이병권

Sep. 2019 – Present : Integrated Ph.D course in Industrial Engineering (Operations Management), Seoul National University.
Mar. 2015 – Aug. 2019 : BS in Industrial Engineering, Seoul National University.
Mar. 2012 – Feb. 2015 : Graduation in Yangseo High School

Data-driven supply chain management. (Deep reinforcement learning, Bandit algorithm, etc.)
Centralized/Decentralized multi-echelon distribution systems optimization.
Information sharing in supply chain management.

Byeongkwon Lee, Kun Soo Park, Seyoun Jung, A Modified Deep Deterministic Policy Gradient Algorithm for Data-Driven Inventory Management, Journal of the Korean Society of Supply Chain Management, 21(3), 71-89
- We develop a modified version of deep deterministic policy gradient(DDPG) algorithm, which is one of the most popular deep reinforcement learning algorithms dealing with continuous action spaces, and apply it to the infinite-horizon newsvendor problems with constant lead time. Reflecting the key features of the inventory management problems, our algorithm, named as Inventory based DDPG (IDDPG), is differentiated in the state variables, action spaces, and cost functions compared to the DDPG. By conducting numerical experiments and comparing the performances, we found that when applied to the inventory management problems, IDDPG is able to find the near-optimal solutions and outperforms the DDPG in most cases. We also found that our IDDPG can be applied to a inventory management problem whose optimal solution is not known. (Keyword : Newsvendor Problem, Data-Driven Approach, Deep Reinforcement Learning, Deep Deterministic Policy Gradient)

Byeongkwon Lee, Jeongwook Lim, Kun Soo Park, Optimal Inventory Policy for Upstream When Downstream Follows (s, S) Policy.
Jeongwook Lim, Byeongkwon Lee, Kun Soo Park, Upper Confidence Bound Bandit Algorithm for Data-Driven Inventory Management.
Jiyong Kim, Byeongkwon Lee, Kun Soo Park, Kwanghun Chung, Bilevel Optimization and Stackelberg Game for Capacity Allocation Problem with Effort dependent Demand in Global Supply Chain.
Chaehoon Han, Byeongkwon Lee, Kun Soo Park, Advanced Purchase Discount Contract between Decentralized Two-Echelon Distribution Systems.

Optimal Inventory Policy for Upstream When Downstream Follows (s, S) Policy. in Korean Institute of Industrial Engineers and Korean Academic Society of Business Administration 2023 Spring Conference, Jeju, Korea.
A Markov-Modulated Demand Model and Optimization Algorithm for Inventory Control When The Customer Is Using (s, S) Policy. in Korean Institute of Industrial Engineers 2022 Fall Conference, Incheon, Korea.

디지털 공급망으로의 전환: 데이터기반 공급망관리 알고리즘 및 정보공유 협력 체계 개발, 물류산업진흥재단, 2023.05 – 2023.10.
마르코프 수요 모델을 활용한 분권화된 다계층 공급망에서의 재고관리 최적화 알고리즘 연구, 한국연구재단, 2022.06 – 2023.05.
디지털공급망과 정부의 역할, 산업통상자원부, 2021.
순차적 실시간 생산용량배분에 관한 연구: 효율성 및 공정성을 중심으로, 한국연구재단, 2019.09 – 2021.02.
공급망 관리 진단 및 개선 자문, 아모레퍼시픽, 2020.02 – 2020.07.
스마트물류의 확산을 위한 규제개선에 관한 연구, 한국개발연구원, 2019.10 – 2020.08.

수요예측 및 재고관리 최적화 소프트웨어 기술창업
베이지안 통계와 머신러닝 기술 기반 수요예측 알고리즘 개발
Logis All에게 소프트웨어 제공 (3000만원 수익) https://m.blog.naver.com/logisallgroup/222614378172

Hyper-Parameter Optimization Project 참여
MLP(Multi-Layer Perceptron)과 CNN(Convolutional Neural Network) Hyper-parameter 최적화를 위한 GA(Genetic Algorithm)을 활용법 연구

UNIVE 투자유치 프로젝트 참여 Investor Relations 보고서의 산업동향 및 기업 경쟁력 파트 작성
ROKIT HEALTHCARE 기업 투자결정 프로젝트 참여 Additive Manufacturing, 3D Printing, Biotech 산업동향 및 기업 경쟁력 분석
Parcel Net 기업 컨설팅 프로젝트 참여 Last mile delivery를 위한 O2O 플랫폼 비즈니스 서비스 전략 기획

운영관리 연구실Operations Management Lab