2026-03-06T15:38:52Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00232892 2025-01-19T10:17:14Z 1164:5305:11555:11556

Decoding Virtual Strategies: Deep Neural Network-driven Prediction of Player Movement via In-Game Location Data Decoding Virtual Strategies: Deep Neural Network-driven Prediction of Player Movement via In-Game Location Data Mhd, Irvan Franziska, Zimmer Ryosuke, Kobayashi Rie, Shigetomi Yamaguchi Mhd, Irvan Franziska, Zimmer Ryosuke, Kobayashi Rie, Shigetomi Yamaguchi In modern video game design, understanding player movement is pivotal for creating immersive gaming experiences. This research delves into the realm of predictive modeling by leveraging in-game location data and trajectory information. Our approach employs a Deep Neural Network (DNN) model, designed to unravel intricate patterns in player behavior. Our research focuses on mapping virtual strategies through the DNN's predictive capabilities, shedding light on the complex dynamics inherent in player trajectories. By harnessing in-game location data, we demonstrate the effectiveness of our model in capturing player dynamics. This study not only contributes to the field of gaming analytics but also highlights the potential of deep learning in deciphering and predicting player behavior. The findings offer valuable insights into the cognitive aspects of gameplay, paving the way for more responsive and engaging virtual environments. In modern video game design, understanding player movement is pivotal for creating immersive gaming experiences. This research delves into the realm of predictive modeling by leveraging in-game location data and trajectory information. Our approach employs a Deep Neural Network (DNN) model, designed to unravel intricate patterns in player behavior. Our research focuses on mapping virtual strategies through the DNN's predictive capabilities, shedding light on the complex dynamics inherent in player trajectories. By harnessing in-game location data, we demonstrate the effectiveness of our model in capturing player dynamics. This study not only contributes to the field of gaming analytics but also highlights the potential of deep learning in deciphering and predicting player behavior. The findings offer valuable insights into the cognitive aspects of gameplay, paving the way for more responsive and engaging virtual environments. 情報処理学会 2024-03-01 eng technical report https://ipsj.ixsq.nii.ac.jp/records/232892 2188-8736 AA11362144 研究報告ゲーム情報学（GI） 2024-GI-51 4 1 6 https://ipsj.ixsq.nii.ac.jp/record/232892/files/IPSJ-GI24051004.pdf application/pdf 1.5 MB 2026-03-01