A5103061115- Advanced Causal Inference Techniques
- Privacy-Preserving Technologies in Data
- Statistical Methods in Clinical Trials
- Imbalanced Data Classification Techniques
- Statistical Methods and Bayesian Inference
- Machine Learning and Data Classification
- Credit Risk and Financial Regulations
- Health Systems, Economic Evaluations, Quality of Life
- Biomedical Text Mining and Ontologies
- Financial Distress and Bankruptcy Prediction
- Network Security and Intrusion Detection
- Topic Modeling
University of Tsukuba
2023-2025
Anomaly detection is crucial in financial auditing and effective often requires obtaining large volumes of data from multiple organizations. However, confidentiality concerns hinder sharing among audit firms. Although the federated learning (FL)-based approach, FedAvg, has been proposed to address this challenge, its use mutiple communication rounds increases overhead, limiting practicality. In study, we propose a novel framework employing Data Collaboration (DC) analysis -- non-model...
Observational studies enable causal inferences when randomized controlled trials (RCTs) are not feasible. However, integrating sensitive medical data across multiple institutions introduces significant privacy challenges. The collaboration quasi-experiment (DC-QE) framework addresses these concerns by sharing "intermediate representations"—dimensionality-reduced derived from raw data—instead of the data. Although DC-QE can estimate treatment effects, its application to remains unexplored....
ABSTRACT In recent years, research studies have been conducted on analyzing journal‐entry data using advanced visualization techniques and machine learning models. However, because of their highly confidential nature, these are not disclosed externally, which can limit business opportunities to analyze the rich organizational information they contain. To address problems, this study utilized a variational autoencoder generate synthetic with statistical properties similar those actual data....
In recent years, the development of technologies for causal inference with privacy preservation distributed data has gained considerable attention. Many existing methods focus on resolving lack subjects (samples) and can only reduce random errors in estimating treatment effects. this study, we propose a collaboration quasi-experiment (DC-QE) that resolves both covariates, reducing biases estimation. Our method involves constructing dimensionality-reduced intermediate representations from...
Estimation of conditional average treatment effects (CATEs) is an important topic in various fields such as medical and social sciences. CATEs can be estimated with high accuracy if distributed data across multiple parties centralized. However, it difficult to aggregate they contain privacy information. To address this issue, we proposed collaboration double machine learning (DC-DML), a method that estimate CATE models preservation data, evaluated the through numerical experiments. Our...
In recent years, the development of technologies for causal inference with privacy preservation distributed data has gained considerable attention. Many existing methods focus on resolving lack subjects (samples) and can only reduce random errors in estimating treatment effects. this study, we propose a collaboration quasi-experiment (DC-QE) that resolves both covariates, reducing biases estimation. Our method involves constructing dimensionality-reduced intermediate representations from...