About Me
Hello, I am Youngeun Nam. I am a Ph.D. candidate in Data Mining Lab at KAIST. My academic experience is deeply rooted in the field of data mining which involves uncovering meaningful patterns and insights from vast and complex datasets. Currently, my research is focused on exploring the potential of multi-modal data-centric deep learning across various domains. This area of study is fascinating because it integrates and analyzes different types of data—such as images, text, and numerical data—simultaneously, leading to more robust and comprehensive models that can better understand and predict complex phenomena. My work aims to push the boundaries of what is possible with deep learning, particularly in the context of real-world applications. In addition to my academic pursuits, I am strongly interested in applying these advanced data mining techniques to the sports domain, where data analysis is increasingly becoming a critical component of performance enhancement, strategic planning, and injury prevention. My passion for sports analytics has been further fueled by my professional experience as a data analyst at a leading sports data analysis company, named Fitogeter.
Education
KAIST
Ph.D.
2022.03 - Present
Korea Advanced Institute of Science and Technology | School of Computing
Data Mining Lab advised by Jae-Gil Lee
KAIST
M.S
2020.03 - 2022.02
Korea Advanced Institute of Science and Technology | Industrial and System Engineering
(Graduate School of Data Science)
Data Mining Lab advised by Jae-Gil Lee
POSTECH
B.S
2013.03 - 2017.02
Pohang University of Science and Technology | Industrial and Management Engineering
Experience
Fitogether, Innovating the Sports Culture Using IT Technology.
Based on a wearable EPTS with its own technology, Fitogether measures player/team data during sports (association football) activities, and runs an analytics service ‘OhCoach’ using the data. In particular, I contributed to the launch of the soccer data analysis web service.
-
Producing manuals for Fitogether ‘Ohcoach’ service users at the ‘2018 K League U17/U18 Championship’ as a sports data analysis startup intern.
-
Creating crawling module with detailed information about K League K1, K2, R League, and ACL competition.
-
Creating the ‘Register’ module, the foundation for data analysis using Python, and implementing the algorithm.
Hyundai AutoEver leads a paradigm shift for the future of the 4th industrial revolution.
Working at Hyundai Autoever IT Jobs Finance Team (Hyundai Card, Capital, Commercial).
‘Hyundai Card/Capital/Commercial Blockchain Platform Construction and Service Challenge Implementation’ Project Developer.
Projects
Samsung Mobile Experience
KAIST
Jul. 2022 - Jul. 2023
Few-shot Anomaly Detection and Root Cause Estimation development.
Samsung Mobile Experience
KAIST
Jun. 2021 - Jun. 2022
Real-time service incident prediction development.
Samsung SDS
Seoul National University
Aug. 2018 - Jul. 2018
Storage-based platform model business idea research project.
Platform proposal that provides new value to storage consumers.
Hyundai Card
Hyundai Autoever
Jun. 2017 - Dec. 2017
Hyundai Card/Capital/Commercial Blockchain Platform Construction and Service Task Implementation.
Publications
-
Bae, M., Shin, Y., Nam, Y., Lee, Y., and Lee, J., Semi-Supervised Learning for Time Series Collected at a Low Sampling Rate. Proceedings of the 30th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), Barcelona, Spain, 2024. [Paper] [Video]
-
Nam, Y., Yoon, S., Shin, Y., Bae, M., Song, H., Lee, J., and Lee, B. S., Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection. International World Wide Web Conference (WWW), Singapore, Singapore, 2024. [Paper] [Video] [Poster]
-
Nam, Y., Trirat, P., Kim, T., Lee, Y., and Lee, J., Context-Aware Deep Time-Series Decomposition for Anomaly Detection in Businesses. Proceedings of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD). Torino, Italy, 2023. [Paper] [Slide] [Poster]
-
{Trirat, P., Nam, Y.}, Kim, T., and Lee, J., AnoViz: A Visual Inspection Tool of Anomalies in Multivariate Time Series. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI Demonstration Program). Washington, DC, 2023. [Paper] [Video] [Poster] [Live Demo]
-
Kim, D., Min, H., Nam, Y., Song, H., Yoon, S., Kim, M., Lee, J. COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies. The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI). Virtual Event, 2022. [Paper] [Video]
-
Nam, Y., Kang, J., Lee, J. ActiveBoostThief: Model Extraction Attack Using Reliable Active Learning. Korea Computer Congress. 2021. [Paper] [Slide]
-
Kim, M., Kang, J., Kim, D., Song, H., Min, H., Nam, Y., Park, D. Lee, J. Hi-COVIDNet: Deep Learning Approach to Predict Inbound COVID-19 Patients and Case Study in South Korea. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). Virtual Event, California, 2020. [Paper] [Video]
Awards & Scholarship
- Excellence in Character Scholarship, 2024 (₩1,000,000)
- Young-Han Kim Global Leader Scholarship, 2024 (₩4,000,000)
- School of Computing, KAIST, Outstanding Teaching Assistant Award, 2023 Spring
- The Thirty-Seventh AAAI Conference on Artificial Intelligence Scholarship, 2023 ($500)
- Department of Industrial & Systems Engineering, KAIST, Scholarship, 2021 (₩1,000,000)
Reviewer Services
- Program Committee
- ACM International World Wide Web Conference (WWW): 2024
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): 2024
- Annual Conference on Neural Information Processing Systems (NeurIPS): 2024
- Asian Conference on Machine Learning Conference Track (ACML): 2024
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): 2025 August
- International Conference on Learning Representations (ICLR): 2025
- Artificial Intelligence and Statistics (AISTATS): 2025
- ACM International World Wide Web Conference (WWW): 2025