Track 1 Sessions are for All Levels
Track 2 Sessions are Expert/Practitioners Level
Pre-Conference Workshop
Sunday, March 4, 2012
Full-day Workshop
R for Predictive Modeling: A Hands-On Introduction
Click here for the detailed workshop description
[ Top of this page ] [ Agenda overview ]
Tuesday, March 6, 2012
Wednesday, March 7, 2012
Exhibit Hall Open
Registration & Breakfast
8:30-9:15am
Keynote
Text Analytics and Mining Big Data: From Sentiment Analysis to Understanding Consumer Intent
This talk will cover:
- Describe what we mean by Big Data and the new generation of Data Science and Data Scientists
- While large variety and volume of data have been around for a while, it was in particular text data sets, and most recently social commentary and social media that drove the move to Big Data in a serious way
- Sentiment analysis as a big driver from a marketing perspective has combined with the wide availability of dynamically changing text data sets (news, social media, other dynamic sources) have accelerated the development of technologies to keep up with the fast velocity and wide variety of these data sets
- Predictive analytics to infer the most important aspects of these data sets: usually consumer or user intent” are the holy grail for projects centered around these.
- We will use examples and case studies of Text Analytics and Search technology related projects to demonstrate the concepts and the future opportunities od these techniques, including leveraging the wisdom of the crowds phenomenon and increasing relevance of applications and predictions.
- Striding the divide between science and business, Dr. Fayyad will use examples from his work with some of the most data-rich companies, to map the next frontier of data science, highlighting its impact on various industries. This will lead to discussing new opportunities for new business models that are much more data-driven and data-dependent than we have ever seen before. The talk will include coverage of predictive and text analytics over Big Data.
Speaker: Usama Fayyad, Chairman & CTO of ChoozOn, Former Chief Data Officer, Yahoo!
[ Top of this page ] [ Agenda overview ]
Premier Sponsor Presentation
The Value of Text Analytics
With the explosion of unstructured data both inside and outside the corporate environment, whether its Human Capital Management, Insider Threat, Sentiment Analysis, or Social Media Analytics, the deployment of text analytic solutions have moved beyond the early adopters. Do you know the value of text analytics and how it can impact your business. If you’re not analyzing the data about your business you can be sure your competitors are.
Speaker: Steven Reeves, Text Analytics Overlay within the IBM-SPSS North American IOT Group
[ Top of this page ] [ Agenda overview ]
Premier Sponsor Presentation
Technology Strategies for Big Data Analytics
The exploding volume, complexity and velocity of big data present an increasing challenge to organizations, but also a significant opportunity to derive valuable insights. As organizations are tasked with managing massive data sets, it’s clear that the value of big data will be derived from the analytics that can be performed on it. Analytics is the key to identifying patterns, managing risks and tackling previously unsolvable problems.
This presentation provides an overview of how to comprehensively address big data, including emerging strategies for information management, analytics and high-performance computing.
Speaker: Kathy Lange, Senior Business Director, SAS Business Analytics Practice
[ Top of this page ] [ Agenda overview ]
9:35-10:00am
Breaks / Exhibits
[ Top of this page ] [ Agenda overview ]
Track 1: Software Tools for Text Analytics
Case Study: Amdocs & the US Government Accountability Office
Text Analytics Software: Selecting the Right Fit
Text analytics software comes in a variety of options and selecting the right one for your organization has gotten more complex over the last couple of years. This session, using a number of recent examples, presents a methodology for making sense of the complexity and picking the right type of software for your current and future needs. The first phase is a traditional software feature evaluation followed by a full Proof of Concept as the critical second phase. We will cover how to set up and run a text analytics POC and how to get meaningful results.
Speaker: Tom Reamy, Chief Knowledge Architect, KAPS Company
[ Top of this page ] [ Agenda overview ]
Track 2: Customer Support
Case Study: A Fortune 500 Global Technology Company
Rules Rule: Inductive Business-Rule Discovery in Text Mining
Text mining remains at the leading edge (rather than the mainstream) of analytics for the corporate world, largely because of the complexities associated with how language is used. Words and phrases in a corporate lexicon can be used ambiguously, inconsistently, and incorrectly, making it difficult but not impossible for a human to understand. However, for predictive analytics, these ambiguities must be overcome so that algorithms can be applied consistently to historic data.
Call center data is no exception to these problems. A Fortune 500 global technology company applied text mining to their help desk calls related to the repair of supported devices. Complexities included the usual text ambiguities and spelling errors, but also included variable English terms and abbreviations as used in foreign countries. By incorporating a combination of manual text extraction by domain experts with automated machine learning using decision trees, an operational system of business rules was developed that exceeds specifications for profitable identification of parts needed for repairs.
