行動モデリング

技術カテゴリ紹介

「行動」データはヒトの内面を豊かに、そして率直に物語っています。 様々なデバイスが普及しデジタル化されたヒトの行動を、機械学習・数理最適化・確率論などの計算論的アプローチによって扱う「Behavioral Data Science」と呼ばれる新しい研究領域が盛り上がりを見せています。 私たちはこの領域において、社会科学・人文科学分野におけるヒトの行動原理に関するインサイトと、観測可能な行動データをもとに、ヒトや集団の行動を数理モデル化する研究開発(私たちは、行動モデリングと呼んでいます)に取り組んでいます。

必ずしも合理的に判断しない(できない)ヒトの特性も含め、コンピュータによって行動を再現し予測することを目指します。

さらに、その行動モデルを活用しながら「ヒトと社会のWell-Being」に向け、ヒトの行動を自然な形でより良い方向に変容させるための方法論についても研究開発しています。

研究紹介

  1. 行動モデリング&行動変容技術

関連技術

  1. 社会集団モデリング技術

査読付き文献リスト

2023

論文

  1. Yasunori Akagi, Naoki Marumo, Hideaki Kim, Takeshi Kurashima, Hiroyuki Toda, "MAP inference algorithms without approximation for collective graphical models on path graphs via discrete difference of convex algorithm", Machine Learning, vol.112, no.1, pp.99-129, 2023.
  2. Yuya Hikima, Yasunori Akagi, Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki Toda, "Price and Time Proposal Optimization for Ride-Hailing Services Based on Individual Utilities", Transactions of the Japanese Society for Artificial Intelligence, vol.38, no.1, pp.CC-M13_1-12, 2023.
  3. 冨永登夢, 山本修平, 倉島健, 戸田浩之, "個人特性が経験サンプリング法における回答数の時間変化に及ぼす影響:StudentLifeデータセットを用いた実証分析", 情報処理学会論文誌, vol.64, no.2, pp.336-351, 2023.

国際会議

  1. Takeshi Kurashima, Tomoharu Iwata, Tomu Tominaga, Shuhei Yamamoto, Hiroyuki Toda, Kazuhisa Takemura, "Personal History Affects Reference Points: A Case Study of Codeforces", In Proceedings of the 17th International AAAI Conference on Web and Social Media (ICWSM 2023), in press, 2023.
  2. Yuya Hikima, Yasunori Akagi, Hideaki Kim, and Taichi Asami, "An Improved Approximation Algorithm for Wage Determination and Online Task Allocation in Crowd-sourcing", Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023), in press, 2023.

表彰

  1. Best Paper (Outstanding User Modeling):Takeshi Kurashima, Tomoharu Iwata, Tomu Tominaga, Shuhei Yamamoto, Hiroyuki Toda, Kazuhisa Takemura, "Personal History Affects Reference Points: A Case Study of Codeforces", In Proceedings of the 17th International AAAI Conference on Web and Social Media (ICWSM 2023), in press, 2023.

2022

論文

  1. Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Hiroyuki Toda, Takeshi Kurashima, Hisashi Kashima, "Context-aware spatio-temporal event prediction via convolutional Hawkes processes", Machine Learning, vol.111, no.8, pp.2929-2950, 2022.

国際会議

  1. Hideaki Kim, Taichi Asami, Hiroyuki Toda, "Fast Bayesian Estimation of Point Process Intensity as Function of Covariates", Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022.
  2. Maya Okawa, Tomoharu Iwata, "Predicting Opinion Dynamics via Sociologically-Informed Neural Networks", In Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2022), pp.1306-1316, 2022.
  3. Yuya Hikima, Yasunori Akagi, Marumo Naoki, and Hideaki Kim, "Online Matching with Controllable Rewards and Arrival Probabilities", Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022), pp.1825-1833, 2022.

表彰

  1. 第18回上林奨励賞:大川真耶, 富樫陸, 董于洋
  2. 第37回電気通信普及財団賞 テレコム学際研究賞 奨励賞:大川真耶, 岩田具治, 田中佑典, 戸田浩之, 倉島健, "Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes"
  3. LOISグッドプレゼンテーション賞:冨永登夢, 山本修平, "減量中の行動特性と減量後の体重維持の分析"

2021

論文

  1. Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima, Hiroyuki Toda, Naonori Ueda, Toshiyuki Tanaka, "Time-delayed collective flow diffusion models for inferring latent people flow from aggregated data at limited locations", Artificial Intelligence, vol.292, pp.103430, 2021.

