Industry Session 1 : Monday 1730-1900The Europe Media Monitor family of news analysis applicationsMijail Kabadjov, European Commission – Joint Research Centre (JRC), Ispra, Italy "The speaker will present the Europe Media Monitor (EMM) family of applications developed at the Joint Research Centre (JRC) of the European Commission. EMM consists of four publicly accessible news analysis systems (see http://press.jrc.it/overview.html):
EMM collects more than 80,000 articles per day from about 2,200 online news sources (e.g. BBC, Le Monde) in 43 different languages, including non-Latin character set languages such as Chinese, Arabic and Russian. EMM applications employ robust and efficient techniques using statistics and Language Technology to cluster news articles into major news stories, monitor the development of a story over time and across languages, extract information about entities (locations, persons and organisation) covered in the media, and more. The major objective of EMM is to serve the needs of users in the European Commission and in European Union Member State institutions. However, the service is freely accessible online so that a wide range of other users benefit from the applications: EMM web sites get between one and two Million hits per day (approximately 30,000 visitors per day). Additionally, many users are subscribed to email notifications. For more technical details and related research publications, see http://langtech.jrc.it. About the Speaker Mijail Kabadjov works at the European Commission’s Joint Research Centre (JRC) in Ispra (Italy), in the field of multilingual text summarisation and text mining. He joined the JRC from the School of Informatics of the University of Edinburgh (UK) where he spent two years with the Language Technology Group developing text mining applications for the biomedical and recruitment domains. He holds a Ph.D. in Computer Science from the University of Essex (UK), defended with a thesis on general-purpose anaphora resolution. Before commencing the Ph.D., he worked on various projects in industry, ranging from fraud detection in credit card transactions to customer service optimisation of a large manufacturing firm. Organizational Traits leading to High ROI for Data MiningAntonia de Medinaceli, Elder Research, Inc. Organizations can use data mining and advanced analytics to dramatically improve their bottom line in three basic ways, by (1) streamlining a process, (2) eliminating the bad, or (3) improving the good. But modern organizations are so effective at their core tasks that data mining usually results in an iterative, rather than transformative, improvement. This talk will discuss the traits and culture within a business unit that tend to turn data mining techincal successes into business successes, by highlighting some projects for some of America's most innovative agencies and corporations. About the Speaker Antonia de Medinaceli is a Senior Business Analyst at Elder Research, where she has been involved in all aspects of the data mining process over the past decade. Antonia has applied data mining technologies to a wide range of projects, including direct marketing, crime pattern analysis, credit scoring, and fraud detection. Her consulting experience is both domestic and international, and she is fluent in her native French and proficient in Spanish. Antonia is experienced with most of the leading statistical software packages, and has taught data mining short courses both on concepts and specific software. She has degrees in Computer Science and Systems Engineering from the University of Virginia. Improving Online Marketing Performance through Data Mining and OptimizationRob Cooley, Optimine On-line marketing spend is rapidly growing and relatively poorly understood when compared to many of the traditional marketing channels. On-line marketing has characteristics that are similar to both indirect (e.g. television, radio) and direct (e.g. catalog) marketing. The ability to track Web visits through “cookies” all the way through a purchase is analogous to a catalog marketer’s use of source codes to trace orders back to specific catalog versions. However, the concept of ad impressions that are viewed by an untracked audience is similar to television audiences viewing a commercial. The unique nature of on-line marketing and the available data sources leads to a need for unique applications for managing and optimizing the spend. This talk will present the results from three live tests of the use of data mining and constraint-based optimization to improve the business results for paid search, one of the major areas of online marketing. The case studies will cover a large US retail bank, a large US e-commerce site, and a US real estate lead aggregator. About the Speaker Robert Cooley holds a PhD in Computer Science from the University of Minnesota. Currently, Dr. Cooley is the Chief Technology Officer for OptiMine Software, which specializes in analytic applications for on-line marketing. Prior to OptiMine, Dr. Cooley was a VP of Technical Operations for KXEN Inc., a data mining software company. Dr. Cooley is known for his groundbreaking work in Web Mining and has over a decade of experience applying data mining to business problems. He has published numerous papers on the topics of CRM Mining, Web Usage Mining, and Text Mining.
