Top 10 Lessons Learned Developing, Deploying, and Operating Real-World Recommender Systems
by Francisco Martin (Founder/CEO Strands, Corvallis, Oregon, USA.)
The number of online services providing users with real-time recommendations has increased exponentially over the last few years. Recommender Systems that were originally only accessible to a limited number of high-tech companies are now widely available through a growing number of both technical choices and vendors. The acceptance however, of automatically delivered recommendations by users depends on numerous factors that go far beyond the algorithms that constitute the major focus of researchers. Dr. Martin will share a number of lessons learned over the last ten years creating and operating recommender systems in a multitude of domains, from digital music to fitness plans through personal finance management, and in a multitude of business settings, from lightweight integrations to highly-coupled integrations within secure bank environments.
About The Speaker
Francisco Martin is a scientific entrepreneur who serves as President, Chief Executive Officer and Chairman of the Board of Strands, Inc. (“Strands”) and its subsidiaries in Spain and Finland. Strands develops recommendation and personalization technologies to help people discover new things. The Strands recommendation engine works by “learning” people’s tastes and how their preferences evolve over time. Strands’ recommendation technology is used to generate real-time recommendations or preference predictions in a wide variety of different areas. Since Dr. Martin founded Strands in October 2003, he has grown the company to over 100 employees, at locations throughout the United States and Europe. Operating from the company’s headquarters in Corvallis, Oregon, Dr. Martin has raised $55M in funding. The company also has filed 24 U.S. patent applications covering its groundbreaking technologies, and Dr. Martin is a named inventor on 13 of these. Strands was named the 2007 Orange Innovation Contest Winner, the Nokia Mobile Rules! 08 Competition Winner, and the 2008 BlackBerry Partners Fund Developer Challenge Best in Show Grand Prize Winner.
Dr. Martin holds a Ph.D. in Computer Science with highest honors from Technical University of Catalonia. He developed his scientific career at the Artificial Intelligence Research Institute of the Spanish National Research Council. He has been a visiting researcher at the School of Mathematical Sciences at the University of Bath in the United Kingdom and the School of Electrical Engineering and Computer Science (EECS) at Oregon State University (OSU).
Up-Close and Personalized: A Marketing View of the Future of Recommendation Algorithms
by Michel Wedel (Pepsico Professor of Consumer Science, Marketing Department, Smith School of Business, University of Maryland, USA)
Recommendation systems have become the backbones of virtually any company with a significant online presence. In spite of the exponential growth in their development and use, several barriers prevent the effectiveness of product recommendations to reach its full potential. In particular, consumers often lack the time or ability to actively interact with these systems, and as a consequence do not provide product or service evaluations, or do not utilize the recommendations that are provided to them.
Rather than focusing on algorithmic issues such as scalability and efficiency, the Marketing literature has focused on the development of recommendation systems that are based on a fundamental understanding of consumer behavior, and the drivers and representation of consumer heterogeneity in the need for products and acceptance of recommendations. In particular recently so called Adaptive Personalization Systems (APS) have emerged in this literature. These systems work in real-time, operate on internet- and mobile platforms, require minimal proactive user effort and go substantially beyond the functionality of most standard recommendation systems.
These developments in the marketing literature are reviewed and two illustrations of APS are provided, in the context of news and music. These illustrations reveal that Adaptive Personalization Systems have the potential to significantly increase the effectiveness of personal recommendations, and perform better than extant methods.
About the Speaker
Michel Wedel is the PepsiCo Professor of Consumer Science at the Robert H. Smith School of Business at the University of Maryland. His main research interest is in Consumer Science: the application of statistical and econometric methods to further the understanding of consumer behavior and to improve marketing decision making. He has won the Hendrik Muller lifetime award for the social and behavioral sciences awarded by the Royal Netherlands Academy of Sciences for “exceptional achievements in the area of the behavioral and social sciences,” and has been elected foreign correspondent of that Academy. He has also won the O’Dell best article award from the Journal of Marketing Research. He has written over 150 articles in peer reviewed journals that were cited more than 2000 times. He was ranked first among all scholars in economics and business in the Netherlands. He has supervised 12 PhD students, serves on the editorial boards of the Journal of Classification, Quantitative Marketing and Economics, and Journal of Marketing, and is area editor for Marketing Science and The Journal of Marketing Research. He has published books on Market Segmentation, Models for Marketing Decisions and Visual Marketing. He has consulted for over 25 different companies in the nonprofit and profit sectors, including companies in market research, consulting, direct marketing, food, financial services, automotive, and telecommunications.
