Data Analytics and the Personalization of Mobile Services

Wednesday, May 14th, 2014 at 6:30 PM

TI Auditorium


6:30 - 7:00 PM Networking & Refreshments
7:00 - 8:00 PM Talks
8:00 - 8:30 PM Panel Session
8:30 - 8:45 PM Speaker Appreciation & Adjournment

Chair: MP Divakar
Organizer: Raja Banerjea & Rajeev Krishnamoorthy

Session Abstract:  Siri and Google Now have popularized the notion of virtual assistants on mobile devices. This event features two speakers, Sayandev Mukherjee of DOCOMO and John Feland of Argus Insights, who will discuss the (big and small) data analytics and technology behind these assistants and other intelligent mobile services.

Speaker: Sayandev Mukherjee

Bio: Sayandev Mukherjee is a Senior Research Engineer in the Data Mining team of the Network Services Innovations Group at DOCOMO Innovations Inc., in Palo Alto, CA. Dr. Mukherjee received his Ph.D. from Cornell University, Ithaca, NY in 1997. He has worked at Bell Laboratories, Marvell Semiconductor Inc. and SpiderCloud Wireless Inc., has over eighty publications in journals and conferences, and has been awarded thirteen patents. He is the author of "Analytical Modeling of Heterogeneous Cellular Networks --- Geometry, Coverage, and Capacity," published by Cambridge University Press.

Title: Intelligent Personal Assistants: a view from the intersection of data mining and mobile services

Abstract: With the introduction of Siri, the concept of an "intelligent personal assistant" residing on one's mobile phone has become widely understood. What is not widely known is that the first intelligent interactive personal assistant for Android came not from Google but from DOCOMO, in the form of the "Shabette Concier" service in Japan in 2012. With the introduction of "Google Now" later in 2012, the world was introduced to another kind of intelligent personal assistant, one that was predictive rather than just reactive. At DOCOMO Innovations in Palo Alto, we have worked on designing interactive and predictive intelligent personal assistant applications running on mobile devices. This talk will describe the challenges and design choices involved. For "Shabette Concier", this included machine learning for task identification, collection of training data for training the machine learning algorithm, and entity extraction from natural language text. For the predictive assistant, called "Tap de Concier," the challenges of security, personalization, and always-on availability led to a novel architecture design that is an example of "massive" (in terms of numbers of users) data mining on "small" data sets (each user's information).

Speaker: John Feland

Bio: John Feland is the founder and CEO of Argus Insights. Argus, a leader in Experience Analytics, was started in 2009 to answer the question, "How can traditional market research be improved and help drive innovation instead of validation?" Dr. Feland has taught Design and Innovation at Stanford University, led the team to create the first working Multi-Touch Smartphone prototype half a year before the iPhone was announced. Driven by his deep experience in the Consumer Electronics value chain and human center design, Feland has built an enterprise focused on helping clients uncover unfair methods of competing by delighting customers.

Title: Big Lies, Small Data, Virtual Phones providing Real Assistance

Abstract: Virtual assistants have leveraged Big Data since the beginning to determine the best way to help users, at times with unexpected results. Siri famously responded that the best smartphone was the Nokia Lumia 900 until Apple hardwired the response. When you invert the process and use consumer data to better understand virtual assistants, similar surprises take hold. Dr. John Feland will highlight what is found when you place virtual assistants under the Big Data Microscope using the largest dataset of mobile consumer experiences on the planet. Additionally Dr. Feland will peek around the corner and share some initial findings of leveraging these same mobile insights to improve the personalization of virtual assistants.