景気の先行きを考える上で，製造業の生産活動の活況度合いをいち早く把握することは重要である．製造業が生産活動を行う際には電力が消費される点を踏まえ，本研究では，大手電力会社が公表する 5分ごとの電力需要データに着目することで，製造業の活動状況を高い速報性をもって推計するナウキャスティングモデルを構築した．具体的には，日中の電力需要の高頻度データに対して主成分分析を行うことで，電力消費の変動パターンを表す主成分ファクターを抽出し，それらを用いて，製造業の生産活動を推計する正則化回帰モデルを構築した．なお，製造業等の生産活動を表す公式統計としては，経済産業省が集計する鉱工業生産指数が挙げられるが，本提案手法に基づくと，同指数の公表よりも一カ月程度早い製造業活動の推計が可能となった．更に，本手法に基づく生産指数の推計結果は，同指数の公表前に集計された市場予想平均値と比較して，高い予測精度が実現できることを確認した．

In recent years, many researchers have studied stock trading using technical analysis. However, it is necessary to have deep knowledge to use such technical analysis and it is difficult to make a profit using such techniques. Therefore, we construct an evolutionary model to create a profitable investment strategy using technical indicators. We confirmed the effectiveness of our model using historical data of the stock market. We confirmed the effectiveness of our model using historical data of the stock market.

Recently, the Artificial Intelligence based Werewolf Project has been attracting attention. Because, it is important for human-like artificial intelligence research to construct an artificial intelligence for the Werewolf Game which requires abilities to bamboozle and detect a lie. Therefore we construct an artificial intelligence for deducing roles of players in the Werewolf Game using information about conversations among players.

Taking a questionnaire is effective way to model consumer awareness. However hearing a lot of questions is very hard from the point of view of answer accuracy and response rate. One way to solve this problem, we take partial questionnaires that differ among answers and merge some answers so as to contain all answers of questions in the original questionnaire. In this study, we propose a method that is merging the partial answers based on Probabilistic Latent Model. The experimental result shows that the proposed method can create virtual answer data which is similar to original answer data from the viewpoint of latent segments in answer data.

How can companies manage a digital transformation project in order to realize the demonstration experiments with a satisfactory result for everyone in the company? Discussion about digital transformation is more complex than discussion about previous ICT introductions because it is difficult to understand technologies such as AI and IoT, the quality of data. As an academic background, in the context of corporate information system introduction, especially in the context of digital transformation strategy, there are not many researches discussing the organizational activities from a micro-perspective. This research describes the decision-making process in the project from the perspective of Strategy as Practice regarding the introduction of the system applied AI touch rally system conducted by a certain company and AIST in 2019.

In the strategy of shopping complexs, it is important to know customers. In this resarch, we collected the action history of the event held in one of shopping complexs by using ID wristbands. We report the analysis results of the obtained data using PLSA and Bayesian network, and also consider application of this system.

In this paper, issues of data compliance with human behavior history are overviewed and viewpoints how to make clear them are shown in service business using technology with Internet of Things to excavate knowledge in personal data. Unlike laws and regulations, compliance is based on the consensus building between stakeholder mutually related and reasonable systematization is necessary for joint user toward shared data. In order to enables coexistence of utilizing data and protecting privacy of it, it is stated how criteria data is disclosed on requirements of consensus building by stakeholder.

研究開発などの知識生産活動を測定する上で，論文や特許のデータは重要であり，これまでにも様々な分析がなされてきた．ただし，過去においては大量データの分析手法が限られていたことから，引用関係を含む書誌情報の分析が多かった．また，論文については引用件数のTop10%程度までに絞り込んで分析されていたり，特許についても特定の分類やキーワードに紐付くものに絞り込んで分析されていたりするものが多かった．本試行では，分散表現やグラフインデックス，次元縮約などを用い，意昧内容の類似度ベースで大量の日米の特許と，著名な論文データベースに採録されている論文全体を一気に分析し，可視化した結果について述べる．その上で，提案手法を用いることで，マクロ・ミクロの両面から日米間での特許傾向の違いや，論文における位置づけなどの把握が容易に行えることを示す．

Each year, about 1.35 million people die as a result of traffic accidents in the world. It means almost 3,700 people are killed each day in traffic accidents. In Japan, Aichi Prefecture has the most fatalities by prefecture for 16 years since 2018. Public Organization of Aichi Prefecture has a goal "By 2020, reducing the annual number of traffic fatalities within 24 hours after an accident to no more than 155". This paper is in an early stage to reveal the cause of fatal traffic accidents in Aichi Prefecture. We attempt to get clues for decreasing fatalities and traffic accidents by analyzing traffic accident data that are collected by Aichi Prefectural Police. In addition, we aim to ultimately achieve a society with no traffic accidents in the world.