Speaker: Dean Abbott, President, Abbott Analytics
[ Top of this page ] [ Agenda overview ]
Track 1: Product Launching
Case Study: Product Launch Analysis
Product Launch Analysis
In the days after product launch, marketing organizations usually focus on the immediate success of their campaigns. Analysis of social media verbatim creates new opportunities to supplement this work by showing how consumers are reacting to the product. All the pre-launch research in the world never captures actual post-launch reaction. Using NLP analysis and classification, Semphonic analyzed the launch of a new category of notebook for Samsung. We\\’ll show the techniques we used to replicate Conjoint-type analysis, the challenges separating out social campaign chatter from true customer reactions, and the benefits of creating a text-analytics system for ongoing customer research.
Speaker: Gary Angel, President & CTO, Semphonic
[ Top of this page ] [ Agenda overview ]
Track 2: Insurance
Case Study: Accident Fund
Using Text Analytics to Accurately Segment Workers’ Compensation Injuries
Workers’ compensation insurers can utilize predictive models to identify high-cost injuries early-on for triage and cost prevention. At Accident Fund, we were interested in the insured’s secondary conditions (i.e., co-morbidities) such as obesity and diabetes as model variables because these factors can significantly influence overall outcome. Co-morbidities are traditionally captured in adjuster notes; thus we applied text analytics to generate co-morbidity indicators. In this case study we will present lessons learned from handling challenges presented by freeform adjuster notes that include:
- Developing synonyms
- Handling negation logic
- Handling large data quantities, and;
- Validating the performance of the algorithm.
Speaker: Amir Biagi, Associate Predictive Modeler, Accident Fund Insurance Company of America
[ Top of this page ] [ Agenda overview ]
10:45-11:05am
Breaks / Exhibits
[ Top of this page ] [ Agenda overview ]
11:05-11:50am
Expert Panel
Text Analytics Hits the Mainstream
Text analytics has taken off, across industry sectors and across application areas that include decision support, sentiment analysis, fraud detection, survey analysis and beyond. Where exactly are we in the process of crossing the chasm toward pervasive deployment, and how can we ensure progress keeps up the pace and stays on target?
This panel of leading experts will address:
- How much of text analytics’ potential has been fully realized?
- Where are the outstanding opportunities with greatest potential?
- What are the greatest challenges faced by the industry in achieving widescale adoption?
- How are these challenges best overcome?
Expert Panelists: Usama Fayyad, Chairman & CTO of ChoozOn, Former Chief Data Officer, Yahoo!; Richard Foley, Worldwide Product Marketing Manager & Strategist, SAS Text Analyst; & Steven Reeves, Predictive Analytics Solutions Architect of Text Analytics Overlay within the IBM-SPSS North American IOT Group
[ Top of this page ] [ Agenda overview ]
Birds of a Feather Lunch / Exhibits
Financial Indicators from Social Media
Keynote
Modeling Collective Mood States Using Social Media Analytics
Social media have become a crucial part of our social lives. The user communities of Facebook and Twitter combined now exceed the populations of most industrialized nations. The content generated by these millions of users offers a real-time record of our collective actions, thoughts and emotions. Advances in network analysis and text mining applied to the resulting large-scale social media data have enabled topic detection and the measurement of emotional and mood states at a societal scale. This evolution has underpinned fundamental changes in how social science research is conducted, and has found wide-spread applications in marketing, politics and even finance.
In this presentation, I will give an overview of how complex network models are applied to the analysis of online social networks, and how it has given rise to the emerging domain of computational social science. The presentation will discuss social network models, and how they have been used to study contagion and information propagation, leading to models of marketing trends, meme propagation, and other socio-cultural phenomena. In our own research we have focused on the extraction of indicators of collective mood states from large-scale social media feeds, and their applications to behavioral finance. I will provide on overview of sentiment tracking methods, their application to social media feeds, and how they can be leveraged to measure collective mood states which according to recent results may have predictive value with respect to societal and financial market trends.
Speaker: Johan Bollen, Associate Professor, School of Informatics and Computing, Center for Complex Networks and System Research, Indiana University
[ Top of this page ] [ Agenda overview ]
1:45-2:15pm
Breaks / Exhibits
[ Top of this page ] [ Agenda overview ]
Track 1: Social Data
Case Study: Real-world examples in Financial Services, Emergency Response
Exploring Social Data: Use Cases for Real-World Application
With billions of social activities passing through the ever-growing real-time social web each day, companies are beginning to harness the power of social data. However, in today’s social data economy, not all social data is created equal. While all social media data can be valuable, it is a matter of discovering which type of social data is best suited for each specific use case. Through this session, participants will learn from real-world case studies in Financial Services, Emergency Response, Brand Analytics and other industries about how businesses are applying social data to their operations to drive value.
