinterest. She dos it because she wants to express herself and she wants to communicate with a wider circle of friends than she can meet in person. She communicates in both, synchronous and asynchronous ways. She has learnt that the more she adds to discussions, the more she gets in return. In Social Media, she experiences the Pay-it-Forward principle in action at its best.
Sharing Economy has attained full age in 2014
Let’s assume we can all agree on that: communication openly and actively, sharing ideas, opinions, homes, cars, money and much more with others is not an extravagant imagination of Utopia, Inc., but a multi-billion dollar business eclipsing traditional business models around the world. Furthermore, it’s not just a gigantic business but a sympathetic and friendly way of matching supply and demand of individuals. Who wouldn’t prefer an individually furnished private home over a standard hotel room?
If we agree on the power of sharing the above mentioned martial and immaterial goods, can we also agree on the power of sharing data? Our data? Our own body’s data? Can we agree on the tremendously positive and socially relevant effects of sharing the data we produce ourselves, day by day? If you own a smartphone (you most probably will), you produce about 20 MB of smartphone data (i.e. data racked with your smartphone’s sensors) each day. Perhaps you haven’t been aware of that fact, or you just didn’t know how relevant this data could be for yourself, and for your social graph, respectively. Do you know how much you move each day? The U.S. Surgeon General wants you to move at least 10,000 steps a day to prevent and decrease overweight and obesity. (It’s very easy to know your steps: just get yourself one of those fitness trackers.)
And, did you know that your Vitamin D level is one of the key drivers of your well-being? Most North Americans, North and Central Europeans suffer from a Vitamin D deficiency. Do you actually know your Vitamin D level? Do you know that you can find it out yourself?
Let’s get more complex regarding data: microbes in the human body are responsible for how we digest food and synthesize vitamins, our overall health and metabolic disorders. The aggregate of microbes is called microbiome. Do you have any idea about your individual microbiome? Do you know that you can find out about your microbiome yourself, by using a simple kit?
Sharing Data still in its infancy, but…
So far, we have talked about the relevance and value of our data for ourselves. But – weren’t you interested in preventing your first stroke because thousands of other men at your age have provided their heart and respiratory rates anonymously and based on the analysis of this data you had been warned early enough to take appropriate action?
Wouldn’t you agree that the Pay-it-Forward principle works perfectly in the field of personal body data? The difference to the AirBnB model is that you provide your body data anonymously. It will be aggregated and used in a way that nobody knows that’s you behind your data. Since data analysis and respective actions or recommendations rely on big data, it’s necessary that many people participate and share their own data.
… will become a Social Responsibility in 2017
Today, in late summer of 2014, many people are sceptical and hesitate to provide their data. We think that personal body data sharing will be regarded as quite normal within a few years. If this movement takes up the same speed as the Sharing (Goods) Economy, it will be accepted as „normal“ within 2-3 years. We believe, that data sharing will become a social responsibility, comparable to fasten one’s seat belt or wearing a bike helmet. It probably won’t be called data sharing since this is a B2B term. There already is a very good term – the Quantified Self, or QS. The term itself does not include the sharing element. But for every active members of the QS movement sharing is a relevant part of the quantification process because the value of an individual’s data is even bigger if used for general purposes.
We regard data sharing – our Quantified Self – as one of the most important movements of modern times and we would love to know how you think about it: please comment, provide us with your feedback: do you already share your data? How do you do it? Or, are you still sceptical?
Working with lots of data, the biggest challenge is not to store or handle this data – these jobs are far from being trivial, but there are solutions for nearly any kind of problem in this space. The real work with data starts when you ask yourself: what’s behind the data? How could you interpret this data? What story can you tell with this data? That’s what we do and we want to share some of our findings with you and motivate you to join our discussion about the meaning of the data . We want to create Data Fiction.
Today, we start with some sensor data collected by our explore app – the smartphone’s battery status including the loading process. Below you see sample data for our user’s behavior during the week (Feature Visual) and at the weekend (Figure 1).
In Figure 1 you see that most users load their smartphones around 7 a.m. and (again) around 5 p.m. What does that tell us? First, we know when most users wake up in the morning – around 7 a.m.. Most probably they have used their smartphones‘ alarm functions and then connect their devices to the power supply. Late afternoon, they load their devices a second time – probably at their office desks – before they leave their workplaces. During weekends, the loading behavior is different: people get up later, and maybe use their devices for reading, social networking or gaming, before they reconnect them to their power supplies.
Late rising leads to an avarega minimum battery status of 60% during weekends, whereas during the week, users let their smartphones batteries go down to 50%. This 10% difference is interesting, but the real surprise is the absolute minimum battery status of 50% or 60%, respectively. It seems that the days of „zero battery“ and hazardous action to get your device „refilled“ are completely over.
For some, data is art. And often, it’s possible to create data visualizations resembling modern art. What do you think of this piece?
This matrix shows the daily smartphone loading behavior of explore users per time of day. Each color value represents a battery status (red = empty, green = full). So, you either can print it and use it as data art on your office’s wall or you think about the different loading types: some people seem to „live on the edge“, others do everything (i.e. load) to staying on the safe side of smartphone battery status.
What are your thoughts on this? When and how often do you load your mobile device? Would you describe your loading behavior as „loading on the edge“ or „safe? We would love to read your thoughts! Come on – let’s create Data Fiction!
DATA FICTION – THE STORIES BEHIND THE DATA
People, animals, plants and things produce data – a lot of data. The data itself is the basic resource – like words are the basis for language. If you put words together to sentences and you combine sentences to chapters and aggregate several chapters – you write a story, you create fiction. Same with data: if you combine different data sources to data pools and aggregate them – you write the story behind the data, you create data fiction.
[Strong narrative] augments the available data by way of context, and extends the patience of the audience by sustaining their interest as well.
Does that sound like you?
We’d love to see and discuss your applications, analyses, case studies and models with you and help you make your data fiction become reality.
DATA, APP & COMPLEX EVENT PROCESSING ENGINE
We will provide you with sample data resulting from the usage of our explore app.
The data has been created by users of the explore app. In explore, the user interacts by answering surveys, attending tasks and heeding valuable recommendations based on her behavior. She immediately sees the results of her interactions in the feedback area. Second, explore tracks several sensors of the user’s phone, which can be set on and off by the user herself (see full list of sensors below). explore connects both areas, interactions and the sensor tracking area, with the integrated Complex Event Processing Engine CEPE.
The Complex Event Processing Engine (CEPE)
The CEPE is a mechanism to target an efficient processing of continuous event streams in sensor networks. It enables rapid development of applications that process large volumes of incoming messages or events, regardless of whether incoming messages are historical or real-time in nature.
Our CEPE is based on ESPER and Event Processing Language EPL
List of Sensors
– GPS location data
– Network location data
– Magnetic field
– Battery status
– Mobile Network
– Overview and extended description or representation of your main idea, any subtopics and a conclusion
– Use or integration of at least 1 (one) category of sensor data (e.g. Gyroscope). If you use GPS location, you should use or integrate at least 1 (one) additional category of sensor data beside GPS location data.
DATA FICTION TYPES
We will reward fascinating data fiction with preferred access to our data, a post on the QS Blog and the possibility of making data fiction come true.
Yes, I am a data fictionista and want to submit my data fiction!