전체
-
[세미나][26년 2월 1주차 세미나] Reinforcement Learning and Practice ( and 4 more others )
2026-02-03 -
[공지사항]학부연구생 서준일 KSC2025 학부생 최우수 논문상 수상
2026-01-30 -
[세미나][26년 1월 5주차 세미나] 3D 이동표적 탐색을 위한 다중 UAV 협력 탐색 연구 ( and 2 more others )
2026-01-29 -
[세미나][26년 1월 4주차 세미나] ROIC Prediction & 'DB Insurance & Finance Contest' & Hanwha Life Future Talent Contest : Moi AI Service ( and 3 more others )
2026-01-21 -
[세미나][26년 1월 3주차 세미나] (PR) DeepSeek-OCR: Contexts Optical Compression
2026-01-21 -
[세미나][26년 1월 2주차 세미나] Reinforcement Learning & MDP Pratice ( and 1 more other )
2026-01-21
공지사항
-
[공지사항] 학부연구생 서준일 KSC2025 학부생 최우수 논문상 수상
2026-01-30 -
[공지사항] 2025년 2학기 1차 컴퓨터비전 연구실 연구원 모집
2025-09-29 -
[공지사항] Graduate Program Admission for International Students
2025-07-22 -
[공지사항] 학부연구생 최규문, 조동현 봉림소프트웨어전시회 공대학장상 수상
2025-06-04 -
[공지사항] 2025년 1학기 컴퓨터비전 연구실 연구원 모집
2025-04-30 -
[공지사항] 2024년 2학기 컴퓨터비전연구실 연구생 모집
2024-11-13
세미나
-
[세미나] [26년 2월 1주차 세미나] Reinforcement Learning and Practice ( and 4 more others )
2026-02-03 -
[세미나] [26년 1월 5주차 세미나] 3D 이동표적 탐색을 위한 다중 UAV 협력 탐색 연구 ( and 2 more others )
2026-01-29 -
[세미나] [26년 1월 4주차 세미나] ROIC Prediction & 'DB Insurance & Finance Contest' & Hanwha Life Future Talent Contest : Moi AI Service ( and 3 more others )
2026-01-21 -
[세미나] [26년 1월 3주차 세미나] (PR) DeepSeek-OCR: Contexts Optical Compression
2026-01-21 -
[세미나] [26년 1월 2주차 세미나] Reinforcement Learning & MDP Pratice ( and 1 more other )
2026-01-21 -
[세미나] [25년 12월 4주차 세미나] 동계방학 학습 계획 ( and 1 more other )
2026-01-21
자료실
International Journal
-
KoTaP: A Panel Dataset for Corporate Tax Avoidance, Performance, and Governance in Korea
https://www.nature.com/articles/s41597-026-06722-5#citeas Abstract This study introduces the Korean Tax Avoidance Panel (KoTaP), a long-term panel dataset of non-financial firms listed on KOSPI and KOSDAQ between 2011 and 2024. After excluding financial firms, firms with non-December fiscal year ends, capital impairment, and negative pre-tax income, the final dataset consists of 12,653 firm-year observations from 1,754 firms. KoTaP is designed to treat corporate tax avoidance as a predictor variable and link it to multiple domains, profitability, stability, growth, and governance. Tax avoidance itself is measured using complementary indicators—cash effective tax rate, GAAP effective tax rate, and book–tax difference measures—with adjustments to ensure interpretability. A key strength of KoTaP is its standardized firm-year panel structure with standardized variables and its consistency with international literature on the distribution and correlation of core indicators. At the same time, it reflects distinctive institutional features of Korean firms, such as concentrated ownership, high foreign shareholding, and elevated liquidity ratios, providing both international comparability and contextual uniqueness. KoTaP enables applications in econometric and machine-learning applications, including explainable methods.

-
LFTD: Transformer-Enhanced Diffusion Model for Realistic Financial Time-Series Data Generation
https://www.mdpi.com/2673-2688/7/2/60 Abstract Firm-level financial statement data form multivariate annual time series with strong cross-variable dependencies and temporal dynamics, yet publicly available panels are often short and incomplete, limiting the generalization of predictive models. We present Latent Financial Time-Series Diffusion (LFTD), a structure-aware augmentation framework that synthesizes realistic firm-level financial time series in a compact latent space. LFTD first learns information-preserving representations with a dual encoder: an FT-Transformer that captures within-year interactions across financial variables and a Time Series Transformer (TST) that models long-horizon evolution across years. On this latent sequence, we train a Transformer-based denoising diffusion model whose reverse process is FiLM-conditioned on the diffusion step as well as year, firm identity, and firm age, enabling controllable generation aligned with firm- and time-specific context. A TST-based Cross-Decoder then reconstructs continuous and binary financial variables for each year. Empirical evaluation on Korean listed-firm data from 2011 to 2023 shows that augmenting training sets with LFTD-generated samples consistently improves firm-value prediction for market-to-book and Tobin’s Q under both static (same-year) and dynamic (τ → τ + 1) forecasting settings and outperforms conventional generative augmentation baselines and ablated variants. These results suggest that domain-conditioned latent diffusion is a practical route to reliable augmentation for firm-level financial time series.

