Katsuya Ito (伊藤克哉)

Founder & CEO @ INDX
Organising and analysing unstructured data from Japanese companies.
E-mail: katsuya1ito at gmail.com
Location : Minato-ku Tokyo
Areas of Interest: Machine Learning, Deep Learning, Unstructured Data Analysis, Business Development, Finance, Mathematics, Entrepreneurship.


Self-Introduction

Born in 1994 in Kobe/Akashi, I graduated from the University of Tokyo with a degree in Mathematics and a Master’s in Economics. After starting my career in 2019, I worked as an engineer at PFN, an unicorn AI startup, and gained experience in new business development utilizing AI at Mitsui & Co., Ltd., a major trading company. Recently, I founded INDX, a company dedicated to organising and analysing unstructured data from Japanese companies to unlock new value and insights.

#MachineLearning #DataAnalysis #Entrepreneurship #Math #Economics #UTokyo #PFN #INDX

For more personal and informal insights, here.

Job Experience

Start End Company name and Title
April 2025 - INDX Co., Ltd. Founder & CEO
April 2021 March 2025 Mitsui & Co., Ltd. Project Manager
May 2019 March 2021 Preferred Networks Engineer

Education

Start End School
April 2013 March 2017 University of Tokyo, Department of Mathematics
April 2017 March 2019 University of Tokyo, Graduate School of Economics

Qualifications

Year Month Qualifications
2009 December Applied Information Technology Engineer Examination
2013 December Chinese Standard Exam HSK 4th Level
2021 May TOEIC L&R Score 955
2023 September TOEFL iBT Score 93

Selected Papers

My Role Title Publication Year
Co- Author　 Power Laws and Symmetries in a Minimal Model of Financial Market Economy Physical Review Research 2022
Co-author　 No-Transaction Band Network: A Neural Network Architecture for Efficient Deep Hedging The Journal of Financial Data Science 2021
Co-author　 Deep Portfolio Optimization via Distributional Prediction of Residual Factors AAAI 2021 2021
Co- Author　 Taming Tail Risk: Regularized Multiple β Worst-Case CVaR Portfolio Symmetry 2021
Lead Author　 Trader-Company Method: A Metaheuristic for Interpretable Stock Price Prediction AAMAS 2021 2020
Lead Author　 NAPLES;Mining the lead-lag Relationship from Non-synchronous and High-frequency Data arXiv preprint 2020
Lead Author　 Direct Estimation of Lead–Lag Relationships Using Multinomial Dynamic Time Warping Asia-Pacific Financial Markets 2020
Co-author　 Myocardial infarction in type 2 diabetes using sodium–glucose co-transporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors or glucagon-like peptide-1 receptor agonists: proportional hazards analysis by deep neural network based machine learning Current Medical Research and Opinion 2020
Lead Author　 Structural Change Point Detection Using A Large Random Matrix and Sparse Modeling. EDBT/ICDT Workshops 2019

Selected Papers (Japanese)

My Role Title Publication Year
Lead Author LLM-Traders: 大規模言語モデルを用いた金融時系列予測 人工知能学会全国大会論文集 第 38 回 (2024), 3Xin2-83 2024
Lead Author ABCD-Forecast: 機密金融時系列予測のためのデータ拡張バギング手法 人工知能学会全国大会論文集 第 37 回 (2023) 2023
Lead Author Trader-Company 法: メタヒューリスティクスを用いた株価予測 金融機関を模したモデルによる時系列予測 人工知能学会全国大会論文集 第 34 回 (2020) 2020
Co-author 株価の残差リターンに注目した深層学習ポートフォリオ最適化 人工知能学会全国大会論文集 第 34 回 (2020) 2020
Lead Author 非同期時系列の Lead-Lag 効果推定のための新しい推定量 人工知能学会第二種研究会資料 2021 2021
Co-author 効率的な Deep Hedging のためのニューラルネットワーク構造 人工知能学会第二種研究会資料 2021 2021

Professional Work Records

My Role Title Publication Year
Project Lead How Confidential Computing is Changing the World Confidential Computing Summit (Presenter NVIDIA) 2024
Project Lead 三井物産、暗号化したままデータ解析　AI活用【イブニングスクープ】 日経新聞 2022
Project Lead EAGLYS・三井物産で秘密計算PoCを実施 EAGLYS　プレスリリース 2022
Lead Enginner 野村アセット、プリファードと組みAI運用投信 日経新聞 2021
Lead Enginner Preferred Networksとの共同研究を活用したパイロットファンドの設定について 野村ホールディングス株式会社　プレスリリース 2021
Lead Enginner Preferred Networksとの共同研究論文が、人工知能分野の国際学会AAAIおよびAAMASで採択 野村ホールディングス株式会社プレスリリース 2020

Selected Blog Posts and Talks

 

 

*Last updated on 7 06, 2025.