Kaito Takano, Masanori Hirano, Kei Nakagawa, "Modeling Hawkish-Dovish Latent Beliefs in Multi-agent Debate-Based LLMs for Monetary Policy Decision Classification," The 26th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2025), pp.488-505, Modena, Italy, Dec. 16th, 2025. doi.org/10.1007/978-3-032-13562-9_38
Masanori Hirano, "Building LLM-Based Artificial Market Simulations: Can LLMs Function as Agents in Multi-agent Simulations for Finance?," The 26th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2025), pp.56-71, Modena, Italy, Dec. 16th, 2025. doi.org/10.1007/978-3-032-13562-9_5
Misa Sato, Masanori Hirano, Kentaro Imajo, Mitsuo Yoshida, "Measuring Technology Commercialization Using Corporate Disclosures and Observing Temporal Patterns," 29th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2025) Procedia Computer Science, pp.2503-2512, Osaka, Japan, Sep. 11th, 2025. doi.org/10.1016/j.procs.2025.09.372 Published as a Journal article
Ryoya Yoshida, Masanori Hirano, Kentaro Imajo, "Conditional Diffusion Model with Volatility Estimation for Financial Time-Series Generation," 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF 2025) in 18th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2025), pp.780-787, Kitakyushu, Fukuoka, Japan, July 17th, 2025. doi.org/10.1109/IIAI-AAI67470.2025.00143 Accept rate (Full paper): 111 / 453 = 24.5%
Masanori Hirano, Kentaro Imajo, "The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging," 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF 2025) in 18th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2025), pp.772-779, Kitakyushu, Fukuoka, Japan, July 14th, 2025. doi.org/10.1109/IIAI-AAI67470.2025.00142, arXiv:2409.19854, ssrn.com/abstract=4971271 Accept rate (Full paper): 111 / 453 = 24.5%
Masanori Hirano, Kentaro Imajo, "pfmt-bench-fin-ja: Preferred Multi-turn Benchmark for Finance in Japanese," 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF 2025) in 18th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2025), pp.806-809, Kitakyushu, Fukuoka, Japan, July 14th, 2025. doi.org/10.1109/IIAI-AAI67470.2025.00147 Accept rate (Full paper): 111 / 453 = 24.5%, Competitive paper award!
Xinghong Fu, Masanori Hirano, Kentaro Imajo, "Financial Fine-tuning a Large Time Series Model," IEEE Symposium on CI for Financial Engineering and Economics (IEEE CiFer), Trondheim, Norway, Mar. 19th, 2025. doi.org/10.1109/CiFer64978.2025.10975735, arXiv:2412.09880
Rushikesh Handal, Matoya Kazuki, Yunzhuo Wang, Masanori Hirano, "KANOP: A Data-Efficient Option Pricing Model using Kolmogorov-Arnold Networks," IEEE Symposium on CI for Financial Engineering and Economics (IEEE CiFer), Trondheim, Norway, Mar. 18th, 2025. doi.org/10.1109/CiFer64978.2025.10975732, arXiv:2410.00419 Best Paper Nominated
2024
Kei Nakagawa, Masanori Hirano, Yugo Fujimoto, "Evaluating Company-specific Biases in Financial Sentiment Analysis using Large Language Models," 2024 IEEE International Conference on Big Data (IEEE BigData 2024), pp.6614-6623, Washington DC, USA, Dec. 16th, 2024. doi.org/10.1109/BigData62323.2024.10826008, arXiv:2411.00420
Kota Tanabe, Masanori Hirano, Kazuki Matoya, Kentaro Imajo, Hiroki Sakaji, Itsuki Noda, "Enhancing Financial Domain Adaptation of Language Models via Model Augmentation," 2024 IEEE International Conference on Big Data (IEEE BigData 2024), pp.6661-6669, Washington DC, USA, Dec. 16th, 2024. doi.org/10.1109/BigData62323.2024.10825292, arXiv:2411.09249
Kei Nakagawa, Masanori Hirano, Kentaro Minami, Takanobu Mizuta, "A Multi-agent Market Model Can Explain the Impact of AI Traders in Financial Markets -- A New Microfoundations of GARCH model," The 25th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2024), pp.97-113, Kyoto, Japan, Nov. 18th, 2024. doi.org/10.1007/978-3-031-77367-9_9, arXiv:2409.12516
Masanori Hirano, "Experimental Analysis of Deep Hedging Using Artificial Market Simulations for Underlying Assets Simulators," IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), Hoboken, NJ, USA, Oct. 22nd, 2024. doi.org/10.1109/CIFEr62890.2024.10772803, arXiv:2404.09462
Rawin Assabumrungrat, Kentaro Minami, Masanori Hirano, "Error Analysis of Option Pricing via Deep PDE Solvers: Empirical Study," 15th International Conference on Smart Computing and Artificial Intelligence (SCAI 2024) in 16th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2024), pp.329-336, Takamatsu, Kagawa, Japan, July 7th, 2024. doi.org/10.1109/IIAI-AAI63651.2024.00068, arXiv:2311.07231, ssrn.com/abstract=4630864
Masanori Hirano, Kentaro Imajo, "Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training," 15th International Conference on Smart Computing and Artificial Intelligence (SCAI 2024) in 16th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2024), pp.273-279, Takamatsu, Kagawa, Japan, July 6th, 2024. doi.org/10.1109/IIAI-AAI63651.2024.00059, arXiv:2404.10555, ssrn.com/abstract=4796245 Accept rate (Full paper): 87 / 293 = 29.7%, Honorable mention award!
Masanori Hirano, "Construction of a Japanese Financial Benchmark for Large Language Models," Joint Workshop of the 7th Financial Technology and Natural Language Processing (FinNLP), the 5th Knowledge Discovery from Unstructured Data in Financial Services (KDF), and The 4th Workshop on Economics and Natural Language Processing (ECONLP) in conjunction with LREC-COLING-2024, pp.1-9, Torino, Italy, May 20th, 2024. doi.org/aclanthology.org/2024.finnlp-1.1, arXiv:2403.15062, ssrn.com/abstract=4769124
2023
Masanori Hirano, Kentaro Minami, Kentaro Imajo, "Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling," 4th ACM International Conference on AI in Finance (ICAIF '23), pp.19-26, Brooklyn, NY, USA, Nov. 27th, 2023. doi.org/10.1145/3604237.3626846, arXiv:2307.13217, ssrn.com/abstract=4520273
Masanori Hirano, Kentaro Imajo, Kentaro Minami, Takuya Shimada, "Efficient Learning of Nested Deep Hedging using Multiple Options," 13th International Conference on Smart Computing and Artificial Intelligence (SCAI 2023) in 14th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2023), pp.514-521, Koriyama, Fukushima, Japan, July 9th, 2023. doi.org/10.1109/IIAI-AAI59060.2023.00104, arXiv:2305.12264, ssrn.com/abstract=4454377
2022
Yugo Fujimoto, Kei Nakagawa, Kentaro Imajo, Kentaro Minami, "Uncertainty Aware Trader-Company Method: Interpretable Stock Price Prediction Capturing Uncertainty," 2022 IEEE International Conference on Big Data (IEEE BigData 2022), pp.1238-1245, Osaka, Japan, Dec. 17th, 2022. doi.org/10.1109/BigData55660.2022.10021096
2021
Kentaro Imajo, Kentaro Minami, Katsuya Ito, Kei Nakagawa, "Deep Portfolio Optimization via Distributional Prediction of Residual Factors," The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), pp.213-222, Online, May 18th, 2021. doi.org/10.1609/aaai.v35i1.16095, arXiv:2012.07245
Katsuya Ito, Kentaro Minami, Kentaro Imajo, Kei Nakagawa, "Trader-Company Method: A Metaheuristic for Interpretable Stock Price Prediction," The 20th International Conference on Autonomous Agents and Multiagent Systems, pp.656-664, Online, May 3rd, 2021. doi.org/10.5555/3463952.3464032, arXiv:2012.10215
学術論文雑誌
2023
Shota Imaki, Kentaro Imajo, Katsuya Ito, Kentaro Minami, "No-Transaction Band Network: A Neural Network Architecture for Efficient Deep Hedging," The Journal of Financial Data Science, vol. 5, no. 2, pp.84-99, 2023. doi.org/10.3905/jfds.2023.1.125, arXiv:2103.01775
2022
Liu Ziyin, Katsuya Ito, Kentaro Imajo, Kentaro Minami, "Power laws and symmetries in a minimal model of financial market economy," Physical Review Research, vol. 4, no. 3, e033077, 2022. doi.org/10.1103/PhysRevResearch.4.033077, arXiv:2206.06802