Papers - Takahashi, Hiroshi

The Relationship Between the Characteristics of Company Executives and Their Companies Observed Through Facial Emotions and Text Analysis - Analysis of Nikkei 225 Firms -

SAISHO Atsutaka, SUGE Aiko, TAKAHASHI Hiroshi

JSAI Technical Report, Type 2 SIG (The Japanese Society for Artificial Intelligence)  2019 ( BI-011 ) 09 2019.01

　View Summary

<p>Company executives play an important role in corporate activities. In this research, we focus onthe characteristics of the top executive, who make the important decisions. We attempt to measure the facialemotional score of these executives from the photographs published on their firm's annual report. Inaddition, we create a narcissism index from the number of times these executives appear on their reports.Finally, we analyze how these emotional scores or narcissism indexes relate with their company'sperformance and behavior.</p>

• Access to Document (DOI)
• CiNii Research

Rental price analysis with an agent-based simulation? A case study of Shimokitazawa?

ZHANG Zhenkun, OTA Akira, SUGE Aiko, KANEDA Toshiyuki, TAKAHASHI Hiroshi

JSAI Technical Report, Type 2 SIG (The Japanese Society for Artificial Intelligence)  2019 ( BI-011 ) 02 2019.01

　View Summary

<p>Pedestrian traffic is reported to be a component of rental price. However, rental price analysiswith an agent-based simulation has not been conducted. In this article, shop rental around Shimokitazawastation is analyzed by conducting an agent-based simulation. The result shows that there is a positivecorrelation between shop rental and the number of footprint, which is the output of the agent-basedsimulation.</p>

• Access to Document (DOI)
• CiNii Research

Analysis of the relationship between news reports and commodity futures prices; through the examples of corn, soy bean and wheat

ITO Takema, SUGE Aiko, TAKAHASHI Hiroshi

JSAI Technical Report, Type 2 SIG (The Japanese Society for Artificial Intelligence)  2019 ( BI-011 ) 12 2019.01

　View Summary

<p>News reports can be one of the main factors that influence commodity futures prices. In thispaper, we conducted analysis on the relationship between news reports and commodity futures. Firstly, wedeveloped a fluctuation index of the futures prices on a daily basis, through event study. Next wevectorized the news report data and analyzed their relationships with the futures prices. In this analysis,we used the multivariate autoregressive model to examine the possibilities of forecasting commodityfutures prices by using the news report index. We also analyzed the relationship between the news indexdeveloped in this paper and the stock prices of enterprises related with commodity futures.</p>

• Access to Document (DOI)
• CiNii Research

Estimating the synergy effect and its relevance to corporate behavior -Analysis of Japanese companies-

MATSUMOTO Yusuke, SUGE Aiko, TAKAHASHI Hiroshi

JSAI Technical Report, Type 2 SIG (The Japanese Society for Artificial Intelligence)  2019 ( BI-011 ) 07 2019.01

　View Summary

<p>To keep up with rapid changes in the business environment, Japanese companies have requiredto conduct business transformation in recent years. In this paper, we classified companies by using FuzzyC Means, and estimated the synergy effect of multi-business companies based on that classification. Inaddition to this, we investigated the corporate behavior, especially when making a decision to sell a business,focusing on divestment through M&A.</p>

• Access to Document (DOI)
• CiNii Research

Debriefing Framework for Business Games Using Simulation Analysis

Kikuchi T., Tanaka Y., Kunigami M., Yamada T., Takahashi H., Terano T.

Communications in Computer and Information Science (Communications in Computer and Information Science)  999   64 - 76 2019

Joint Work,  ISSN  9789811369353

　View Summary

© 2019, Springer Nature Singapore Pte Ltd. Researchers are aware of the importance of debriefing in gaming. However, there has been little progress in establishing a methodology for evaluating player behavior. Therefore, we propose a framework to support the evaluation of player behavior in business games using computers. Specifically, we introduce a simulation analysis methodology that involves the following steps: (1) constructing an agent-based model based on the subject of the business game and categorizing simulation-logs; and (2) mapping logs of player behavior onto typed results. In this way, the positioning of the player in the overall simulation scenario is visualized, and a range of possible results is presented. Both players and facilitators receive information that is useful for debriefing.

