CHIH-MING CHEN

Embedding ALL the World

A game-like profile of a machine-learning researcher

Chih-Ming Chen
LV 1 · ML RESEARCHER
XP 0 / 100 — explore to level up
CLASS: ALGORITHM DEVELOPER · PhD CANDIDATE

Chih-Ming Chen

|

A Ph.D. researcher with a deep passion for data analysis — research that isn't only theoretical but applicable to real-world problems. Builds recommendation products, competes in predictive-modeling challenges, and leads open-source machine-learning projects.

CHARACTER SHEET

Stats · Skills · Training Arc

SKILL STATS

Python (beloved) 96 / 100
Recommender Systems 98 / 100
Network Embedding 95 / 100
Factorization Models 92 / 100
C / C++ & Scripting 84 / 100
Competitive Data Science 94 / 100

PLAYER INFO

GUILDMiso Technologies — ML Developer (remote, Foster City CA)
ACADEMYTaiwan Int'l Graduate Program — PhD Candidate, Social Networks & Human-Centered Computing
LABC&C Lab · MAC Lab · CITI, Academia Sinica
SPECIALTYRecommendation, embeddings, collaborative learning — any ML-related quest accepted

TRAINING ARC

2015 — now
PhD, Social Networks & Human-Centered Computing
Academia Sinica / National Chengchi University
2011 — 2013
M.S. Computer Science
National Chengchi University
2007 — 2011
B.S. Computer Science
Soochow University

QUEST LOG

Experience — 10+ years of completed missions

MAIN QUEST · ACTIVE 2019 — current Foster City, CA (remote)

Miso Technologies

Algorithm Developer

  • Maintain and improve the Personalization-as-a-Service system.
MAIN QUEST · ACTIVE 2014 — current Taipei, Taiwan

KKBox / KKLab / KKStream

Algorithm Developer

  • Built a decade-spanning arsenal of recommendation algorithms for music & video streaming.
Reveal the full loot table
  • Cross-domain recommendations
  • Text-based item-to-item recommendations
  • Streaming item recommendations
  • Ticket recommendations
  • Personalized song recommendations
  • Song-to-song recommendations
  • Image-to-song recommendation
  • Heterogeneous query-based recommendations
  • Approximate nearest-neighbor search
  • Personalized daily music discovery
SIDE QUEST · CLEARED 2020 Feb — Jun Singapore

Living Analytics Research Centre (LARC)

Research Assistant

  • Developed a text-aware recommendation model (published at CIKM'20).
SIDE QUEST · CLEARED 2019 Mar — Jul Taipei, Taiwan

CHANGING.AI

Algorithm Developer Intern

  • Maintained and improved the Recommendation-as-a-Service system.
SIDE QUEST · CLEARED 2018 Jul — Sep Hangzhou, China

Tmall, Alibaba Group

Algorithm Developer Intern

  • Investigated online-to-offline recommendation approaches.
  • Implemented an O2O graph-embedding solution and a list-wise learning-to-rank embedding framework.
RESEARCH ARC · CLEARED 2013 — 2017 Taipei, Taiwan

CITI, Academia Sinica

Research Assistant

  • Investigated recommendation-related research.
  • Investigated network-embedding modeling techniques.
MENTOR ARC · CLEARED 2011 — 2018 Taipei, Taiwan

CS Department, National Chengchi University

Teaching Assistant

  • Python Programming (graduate level), 2017–2018.
  • Web Search and Mining (graduate level), 2013–2019.
  • Computer Programming course / lab class, 2011–2012.

ACHIEVEMENTS

Boss fights — data-science competitions & honors

2015
RANK S

PIXNET Visitor Log Data Challenge

1st place / 40+ teams

Moving-average features + factorization machine.

2014
RANK S

KDD Cup 2014 — DonorsChoose.org

2nd on private leaderboard

Pruned feature interactions in FMs + EDA-driven prediction smoothing.

2016
RANK S

KAMERA Data Challenge

2nd place / 100+ teams

Outlier smoothing + linear regression for medical-emergency data.

2020
RANK A

ACM RecSys Challenge 2020

4th place worldwide

Tweet-engagement prediction at Twitter scale.

2017
RANK A

WSDM Cup 2018 — KKBox Music Rec

7th / 1000+ teams

Single GBM with similarity features from his own proNet toolkit.

2015
RANK A

KDD Cup 2015 — MOOC Dropouts

9th prize / 800+ teams

Linear ensemble with novel backward-cumulative features.

2019
SPEAKER

ACM RecSys 2019 — Tutorial Talk

90-minute tutorial: SMORe

Modularize graph embedding for recommendation.

2014
RANK B

Tradeshift Text Classification (Kaggle)

20th / 300+ teams

Two-layer boosting prediction pipeline.

2016
GRANT

TIGP Travel Grant

Publication support

Taiwan International Graduate Program.

2013
SCHOLAR

Departmental Scholarship, NCCU CS

Top-ranking students

Awarded for academic excellence.

INVENTORY

Open-source artifacts — forged & battle-tested

CODEX

Publications — 14 scrolls inscribed in the archives

2020
TPR: Text-aware Preference Ranking for Recommender SystemsCIKM'20 · Oral
Chuang, Chen, Wang, Tsai, Fang, Lim
2020
Skewness Ranking Optimization for Personalized RecommendationUAI'20 · Oral
Wang, Chuang, Chen, Tsai
2020
Item Concept Network: Towards Concept-based Item Representation LearningIEEE TKDE
Wang, Yang, Chen, Tsai, Wang
2019
SMORe: Modularize Graph Embedding for RecommendationRecSys'19 · Tutorial
90-minute tutorial talk
2019
Large-Scale Weighted-Positive and Unlabeled Graph Representation LearningarXiv
Preprint
2018
HOP-Rec: High-Order Proximity for Implicit RecommendationRecSys'18 · Oral
Yang, Chen, Wang, Tsai

JOIN THE PARTY

Recruiting for an ML quest? Looking for a teammate who embeds all the world? Send a raven — or just an email.