Company Recommendation for New Graduates via Implicit Feedback Multiple Matri...Recruit Technologies
This document describes a method for recommending suitable companies to new graduates based on their browsing history and other data. It proposes using implicit matrix factorization of browsing data along with Bayesian optimization of hyperparameters to focus recommendations on less popular, low-browsed companies. An evaluation on Japanese student and company data showed this approach achieved higher recall of suitable matches for low-browsed companies compared to other methods, especially when incorporating additional student and company profile information.
The document outlines the divisions and focus areas of a large company, with most resources allocated to technology R&D, including deep learning and CNN. Other divisions include infrastructure, promotions, UI design, SEO, big data, IT, recruiting, staffing services, and administration.
Company Recommendation for New Graduates via Implicit Feedback Multiple Matri...Recruit Technologies
This document describes a method for recommending suitable companies to new graduates based on their browsing history and other data. It proposes using implicit matrix factorization of browsing data along with Bayesian optimization of hyperparameters to focus recommendations on less popular, low-browsed companies. An evaluation on Japanese student and company data showed this approach achieved higher recall of suitable matches for low-browsed companies compared to other methods, especially when incorporating additional student and company profile information.
The document outlines the divisions and focus areas of a large company, with most resources allocated to technology R&D, including deep learning and CNN. Other divisions include infrastructure, promotions, UI design, SEO, big data, IT, recruiting, staffing services, and administration.