国際会議

  1. Yasunori Akagi, Naoki Marumo, Hideaki Kim, Takeshi Kurashima, Hiroyuki Toda, "Non-approximate inference for collective graphical models on path graphs via discrete difference of convex algorithm", Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 2021.
  2. Hideaki Kim, "Fast Bayesian Inference for Gaussian Cox Processes via Path Integral Formulation", Advances in Neural Information Processing Systems 34 (NeurIPS 2021), spotlight, 2021.
  3. Yuya Hikima, Masahiro Kohjima, Yasunori Akagi, Takeshi Kurashima, and Hiroyuki Toda, "Price and Time Optimization for Utility-Aware Taxi Dispatching", In Proceedings of the 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2021), pp.370-381, 2021.
  4. Tomu Tominaga, Shuhei Yamamoto, Takeshi Kurashima, Hiroyuki Toda, "Effects of personal characteristics on temporal response patterns in ecological momentary assessments", In Proceedings of the 18th IFIP TC 13 International Conference on Human-Computer Interaction (INTERACT 2021), pp.3-22, 2021.
  5. Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Hiroyuki Toda, Takeshi Kurashima, Hisashi Kashima, "Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes", In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2021), pp.1276-1286, 2021.
  6. Yuya Hikima, Yasunori Akagi, Hideaki Kim, Masahiro Kohjima, Takeshi Kurashima, and Hiroyuki Toda, "Integrated Optimization of Bipartite Matching and Its Stochastic Behavior: New Formulation and Approximation Algorithm via Min-cost Flow Optimization", In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), pp.3796-3805, 2021.

2020

国際会議

  1. Masahiro Kohjima, Takeshi Kurashima, Hiroyuki Toda, "Learning with Labeled and Unlabeled Multi-Step Transition Data for Recovering Markov Chain from Incomplete Transition Data", In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020), pp.2412-2419, 2020.
  2. Shuhei Yamamoto, Takeshi Kurashima, and Hiroyuki Toda, "Identifying Near-Miss Traffic Incidents in Event Recorder Data", The 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2020), pp.717-728, 2020.
  3. Yasunori Akagi, Takuya Nishimura, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, "Exact and efficient inference for collective flow diffusion model via minimum convex cost flow algorithm", In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), pp.3163-3170, 2020.

表彰

  1. 情報処理学会2020年度(令和2年度)山下記念研究賞:引間友也
  2. 情報処理学会2020年度(令和2年度)山下記念研究賞:幸島匡宏
  3. DEIM2020最優秀論文賞:佐藤大祐, 松林達史, 福田匡人, 堤田恭太, 中山彰, 戸田浩之, "残差回帰による複合時空間予測手法"

2019

論文

  1. Jun Suzuki, Yoshihiko Suhara, Hiroyuki Toda, Kyosuke Nishida, "Personalized visited-poi assignment to individual raw GPS trajectories", ACM Transactions on Spatial Algorithms and Systems, vol.5, no.3, pp.1-28, 2019.
  2. Maya Okawa, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda, Tomohiro Yamada, "Marked Temporal Point Processes for Trip Demand Prediction in Bike Sharing Systems", IEICE TRANSACTIONS on Information and Systems, vol.102, no.9, pp.1635-1643, 2019.
  3. 松林達史, 清武寛, 幸島匡宏, 戸田浩之, 田中悠介, 六藤雄一, 塩原寿子, 宮本勝, 清水仁, 大塚琢馬, 岩田具治, 澤田宏, 納谷太, 上田修功, "人流における学習型誘導技術のデータ同化", 人工知能学会論文誌, vol.34, no.5, pp.1-11, 2019.
  4. 幸島匡宏, 清武寛, 松林達史, 塩原寿子, 戸田浩之, "打ち切りデータを用いた混合モデルのオンライン EM アルゴリズム", 電子情報通信学会論文誌D, vol.102, no.4, pp.277-288, 2019.

国際会議

  1. Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi, Hiroyuki Toda, "Spatially aggregated Gaussian processes with multivariate areal outputs", Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019.
  2. Hidetaka Ito, Kyota Tsutsumida, Tatsushi Matsubayashi, Takeshi Kurashima, Hiroyuki Toda, "Coordinated traffic signal control via bayesian optimization for hierarchical conditional spaces", 2019 Winter Simulation Conference (WSC 2019), pp.3645-3656, 2019.
  3. Masahiro Kohjima, Tatsushi Matsubayashi, Hiroyuki Toda, "Exemplar Based Mixture Models with Censored Data", In Proceedings of The Eleventh Asian Conference on Machine Learning (ACML 2019), pp.535-550, 2019.
  4. Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa, Hiroyuki Toda, "Predicting traffic accidents with event recorder data", In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility (PredictGIS 2019), pp.11-14, 2019.
  5. Masami Takahashi, Masahiro Kohjima, Takeshi Kurashima, Tatsushi Matsubayashi, Hiroyuki Toda, "Identifying self-changeable actions toward regulating rhythm of daily life", Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers (UbiComp/ISWC 2019), pp.218-221, 2019.
  6. Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, Naonori Ueda, "Deep mixture point processes: Spatio-temporal event prediction with rich contextual information", In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2019), pp.373-383, 2019.
  7. Masahiro Kohjima, Tatsushi Matsubayashi, Hiroyuki Toda, "Generalized interval valued nonnegative matrix factorization", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), pp.3412-3416, 2019.
  8. Daisuke Sato, Tatsushi Matsubayashi, Shoichi Nagano, Hiroyuki Toda, "People flow prediction by multi-agent simulator", 2019 IEEE International Conference on Big Data and Smart Computing (BigComp 2019), pp.1-4, 2019.
  9. Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa, Hiroyuki Toda, "Refining coarse-grained spatial data using auxiliary spatial data sets with various granularities", In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2019), pp.5091-5099, 2019.