Making Sense of IoT Data with Machine Learning

A big promise of the Internet of Things (IoT) is that by analyzing millions of new sources of data from embedded, networked devices our experience of the world becomes better and more efficient. The environment automatically predicts our behavior and adjusts to it, anticipating problems and intercepting them before they occur.   The notion is seductive and almost magical: an automatic espresso machine that starts a fresh latte as you’re thinking it’s a good time for coffee; office lights that dim when it’s sunny and electricity is expensive; a taco truck that arrives just as the crowd in the park is getting peckish. Exciting in theory, this promise is rather unspecific in the details. Exactly how will our experience of the world, our ability to use all the collected data, become more efficient and more pleasurable? However, we don’t have good examples for designing user experiences of predictive analytics.   At RE.WORK Connect Summit, in San Francisco on 12-13 November, Mike Kuniavsky, Principal Scientist of Innovation Services at PARC, will present on the importance of predictive behavior to consumer IoT products and services, exploring UX challenges to creating such behavioral systems, and suggest patterns for addressing those challenges. We caught up with Mike ahead of the summit next month to hear more about his work at PARC. Tell us about your work at PARC and the Innovation Services Group you operate within. Broadly, the mission of PARC's Innovation Services Group is to reduce the risk of   adopting cutting edge technologies using a combination of ethnographic research,   user experience design, and innovation strategy. Essentially we're PARC's   consulting arm, which matches PARC's deep bench of novel technologies with our   customers' specific business needs, using user-centered methods.   Because of our deep hardware, networking and machine learning background, these   days we mostly design Internet of Things products and services for Fortune 100   commercial clients (of which Xerox is one, of course, though they're not our biggest   client). As the senior UX designer/consultant on the team, this means that my work   focuses on both broad service design ideas, such as creating consistent experiences   that span multiple devices and apps, and on specific design challenges that lie at the   heart of such offerings, such as how to design a wearable device (or a device for the   home, or car, or long-haul trucking cab, etc.) that uses a novel sensing technology (a   PARC specialty) that's never existed before.   How can we make sense of IoT data with machine learning? Humans are good pattern matchers at certain things, but we’re not built to collect   and make sense of huge amounts of data or to articulate our needs as complex   systems of mutually interdependent components. Computers are great at these   things. They can make statistical models from many data sources across space and   time and then maximize the probability of a desired outcome. The IoT produces   rivers of data that are constantly shifting, with new patterns that dynamically   emerge and old ones that dissipate. It's incredibly difficult for someone to make   sense of that flow, but that information often can be critical to the livelihood of   individuals. Broadly speaking, machine learning is the umbrella term for algorithms   that automatically (or with some human help) identify patterns in these data rivers   and determine which device behaviors tend to create the most desirable outcomes.   Models that learn and continuously adapt from the outcome of thousands of   situations across many people and long periods can compensate for a much wider   variety of situations, in a more nuanced way, than just about any individual will ever   be able to. This helps such systems be great tools and assistants--and, of course,   there are more nefarious applications to machine learning and artificial intelligence   (the larger discipline of which machine learning is a part), but as user-centered   developers, we're careful at PARC to minimize the known negative effects of the   systems we build and maximize their utility to consumers.   In your talk you will discuss UX of predictive analytics. What are   the challenges to this user experience design? Because predictive machine learning systems are statistical in nature and change   dynamically based on large sets of data, they're quite opaque, often even to the   developers of the algorithms making the models. When there are no obvious dials or   configuration levers with which to adjust their behavior, and the entire interaction   paradigm of working with a system that changes its behavior autonomously, that   learns and may act differently tomorrow than it did today, the user experience can   be very confusing and frustrating. We work a fair bit with machine learning systems, and the challenges run the gamut   of UX: on the service design level, do we treat a machine learning system as a core   actor, one that makes decisions on people's behalf, or an assistant that recommends   courses of action? The answer depends on many factors. On the interaction design   level, do we ask people to train a system, as they would a puppy, for the first month,   with the expectation that initially it'll act unpredictably most of the time, even   though the results will be much better after that month than if we used a generic   model that works out of the box?  How can we learn to embed consumer behaviour in design   foundations? Design is the practice of aligning the experience of a product with the business   needs of the organization creating it. It's about identifying how the extra effort   necessary to use a new device or service will be worth it to an intended audience   (because, after all, managing time is the ultimate zero-sum game, and if we're asking   people to use our product, we're simultaneously asking them to NOT do something   else, so we have it make it worthwhile). Devices that respond to our behavior can be   great assistants if they match the mental model of what we intend to do, or huge   annoyances if they require constant management. By embedding dynamic behavior,   and a form of intelligence, in our devices, we open up huge potential for creating   beneficial experiences, and potentially incredible frustration if things don't go well.   Right now we're at the earliest stages of understanding how to do that, so there are   few answers, but I believe we're starting to see the outline of at least the early   challenges.    What sector or industry has the potential to have the most   significant disruption by IoT? It's tough to say (if I knew for sure, I'd be investing all my money instead of working   at a research lab), but I believe that there are a handful of obvious places where   we're starting to see it: the integration of IT systems at hospitals is creating some   very IoT-heavy environments where the information affects people's health directly;   manufacturing and the operation of other heavy machinery (such as passenger cars)   is replacing people who do highly repetitive actions with robots that are much more   intelligent than simple movable arms (the Baxter robot, etc.); adding small amounts   of predictive intelligence is changing the way that everyday consumables, such as   diapers or bottled water, are being consumed. Xerox printers have been able to   predict when toner is going to run out for many years, and then automatically   reorder it so it arrives just in time. I suspect that's coming to everything from potato   chips to gasoline.Mike Kuniavsky will be speaking at RE.WORK Connect Summit, in San Francisco on 12-13 November. Early Bird tickets end Friday 9 October, book now to save!For further discussions on Internet of Things, Wearables, Connected Devices & more, join our group here.