About Tyler Lee

Moloco Inc.

📆 2024.11 – Present
Machine Learning Engineer (T4)

• Improved install conversion prediction models for Connected TV (CTV) ads by refining attribution logic and model architecture, resulting in improved AUROC and calibration performance.

• Designed user behavior-based features and integrated them into the model training pipeline, improving model expressiveness and addressing data sparsity issues.

• Built a modular data pipeline decoupled from production systems, enabling scalable feature backfilling and improving system reliability.

Asleep Inc.

📆 2020.06 – 2024.08
Cofounder & Director of AI

• Developed EEG-based AI sleep models in collaboration with Seoul National University Bundang Hospital, achieving state-of-the-art performance.
• Published research in Nature and Science of Sleep and JMIR Mhealth Uhealth, advancing the company's impact in the sleep tech industry. (Wired Feature)
• Led clinical studies and integrated AI services with data pipelines from hospitals and consumer apps, automating processes for rapid publication and operational efficiency.

Chief Operating Officer (COO) (2021.11 – 2023.04)

• Managed HR and internal operations, aligning company growth with organizational principles.
• Secured compliance with GDPR and CPPA regulations while leading investor relations and business operations.

Lanada Lab, KAIST

📆 2018.03 – 2020.06

• Led research projects on Multi-agent Reinforcement Learning and IoT networks with partners such as KEPCO and NAVER.

Journal Papers

J1. Taeyoung Lee*, Younghoon Cho*, Kwang Su Cha et al., “Accuracy of 11 Wearable, Nearable, and Airable Consumer Sleep Trackers: Prospective Multicenter Validation Study”, JMIR mHealth and uHealth, Volume 11, 2023

J2. Taeyoung Lee*, Jung Kyung Hong*, Roben Deocampo Delos Reyes et al., “Confidence-Based Framework Using Deep Learning for Automated Sleep Stage Scoring” Nature and Science of Sleep, Volume 13, 2021

Conference Papers

C1. Hai Tran, Sumyeong Ahn, Taeyoung Lee, and Yung Yi, “Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation” Proceedings of International Conference on Pattern Recognition (ICPR), 2020.

C2. Jinhwan Jung, Daewoo Kim, Taeyoung Lee et al., “Distributed Slot Scheduling for QoS Guarantee over TSCH-based IoT Networks via Adaptive Parameterization” Proceedings of International Conference on Information Processing in Sensor Networks (IPSN), 2020.

C3. DaewooKim, SangwooMoon, David Hostallero, WanJu Kang, Taeyoung Lee et al., “Learning to Schedule Communication in Multi-agent Reinforcement Learning” Proceedings of The International Conference on Learning Representations (ICLR), 2019.

Abstracts and Posters

A1. Taeyoung Lee, Kwang Su Cha, Seunghun Kim et al., “Evaluation of a Sound-Based Deep Learning Model with Polysomnography in a patient with Obstructive Sleep Apnea using Positive Airway Pressure Therapy” Chest, 2023. (poster)

A2. Taeyoung Lee, Younghoon Cho, Kwang Su Cha et al., Comparative Analysis of 11 Consumer Sleep Trackers with Polysomnography, World Sleep, 2023. (Oral presentation)

• Ph.D. Candidate (All But Dissertation), School of Electrical Engineering, KAIST
• M.S. in Electrical Engineering, KAIST
  Thesis: “Failure prediction of deep learning models for PSG-based sleep stage classification through dropout confidence.”
• B.S. in Physics, KAIST

• Kwanjeong Educational Foundation Scholarship (2019-2021)
• Samsung Humantech Thesis Prize (2019, 2020)
• KAIST Invention Award, Grand Prize (2017)
• ICT Achievement Award, Ministry of Science and ICT (2017)