Seems something we have done for a while. Is the algorithm more efficient? More numerical? Note the claim for use of statistical methods and ML.
Algorithm Analyzes Social Media Data to Help Brands Improve Marketng
University of Tokyo
February 4, 2020
Researchers at the University of Tokyo in Japan have created an algorithm that predicts consumer purchases from data on consumers’ social media activity, which brands could use to refine their marketing strategies. The algorithm integrates statistical modeling and machine learning-based image recognition. The researchers assessed the algorithm against purchase history and questionnaires, and learned that credit card or point (loyalty) card companies could accurately forecast customers' past purchasing patterns, while their program could accurately predict customers' willingness to try new brands. Said the university’s Toshihiko Yamasaki, “People might say that professionals already ‘see’ these kinds of patterns, but being able to show the similarity between brands numerically and objectively is a new innovation. Our algorithm is demonstrably more effective than judging these things based on intuition alone.”
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment