GX & Decarbonization Research

Yueh-Cheng Huang

Releases a dataset and code for measuring whether photos in sustainability reports actually evidence the adjacent text claims. Covers 443 Chinese-language reports from 150 listed Taiwanese firms (52,568 pages, 17,450 photos), classifying ea…

Sanoh Yusuf

This paper applies text-mining methods to analyze climate transition risk under uncertainty using Japanese equity market data. It appears to extract transition-risk signals from corporate disclosures and empirically link them to market valu…

Dami Moon, Sumiaki Kusahata, Yoshihiro Kawahara

This study proposes and validates an automated method using a Vision-Language Model to extract product-specific attributes (e.g., fabric composition) from unstructured user-generated content on C2C platforms and calculate product-specific G…

DIVYANSHU PRADHAN Divyanshu pradhan, Sanchit Sanchit

Proposes a federated Unified Carbon Footprint Management portal calibrated for India, pairing a deep-learning lifestyle baseline with a barcode-driven product tracker. Among 12 regression models, an MLP achieves R²=0.8963 for lifestyle carb…

Si-Yu Shen, Chao Li, Jun Xie +3

This study builds a financial-materiality-oriented ESG disclosure measure, applying a Text Match Pretrained Transformer (TMPT) to Japanese Annual Securities Reports of listed food and beverage firms (2020-2024) and SASB industry material to…

(著者不明)

This paper addresses AI-based ESG evaluation and risk analysis. Although details are unavailable, it focuses on the intersection of AI and ESG, applicable to corporate sustainability assessment and climate risk quantification.

Kokubu, Hiroyuki

A quarterly snapshot of GX disclosure metrics machine-extracted from integrated reports and sustainability reports of TSE Prime-listed companies. Covers Scope 1/2/3 emissions, SBT status, TCFD disclosure, CDP score, renewable ratio, interna…

Shoichiro Hosomi, Soichiro Yamamoto

This study examines the association between CDP scores (climate change, water security, forests) and firm value (Tobin's Q) and profitability (ROA, ROE) using panel data of Japanese manufacturing firms from 2018 to 2023. Results show that t…

Nyo Me Htun, Toshiaki Owari, Satoshi Suzuki +11

This study develops a multi-sensor machine learning framework integrating UAV multispectral imagery and LiDAR data to estimate living biomass carbon stocks in managed forests in Hokkaido, Japan. XGBoost achieved the highest accuracy (R2=0.8…

M. Kim, J. Yoo

This study re-examines the conflicting findings on ESG and tax avoidance, attributing them to methodological issues: measurement differences, ESG index heterogeneity, and endogeneity. Using random forest and double machine learning, it show…

中尾 悠利子 中園 宏幸 石野 亜耶

This survey explores how companies utilize AI support tools when responding to ESG/sustainability questionnaires (e.g., CDP, EcoVadis), clarifying current practices and challenges. It also examines the benefits of AI adoption and future pro…

(著者不明)

This paper proposes a method to evaluate residential energy performance using feature importance analysis based on HEMS (Home Energy Management System) data. By analyzing energy consumption patterns, it identifies effective energy-saving me…

Kokubu, Hiroyuki

A quarterly snapshot of GX disclosure metrics machine-extracted from integrated reports of TSE Prime-listed companies using AI. Covers Scope 1/2/3, SBT, TCFD, CDP, renewable ratio, internal carbon price, and purchased carbon credits. This v…

(著者不明)

This paper proposes a method to construct and manage ESG factors using news text data. It explores the use of natural language processing to extract ESG-related information for investment decisions.

(著者不明)

This paper proposes an efficient method for extracting ESG information from corporate websites using machine learning. It reduces cost and time compared to manual collection. The method leverages natural language processing and text classif…

(著者不明)

This paper applies statistical causal inference to analyze the causal effect of ESG evaluation on corporate value. It examines whether improvements in ESG scores truly enhance firm value, assessing the effectiveness of ESG investing.

(著者不明)

Proposes and validates ESG evaluation using large language models. Automatically computes ESG scores from corporate disclosures and news, comparing efficiency and accuracy with traditional methods. Contributes to automation and sophisticati…

(著者不明)

This paper proposes a method to automatically extract ESG-related information from integrated reports using large language models (LLMs). It enables efficient analysis of corporate disclosure data for ESG scoring and evaluation. The approac…

(著者不明)

This paper proposes a method for automatically extracting ESG-related information from integrated reports. It leverages natural language processing and machine learning to efficiently collect and analyze corporate disclosure data, supportin…

(著者不明)

This paper proposes an automatic evaluation method for integrated reports that incorporates interpretability. Using AI to analyze report content, it enhances transparency of assessment, aiming to improve the quality of corporate ESG disclos…