Customer Program, which is one of our core science program, aims to build universal customer models and its applications. We’re working on following four research topics in Customer Program at Tokyo office.
Customer Pre-trained Model: Research scientists try to build universal customer models and its applications, motivated by the recent success of pre-trained models in language and vision fields. Such models can be adapted to improve diverse set of solutions for services including recommendation systems, customer targeting solutions and credit scoring functions to name a few. As initial and simpler applications, we work on predictions of customer features so-called customer DNA.
Credit Scoring: It is one of crucial research topics across Rakuten Group (Mainly in our fintech businesses such as credit card, payment, securities and banking business). Research scientist applies machine learning, data mining and optimization techniques to solve challenging problems, build models and solutions regarding credit scoring related projects. Our solution includes scoring for both business clients and individual users.
Policy Optimization: Rakuten group is contacting to our customers with various kinds of communication channels, such as showing banners on web pages, sending email, pushing notifications through apps, to promote our products and services. In order to deliver right contents at the right time to the right customers, research scientist applies reinforcement learning algorithms to build models to contents delivery platforms.
CDNA-IA: Customer DNA (CDNA) is a platform to manage Rakuten customer profiles by utilizing data from different Rakuten businesses. CDNA-IAs, a part of CDNA, are predicted customer profiles using machine learning profiles. The team builds and operates many models for CDNA-IAs. The team does apply recent research progress to develop efficient data pipeline and model creation.