Profile image of Chiwan Park

Chiwan Park

Applied Machine Learning Engineer @ Kakao Corporation


I’m an Applied Machine Learning Engineer at the AI Vertical Solution of Kakao Corporation, where I’m building machine learning applications for various mobile and web services of Kakao. My research interests include applications of large-scale language-vision models, conversational recommender systems, and machine learning on graphs. I hold an M.Sc. in Computer Science and Engineering at Seoul National University, where I conducted research on large-scale graph processing using distributed systems under the guidance of Prof. U Kang. For more details about my research achievements, please refer to my full Curriculum Vitae.

In my free time, I have developed data-related products. SolveSQL, a web-based SQL learning platform for data analysts, is publicly available. I have contributed to open-source data processing tools such as Apache Flink, Apache Sqoop, and Apache MRQL. You can see my hobby development activities on Github.



Seoul National University (Mar. 2016 - Feb. 2018)

M.Sc. in Computer Science and Engineering Thesis: Pre-partitioned Matrix-Vector Multiplication for Scalable Graph Mining Advisor: Prof. U Kang

Yonsei University (Mar. 2010 - Feb. 2016)

B.Sc. in Earth System Sciences B.Eng. in Computer Science and Engineering (double major)


Simple and Efficient Recommendation Strategy for Warm/Cold Sessions for RecSys Challenge 2022

Hyunsung Lee, Sungwook Yoo, Andrew Yang, Wonjun Jang, and Chiwan Park RecSys Challenge Workshop at ACM RecSys 2022 [paper | github]

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 AAAI 2018 (demo paper) [paper | homepage]

A Distributed Vertex Rearrangement Algorithm for Compressing and Mining Big Graphs

Namyong Park, Chiwan Park, and U Kang Journal of KIISE (Vol. 43, 2016, domestic) [paper | homepage]


Kakao Corp. AI Vertical Solution Unit (Apr. 2024 - Now)

To be announced.

Kakao Corp. R&D Center (Apr. 2018 - May. 2021)
Kakao Corp. Advanced Recommendation Technology (ART) Team (May. 2021 - Mar. 2024)

As the unit lead of a research unit within the Kakao ART Team, I managed a group of 10+ individuals responsible for developing and maintaining recommender systems across various Kakao services, including social networking, digital comics, e-commerce, and news platforms. My key experiences and contributions include:

  1. Developing a lightweight user representation model for Daum, a popular news portal service with 10 million users, by leveraging important keywords from user-read articles to capture evolving user interests. The output of model served as a context input feature for bandit models, enhancing news recommendation quality.

  2. Building personalized recommender systems for mm, an audio-only social network services like Clubhouse. I employed graph-based recommendation models, incorporating techniques like graph pruning and regularization to optimize performance.

  3. Combining content-based representation learning and collaborative filtering to address cold-start issues for new comics on Kakao Webtoon and Piccoma in Korea and Japan. The recommender systems served as a user-targeted marketing tools, optimizing the first conversion rate.

  4. Creating a context-aware recommender system for Kakaotalk Gift, an e-commerce platform for sending gifts throught Kakaotalk messenger. The system considered multiple contexts such as demographics, product popularity, and user history including clicked and purchased items, by integrating text and image embedding along with collaborative filtering techniques.

  5. Developing and maintaining machine learning applications for shoppinghow, an e-commerce platform similar to eBay and Amazon. I implemented product categorization and matching systems using Transformers and graph algorithms, applying parallel computing techniques to handling billion-scale data efficiently.