If your business uses third parties to support core operations (and most do, from SMEs to corporates), you'll know they need to access essential data. Without this, they can't deliver the services you require Therefore, alongside this new relationship between you and your third party suppliers, comes a new responsibility for you. You now have an ethical and legal onus to protect the customer information entrusted to you. The devastation that a data breach leaves in its wake is obvious. And the media reports that accompany data breaches leave no doubt as to the financial and human consequences. At the same time, ongoing research into risk management, auditing, information security and supply-chain risk management hasn't stemmed the data breach tide.

Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between queries and documents. In this paper, we propose a topic-based personalized ranking model (TPRM) that integrates user topical profile with pretrained contextualized term representations to tailor the general document ranking list. Experiments on the real-world dataset demonstrate that TPRM outperforms state-of-the-art ad-hoc ranking models and personalized ranking models significantly. Keywords: personalized ranking model · personalized search · topic model · user profile.