Speakers: Chris Moody, President & COO, Gnip
[ Top of this page ] [ Agenda overview ]
Track 2: Social Data
Case Study: AVG Security
Predicting Real-World Events and Sentiment via Social Media Analysis
Throughout the Mid East uprisings social networks such as Twitter have played a central role to communicate, organize and amplify uprising activities. This session will demonstrate how real-time search and analytic technology applied to social media can predict events and trends using real-word examples from the Mid East and elsewhere.
Speaker: Rishab Ghosh, Co-Founder & Vice President of Research, Topsy Labs
[ Top of this page ] [ Agenda overview ]
Track 1: Social Data
Case Study: Hewlett-Packard
Developing Predictive Analytic Solutions Using Social Personas Derived from Social Media
Over the years, predictive analysis has relied on syndicated data to augment a company’s internal data. Predominantly, these solutions have been wrapped around historical customer behavior data. But over the years, there has been tremendous growth in social media content, i.e. reviews, blogs, tweets etc. These social media sources contain numerous leading indicators that can be used towards anticipating behavior. This presentation focuses on techniques used towards developing social personas from these indicators and then in turn using these social personas towards enabling predictive analytic solutions.
Speaker: Kumar Subramanyam, Senior Solutions Architect, Hewlett-Packard
[ Top of this page ] [ Agenda overview ]
Track 2: Sales; High Technology
Case Study: Brocade
Discover & Monetize Customer Intelligence Gold Mines to Improve Sales
Pipeline & Revenue
This session will examine an analytic framework and a suite of modeling techniques that Brocade’s Customer Intelligence function applied to marketing and sales targeting efforts with the results of improved pipeline and revenue. Mining of unstructured data like social media and lead notes, often overlooked by organizations, proves to be an incredible gold mine when combined with modeling of standardized, structured transactional, demographic, and behavioral data. Several examples and case studies will be presented in this session.
Speaker: Susan Chiu, Director of Customer Intelligence, Brocade
[ Top of this page ] [ Agenda overview ]
Track 1: Government
Case Study: Indian Customs Board
Text Mining in Advanced Government Compliance Set-ups
Commodities imported into a country are typically classified through an Internationally Harmonized Coding system up to 8 digits. It is often inadequate as the bundle of commodities at the lowest level are also quite varied in material, value, significance and therefore their pricing leading to inadequacy of reference bands. Text Mining has not only provided an in road into sub classifying the commodities on the basis of their descriptions but have also helped identify risk parameters that link well to asses see evasions and mis-declarations. It is possible to evolve strings of risky key words and prevent the facilitation of suspicious consignments.
Speaker: Kamaljit Anand, Global Head of Client Delivery, KIE Square Consulting
[ Top of this page ] [ Agenda overview ]
Track 2: Sentiment Analysis
Case Study: MTV Networks
Predictive Social Marketing – Sentiment Forecasting and Impact on Success
Every summer, music fans worldwide look forward to one of the biggest music events of the year—the MTV Video Music Awards (VMAs). This year’s VMAs turned out to be one of the world’s largest, simultaneous social viewing experiences ever. Leading up to this year’s VMAs, MTV marketers set out to grow the brand’s social media presence and drive awareness. With 85 million MTV Facebook fans and more than three million Twitter followers—the stage was set for a firestorm of conversation and sharing. In order to assist MTV in their primary goal of gaining deeper insights into relationships between social activity and engagement with digital content, we combined Twitter and MTV.com data streams with text mining and predictive analytics techniques. As marketing continues to develop, sentiment forecasting will be critical to success in optimizing published content for both publishers and advertisers.
Speaker: John Bates, Product Manager, Predictive Marketing Solutions for Adobe® Digital Marketing Suite, Omniture
[ Top of this page ] [ Agenda overview ]
Sponsored Lab
Lab Session: Live Topical Demo
Predictive and Text analytics have been rapidly gaining a foothold in a surprising number and variety of Federal Government and Commercial Business areas from workforce management to national security. This session will look at how the combination of text and predictive analytics is helping government agencies and commercial industry work faster and more effectively amid tightening budgets and decreasing resources and why it has become such a popular resource.
