Hee-Jung Lee
Hanyang University · Economics, Econometrics and Finance
About the Lab
Professor Hee-Jung Lee's research lab specializes in data-driven decision making and knowledge discovery, with a focus on applying advanced analytics and artificial intelligence to real-world industrial and economic challenges. The lab investigates the value dynamics of digital assets such as NFTs, particularly through the lens of blockchain technology, rarity, and market behavior. It also develops innovative methods for knowledge representation and information extraction, especially using formal concept analysis to enhance the manageability and interpretability of complex knowledge databases. Additionally, the lab applies time-series modeling to forecast critical economic indicators, such as port container throughput, under the influence of global disruptions like the COVID-19 pandemic.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15In enterprises operating large-scale equipment, such as plant enterprises, maintenance workers must quickly and accurately find and understand the information required in the equipment maintenance documents to perform maintenance tasks effectively. If the equipment maintenance documents exist in each file for each equipment and the sentence expression constituting each document is ambiguous, it will interfere with the effective performance of the maintenance, and it leads to loss of the company.
This study empirically analyzes the determinants of NFT (Non-Fungible Token) value in the collectible NFT market, focusing on investor types. Using structural equation modeling (SEM) and multi-group analysis, we examine the effects of rarity, number of attributes, and trading volume on NFT value, comparing differences between large-scale (whale) and small-scale (ant) investors. Analyzing over 88 thousand transaction data points for 10,000 NFTs from the Bored Ape Yacht Club (BAYC) collection, res
In this study, we explore factors that affect the value of non-fungible tokens (NFTs). NFTs have been expected to play an important role in the future digital environment because they are made of blockchain technology that can prove ownership of digital assets. In this study, we focus on the value determinants of a representative project of profile picture NFTs among the most actively traded collectible NFTs, that is Bored Apes Yacht Club (BAYC). In order to do this, we first collected attribute
We introduce a method to calculate significance of attributes, objects and concepts in a knowledge database. To identify their significances, we consider the weighted Formal Concept Analysis, and evaluate the intrinsic properties of concept lattice. The significance of attributes and objects considers the following four aspects in combination: relevance, common shared or variety, conformance, and contribution. After that, the concept significance utilizes the results of attributes and objects si
This study investigates how factors such as the number of properties, property rarity, and the number of trades influence NFT value, using path analysis within a structural equation modeling framework. Focusing on the Bored Ape Yacht Club (BAYC), a leading example of collectible NFTs, this analysis indicates that higher rarity and fewer trades generally correlate with greater NFT value. While some inconsistencies were observed in the relationship between rarity and the number of trades, an overa
In this study, we consider the problem of forecasting monthly container throughput of Busan port, the largest port in South Korea. We proposed a forecasting model based on SARIMAX (Seasonal AutoRegressive Integrated Moving Average with eXogenous variables), a well-known traditional time-series model in which an appropriate exogenous variable is embedded to take into consideration the effect of COVID-19 during the pandemic era. The orders of the various terms included in the SARIMAX model were de
Even in the age of digital technology, food is still one of the most important part of everyday life for all of us. Wecan also easily access food-relevant data about the topic on social media, from trends like diet issues to variousculinary recipes. In this study, we performed the text analytics on the natural language recipes, and proposed therecipe recommendation method considering our preference and ingredients at hand. The ingredient componentswere extracted from the natural language recipes
With the constant growth of R&D investment by government-funded research institutes, it has been increasingly necessary to evaluate the effectiveness of R&D performance. There are many approaches that have focused on R&D performance evaluation. Literature is unclear, however, how stakeholders can exploit performance results to improve their R&D capability. In this study, based on the intellectual capital possessed by research institutes, we proposed a new method to search improvement directions
ICO is a newly attempted funding method in the blockchain field in 2013, with an increasing number of projects each year. However, the number of startups failing to raise funds below $100,000 has risen from 51% in 2017 to a maximum of 75% in the second quarter of 2018. Accordingly, startups preparing for ICOs need to study what factors affect successful funding. In this study, we apply the formal concept analysis technique to classify the major occupational groups in the block chain field as dev
Recently, the market competition has been fiercer due to the acceleration of technological change and the launch of intelligent products. In this situation, technology cooperation activities through networks rather than independent technological innovation activities of a single company or institution are recognized as a crucial strategy to gain competitiveness. Technology cooperation can take various forms depending on the target technology, and researchers have conducted performance analyses o
This study aims to identify the social and human capital of spin-off startup founders, and explores the relationship between capital and business performance. We propose a new method using formal concept analysis to address its relationships based on small-scale data, which incorporates the partially ordered capital evolution path with its business outcomes. For this research, we conducted in-depth case studies on spin-off startups from Samsung’s Creative Lab by collecting information from both
Sentiment analysis is a method used to comprehend feelings, opinions, and attitudes in text, and it is essential for evaluating consumer feedback and social media posts. However, creating sentiment dictionaries, which are necessary for this analysis, is complex and time-consuming because people express their emotions differently depending on the context and domain. In this study, we propose a new method for simplifying this procedure. We utilize syntax analysis of the Korean language to identify
A new approach was attempted to analyze the value of NFT, which is emerging as a major field in the digital environment along with cryptocurrency and metaverse. From the point of view that heterogeneous groups may exist in an NFT collection, latent class analysis, an object-oriented methodology, was applied. Existing NFT value studies focus on finding significant variables mainly through regression analysis, so there is a limitation in not considering the heterogeneity within the group. As an an
Research on movie revenue has been divided into analysis of traditional box-office and studies on online market such as VOD, which have recently emerged. However, the commercial success of a particular movie consists of the box-office revenue and the secondary market performance including VOD. The box-office and VOD markets are connected by holdback, which is the time difference of movie and VOD release, and hence the structured relationship should be considered. In this study, a path analysis m
Rapid technological change and accelerating convergence have made early detection of emerging technologies a strategic imperative for nations and enterprises. This study proposes a methodology for detecting emerging and convergence technologies by applying Formal Concept Analysis (FCA) to patent application data. Unlike existing studies relying on simple frequency analysis or static classification, we introduce new quantitative indicators—Average Novelty and Convergence Degree—to structurally an
Research Areas
Dive deeper into Hee-Jung Lee's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.