Chiwan Park

Machine Learning Engineer @ Kakao Corp.

I’m a machine learning engineer at ART (Advanced Recommendation Technology) team of Kakao Corporation where I’m building recommender systems and machine learning applications for various mobile and web services of Kakao. Before joining Kakao ART team, I did some research on large-scale graph processing using distributed systems under guidance of Prof. U Kang at Seoul National University. Here is my full Curriculum Vitae.

Outside of paid works, I enjoy developing various softwares. I have contributed to some open-source software projects such as Apache Flink, and commonmark-java. You can see my activities about open-source software in Github.

News

  • Jan. 24, 2020 - A paper, "FlexGraph: Flexible partitioning and storage for scalable graph mining" was published to PLoS ONE.

  • Aug. 30, 2019 - I gave a talk named "상품 카탈로그 자동 생성 ML 모델 소개" at if (kakao)dev 2019.

  • Apr. 30, 2018 - I joined ART team of Kakao Corp. as a software engineer.

  • Nov. 10, 2017 - A demo paper, "PegasusN: A Scalable and Versatile Graph Mining System" was accepted to AAAI 2018.

  • Mar. 2, 2016 - I joined Data Mining Laboratory at Seoul National University as a master’s student.

Education

Master of Science in Computer Science and Engineering

Mar. 2016 - Feb. 2018 Seoul National University, Seoul, Korea

Bachelor of Science in Earth System Sciences
Bachelor of Engineering in Computer Science (double major)

Mar. 2010 - Feb. 2016 Yonsei University, Seoul, Korea

Publications

FlexGraph: Flexible partitioning and storage for scalable graph mining

Chiwan Park, Ha-Myung Park, and U Kang. PLoS ONE 15(1): e0227032 [paper] [github]

PegasusN: A Scalable and Versatile Graph Mining System

Ha-Myung Park, Chiwan Park, and U Kang. Thirty-Second AAAI Conference on Artificial Intelligence (AAAI) 2018, New Orleans, Lousiana, USA. (Demo Paper) [paper] [homepage (code)]

A Distributed Vertex Rearrangement Algorithm for Compressing and Mining Big Graphs

Namyong Park, Chiwan Park, and U Kang Journal of KIISE, Vol. 43, No. 10, pp. 1131-1143, 2016. [paper] [homepage (code, dataset)]

Experience

Kakao Advanced Recommendation Technology Team (Apr. 2018 - Now)
  • Product Recommender System for Gift

    • Logo of Kakaotalk Gift Kakaotalk Gift is an e-Commerce platform to send gifts through Kakaotalk, a well-known messaging platform in Korea. Choosing gifts depends on multiple contexts like a relationship between sender and receiver, demographical information, and product popularity. I am developing a real-time recommender system based on neural networks, graph embedding, and collaborative filtering to consider the contexts.

  • Recommender Systems for Digital Comics

    • Logo of Kakaopage and Piccoma Kakaopage and Piccoma are digital comics platforms served in Korea and Japan, respectively. I am mainly working with combining content-based representation learning and collaborative filtering for cold-start items. I focus on recommender systems as a user-targeted marketing tool for new comics and optimize the first conversion rate.

  • Large-scale Machine Learning Applications for e-Commerce Platform

    • Logo of shoppinghow by kakaocommerce shoppinghow by kakaocommerce is an e-Commerce platform like eBay and Amazon. Users can search for the products on the platform. I develop and maintain several machine learning applications for product categorization and product matching based on neural networks and graph algorithms. Various parallel computing techniques are applied to the models to handle web-scale data.