Speaker: Steven Reeves, Text Analytics Overlay within the IBM-SPSS North American IOT Group
[ Top of this page ] [ Agenda overview ]
3:45-4:10pm
Breaks / Exhibits
[ Top of this page ] [ Agenda overview ]
Track 1: Healthcare
Case Study: Center for Disease Control
Applying Text Analytics to Answer Quantitative Preparedness Questions
This session will examine how text analytics was integrated into a proof-of-concept to answer specific questions regarding the Centers for Disease Control’s preparedness for national/natural disasters. The analysis is based on a data set consisting of many years’ worth of After Action Reports (AARs). The CDC conducts disaster preparedness exercises to evaluate their ability to respond to national disasters. An AAR is generated after each exercise. However, reviews of AARs are manual and labor intensive. Using text analytics, we were able to efficiently and accurately determine the frequency of past problems and successes and produce trend lines over time.
Speaker: Brent Farrell, Booz Allen Hamilton
[ Top of this page ] [ Agenda overview ]
Track 2: Blackbox Trading
Case Study: AlphaGenius
Behaviorals: Using Twitter & the Social Internet to Obtain Above Market Returns
Behaviorals is not an introduction to behavioral economics or about knowing yourself as an investor. There are lots of books on behavioral economics that give thorough analysis of why investors, as people, make irrational decisions and how to not let yourself fall victim to your own human emotions while investing. Instead, behaviorals is about studying other people as emotional investors and using text analysis of the social Internet to measure mass psychology to obtain above market investment returns.
Speaker: Randy Saaf, CEO, AlphaGenius
[ Top of this page ] [ Agenda overview ]
Track 1: Marketing & Branding
Case Study: AVG Security
Scorecarding from Verbatims
Social Listening creates new opportunities to measure the health of the brand and the impact of marketing. It’s not, however, a slam dunk. Unlike primary research, social listening doesn’t represent a true sample of your customer base and doesn’t offer obvious segmentation variables to drive action. Jill Hunley and Jesse Gross will share their experiences and challenges in creating business intelligence and customer research for AVG from social verbatim. They’ll address true research issues around data quality, segmentation, data summarization and classification, and executive presentation from a hands-on perspective.
Speaker: Jesse Gross, Vice President of Analytics, Semphonic
[ Top of this page ] [ Agenda overview ]
Track 2: Thought Leadership
The Seven Different types of Text Mining and the Five Questions that Reveal the Right Approach
“Text Mining” can still mean different things to different practitioners, as the rapidly growing field encompasses a wide range of technologies and applications. We find there to be seven distinct practice areas – such as information retrieval and document classification — which employ very different goals, terminology, and technology. Which is the best to employ for your goals, given your data? We describe a simple decision tree, with five questions, that can lead you to the resources best suited for your task. To illustrate, we “drop the TAW program down the tree” for a visual clustering of the talks from these two days, and reveal where the conference has been strongest.
Speaker: Andrew Fast, Senior Scientist & Director of Research, Elder Research, Inc.
[ Top of this page ] [ Agenda overview ]
4:55-5:15pm
Break
[ Top of this page ] [ Agenda overview ]
Keynote
Multiple Case Studies: U.S. DHS, SSA
Text Mining: Lessons Learned
Text Mining is the “Wild West” of data mining and predictive analytics – the potential for gain is huge, the capability claims are often tall tales, and the “land rush” for leadership is very much a race.
In solving unstructured (text) analysis challenges, we found that principles from inductive modeling – learning relationships from labeled cases – has great power to enhance text mining. Dr. Elder will highlight key technical breakthroughs discovered while working on projects for leading government agencies, including:
- Prioritizing searches for the Dept. of Homeland Security
- Quick decisions for Social Security Admin. disability
- Document discovery for the Dept. of Defense
- Disease discovery for the Dept. of Homeland Security
- Risk profiling for the Dept. of Defense
Dr. Elder will summarize, from these (and commercial) deployment experiences, the factors essential to a successful text mining project.
Speaker: John Elder, CEO & Founder, Elder Research, Inc.
[ Top of this page ] [ Agenda overview ]
Post-Conference Workshop
Thursday, March 8, 2012
Full-day Workshop
Advanced Methods Hands-on: Predictive Modeling Techniques
Click here for the detailed workshop description
[ Top of this page ] [ Agenda overview ]
Post-Conference Workshop
Thursday, March 8, 2012
Full-day Workshop
Making Text Mining Work: Practical Methods and Solutions
Click here for the detailed workshop description
[ Top of this page ] [ Agenda overview ]
Post-Conference Workshop
Thursday, March 8, 2012
Post-Conference Workshop
Friday, March 9 & Saturday, March 10, 2012
Two-day Workshop
Net Lift Models: Optimizing the Impact of Your Marketing
Click here for the detailed workshop description
[ Top of this page ] [ Agenda overview ]
