Building Recommender Systems in Julia

While I was studying recommendation algorithms in my master's program, I happened to know the Julia programming language. It focuses on high-performance scientific computing by utilizing the just-in-time compiler, and I see the programming language can be a great choice for developers to efficiently and effectively pre-process user-item data, build a recommendation model, evaluate a ranked list of recommended contents, and post-process the recommendation if needed. Thereafter, I have been implementing various recommendation techniques in Julia and packaging them as Recommendation.jl.

recommender-overview

After presenting at JuliaCon conferences twice in 2019 and 2022, I'm finally working on a publication for its proceeding. A paper review process is underway at JuliaCon/proceedings-review.

Articles in this series

  1. Recommendation.jl: Building Recommender Systems in Julia
  2. Publishing My Master's Thesis with Documenter.jl
  3. Lightning Talk about Recommender Systems in Julia at #JuliaCon 2019
  4. Recommendation.jl v0.4.0: Working with Missing Values, Data Typing, and Factorization Machines
  5. Cross Validation for Recommender Systems in Julia
  6. Recommendation.jl Came Back to #JuliaCon 2022

  Author: Takuya Kitazawa

Takuya Kitazawa is a freelance software developer based in British Columbia, Canada. As a technologist specializing in AI and data-driven solutions, he has worked globally at Big Tech and start-up companies for a decade. At the intersection of tech and society, he is passionate about promoting the ethical use of information technologies through his mentoring, business consultation, and public engagement activities. See CV for more information, or contact at [email protected].