Hofyrtv8fcbamvfnw435

楊昇芳

Interest in many fields and like to learn new things. 


Software Engineer, Machine Learning
Taipei,TW
[email protected]

Work Experience

KKBOX - Research Center, Research Student, Dec 2017 ~ May 2019

Co-Developed an algorithm for music recommender system to enhance both the Recall Rate
and Increase Mean Average precision by 3% by utilizing cross-domain Transfer Learning in
two different markets

Company@2x

Skill


Programming Language

  • C / C++
  • Python


Tools

  • Linux / Mac OS / Windows
  • Git


Framework

  • TensorFlow
  • Keras
  • Scikit-learn

Database

  • MySQL
  • SQLite


Certificate

  • TOEIC 760


Education

National Chengchi University, B.S. in Computer Science, 2012 ~ 2017

University@2x

National Chengchi University, M.S. in Computer Science, 2017 ~ 2019

Research: Networking Embedding, Recommender System, Machine Learning, NLP
University@2x

Publication

Negative-Aware Collaborative Filtering ( Accepted by RecSys 19’ )

Propose quantifying the degree of uncertainty for unseen associations by leveraging user preference similarity, and explicitly model the likelihood of each unseen association being a potentially positive user preference; can be applied to other recommendation algorithms with the use of negative sampling.

Competition

Kaggle: Quora Question Pairs - Bronze Medal (TOP 6%) 

Predict the probability that the questions are duplicates