Industry Session 2: Tuesday 1730-1900People aren't always doing what they are saying. Perception versus Reality.Alain Glickman, Orange Datamining is expanding it's scope towards the combination of hard factual measured data with soft declared surveyed data. This new trend enables us to understand causality of events and enables the tagging of qualitative segmentations in the customer base. However, both activities still have alot of challenges, mainly due to the discrepancy of what people say and what they actually do. Perception versus Reality. About the Speaker "Alain joined the France Telecom/Orange Group in Jan '04 as Director of Customer Insight. Prior to that he worked 5 years at Mobistar, an affiliate of France Telecom in Belgium, after being 5 years in Belgacom, the fixed incumbent operator in Belgium. He specialises in Segmentation with its customer base 'tagging', and in Social Network Analysis. His weak points are his relationship with his shaver." The Telecom Revolution: Where does KDD go from here?Alejandro Jaimes Larrarte, Telefonica The telecommunications industry has undergone tremendous changes in recent years. Advances in increased bandwidth capabilities and functionality of mobile devices, along with other factors have resulted in more sophisticated customers, highly competitive global markets, new “players”, and the emergence of new data-intensive services. All of these changes are leading to a search for new business models, partnerships, and open frameworks, which constitute a departure from the way the telecommunications industry had “traditionally” functioned. These factors combined with a tremendous increase in data (not just in traffic, but also in what is available to and generated by consumers in new services) are creating huge opportunities for KDD and tremendous challenges, not just from a business intelligence perspective, but also for user modeling applied to new business models and services. In this talk I will discuss how this landscape has evolved and its impact on KDD tasks, giving specific examples, describing technical challenges and pointing to the links from research to business applications in current and future settings. About the Speaker Alejandro Jaimes is Senior Research Scientist at Telefónica Research in Madrid where he works closely with engineering teams on applied research solutions on data mining and user modeling from a human-centered perspective. Dr. Jaimes obtained his Ph.D. from Columbia University in 2003 and has worked for IBM (USA, Japan), Fuji Xerox (Japan), Siemens (USA), AT&T Bell Labs (USA), and IDIAP Research Institute-EPFL (Swizterland). He holds several patents and has given numerous invited talks and participated in panels at several international conferences. Social network analysis for telco operators.Edouard Servan Schreiber, Teradata Telco operators are now realizing the tremendous value laced in the relationships among their subscribers as revealed by their calling pattern. Social Network Analysis (SNA) goes beyond calling circle analysis by analyzing also how the calling circle communicates among themselves. These network patterns reveal who is influential and who experiences pressure from other subscribers. This information is critical in determining which subscribers are worth more marketing investment due to their potential influence on other subscribers to adopt new products. Also, it reveals who is suddenly more vulnerable to churn even though nothing changed in their behavior ! In this talk we will talk about the notions of SNA, a case study based on Rogers Wireless in Canada, and how the new KXEN module KSN enabled this work. About the Speaker Dr. Edouard Servan-Schreiber is Assistant Director of Advanced Analytics for Europe, Middle East and Africa. His specialty is to help businesses extract value from their data and insure that the sophisticated techniques of automated learning are serving business needs. Edouard has worked across industries and markets within the EMEA region. Among the topics Edouard has actively worked on: clickstream data for customer affinity, mobile marketing, pricing optimization, early warning in manufacturing reliability, text mining, and social network analysis. Edouard began practicing artificial intelligence and statistical learning models at Carnegie Mellon University for his bachelor’s degree, before going to UC Berkeley for his PhD in Computer Science. After returning to his native France, Edouard co-founded newsfutures.com, a technology startup offering prediction market technology. |
|