I-COM’s latest output, titled Frontiers of Marketing Data Science Journal, boasts nine diverse and impactful papers focused on the most exciting challenges faced by the industry. Through in-depth analysis, case studies and research from industry leaders it provides solutions and content aimed at those individuals working at the cutting edge of marketing and advertising.
Supported by Catalina, who helps leading CPG brands influence behavior by personalising the path to purchase, the Frontiers of Marketing Data Science Journal provides a detailed analysis of key topics ranging from Attribution and Blockchain to Machine learning and Optimisation. With content provided by global experts from across the industry the Journal is yet another example of how I-COM brings the Data Science Elite together to deliver industry leading content and insight.
Included in the Journal are:
- The I-COM Primer on Blockchain’s Application to Advertising Technology
by Joshua Koran, Sizmek; Richard Bush, NYIAX; Jean-Paul Edwards, OMD; and Luke Mulks, Brave Software.
- Mixed Effects Marketing Mix Modelling Can Reveal Significant Heterogeneities in Advertising Response
by Saeed R. Bagheri, Amazon Advertising; Seyed Hanif Mahboobi, Amazon Web Services; Mericcan Usta, Apple; Jing Zhao, GroupM; and Hamid R. Darabi, Remedy Partners.
- Leverage Social Media Data to Explore Fashion Trending
by Ling Huang, Tumblr Inc.; and Amanda Brennan, Tumblr Inc.
- Common Errors in Marketing Experiments and How to Avoid Them
by Tanya Kolosova, Associates In Analytics Inc., Samuel Berestizhevsky, Innovator and Actionable Analytics Expert
- Who is Who with Behavioural Data: An Algorithm To Attribute The Device’s Navigation To Users Sharing The Same Device
by Carlos Ochoa, Netquest; Carlos Bort, xplore.ai; and Josep Miquel Porcar, Netquest.
- Trade Promotion Optimisation: Transforming Promotional Spending From A Cost Of Doing Business Into A Driver of Growth
by Donald E. Schmidt Ph.D., Independent Business Analytics.
- Consumer Journey: A New Perspective to the Attribution Problem
by Shawn Song Ph.D., PHD Media; Charlotte Ma, SapientRazorfish; and Pranav Patil, Annalect.
- A Comparison of Machine Learning Approaches for Cross-Device Attribution
by Robert Stratton, Neustar; and Dirk Beyer, Neustar.
- Using Ensembles to Solve Difficult Problems by Steven Struhl, Converge Analytic.
Kajal Mukhopadhyay, Ph.D., Data Science Lead, Marketing Effectiveness from Verizon and editor-in-chief of the Journal comments: “For a long time, we have been needing a professional publication in the realm of academia that combines our industry’s work in the marketing data field with analytic rigor. I strongly feel the Marketing Data Science Journal from I-COM serves that purpose.”
Andreas Cohen, Chairman of I-COM comments: “The Frontiers of Marketing Data Science Journal represents I-COM’s ongoing commitment to deliver high quality, industry focused output on the cutting edge of both the theoretical and practical use of marketing data science. As per the Journal’s tagline it really is at the forefront of the marketing data revolution. I am delighted that we have brought together such a variety of industry leading subject matter experts to deliver what should be a powerful resource and tool for all those working across the sector.”
Wes Chaar, Chief Data & Analytics Officer from Catalina comments: “The I-COM Primer on Blockchain’s Application to Data Technology could not have come at a better time. A lot of people are talking about blockchain, and a lot of articles are being written about it, but there’s still a lot of confusion about what it is and how marketers can truly benefit from it. This series of papers by some of the most esteemed data scientists out there provides needed and much appreciated clarity. Consider for example the article by Dirk Beyer and Robert Stratton: A Comparison of Machine Learning Approaches for Cross-Device Attribution. Modeling Cross-Device Attribution properly is critical for effective attribution. To develop practical guidelines, they assess the performance of a multitude of Machine Learning based approaches. Furthermore, they compare Machine Learning results to those of Random Forest Models.”