• Access to Document (DOI)

Customer Classification Through Time Series Order Data Analysis in High-end Barbecue Beef

SHIN Kiyotaka, QU Xueyin, SUGE Aiko, YAMASHITA Yasuo, TAKAHASHI Hiroshi

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  2019 ( 0 ) 2H1J202 - 2H1J202 2019

Joint Work

　View Summary

<p>The purpose of this research aimed at the improvement of management skills using POS data of restaurant service industry, focusing on customer configuration which is the most important factor in restaurant management. In addition to customer configuration, this analysis takes the time series order data into account which leads to the possibility of better classification. By obtaining more sophisticated knowledge of customer configuration, more value-added services and more efficient management will be expected.</p>

• Access to Document (DOI)

Examination of Behavioral Divergence of Investors against the News through High-Frequency Trading Analyses

Suge Aiko, Takahashi Hiroshi

Abstracts of Annual Conference of Japan Society for Management Information (THE JAPAN SOCIETY FOR MANAGEMENT INFORMATION (JASMIN))  201906 ( 0 ) 273 - 275 2019

Joint Work

　View Summary

<p>While general investment behaviors on the news are comprehended through market movements, individual investor's actions are rarely observed. This research focused on stock trading on the October 31, 2014 and empirically analyzed investor behavior against the released news on that day. Records that we analyzed reflected High-Frequency Trading (HFT), so that we can target short-term investor behavior. As a result, divergence between principal and intermediary (agent) investment were determined as well as individual investment behavior.</p>

• Access to Document (DOI)
• CiNii Research

Estimating Risk Factors with High Frequency Data through Principle Component Analysis

NASU Kentaro, YAMASHITA Yasuo, TAKAHASHI Hiroshi

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  2019 ( 0 ) 4Rin129 - 4Rin129 2019

Joint Work

　View Summary

<p>This paper proposes a unique estimation method of Jump Factor with high frequency data. Our method employs bi-power variation technique and principle component analysis. Proposed method is unique and exhibits a new measure for financial risk. In this study, we calculated four Jump Factors in United States and Germany and integrated them through principle component analysis. In addition, we could confirm the influence of Jump Factors on financial markets by using the proposed method.</p>

• Access to Document (DOI)
• CiNii Research

Explaining Log Data of Agent-Simulation Results with Managerial Decision-Making Description Model

Kikuchi Takamasa, Kunigami Masaaki, Takahashi Hiroshi, Toriyama Masahiro, Terano Takao

STUDIES IN SIMULATION AND GAMING (Japan Association of Simulation And Gaming)  29 ( 1 ) 36 - 48 2019

Joint Work,  ISSN  1345-1499

　View Summary

<p>To understand social and organizational phenomena and connect them to the design of a system, an approach to implement an agent-based model and a case study have been proposed. In this study, we propose a methodology that extends the approach to the following two points i.e., 1) analyzing not the micro-level simulation logs themselves but the patterns of micro-level logs and 2) describing the interpretations of the business cases formally by using an abstract description language. To confirm the feasibility of our proposed methodology, an agent-based model that expresses the decision-making process concerning external environment recognition of an organization was established. For systematically analyzing, we generated the simulation logs from the model via many trials by using the random search method comprehensively. Furthermore, we adopt the Managerial Decision-making Description Model as an abstract description language and wrote down two actual business cases with similar themes; a top-down-type decision-making case and a bottom-up-type decision-making case. Moreover, the comparisons of the business cases with similar themes were performed. Hence, this new methodology enables 1) to comprehensively understand the results and processes of the simulation and to discuss the occurrence frequency and 2) to express the simulation logs and actual business cases in the same format by case description language to compare them.</p>

• Access to Document (DOI)

Analysis of the Effect of Financial Regulation on Market Collapse Process in Financial Network

Kikuchi T., Kunigami M., Yamada T., Takahashi H., Terano T.

Smart Innovation, Systems and Technologies (Smart Innovation, Systems and Technologies)  148   249 - 262 2019

Joint Work,  ISSN  9789811386787

　View Summary

© 2020, Springer Nature Singapore Pte Ltd. This study focuses on the influence of the market collapse process of financial institutions under financial regulation on financial systems. For this purpose, the authors expand simulation models of systemic risks expressing financial regulation and the financing behavior of financial institutions. Using this model, scenario analysis is performed how the collapse process in the financial system changes due to the balance sheet constraint. Our numerical experiment shows that (1) as the amount of marketable assets is increased, the type of failed process with high occurrence changes, and (2) when there is a balance sheet restriction, the frequency of chain collapse is suppressed.

• Access to Document (DOI)

経営意思決定表現モデルを用いたビジネスケースとエージェントモデルの意思決定過程の形式的記述

菊地剛正，國上真章，高橋大志，鳥山正博，寺野 隆雄

情報処理学会論文誌 60 ( 10 ) 1704 - 1718 2019

Research paper (scientific journal), Joint Work, Accepted,  ISSN  1882-7764

　View Summary

組織研究では，ビジネスケースや組織シミュレーションを用いるアプローチがある．自然言語により記述されたビジネスケースや多数のシミュレーション・ログには，解釈や認識の多義性が生じうる．そのため，ケースやモデルの作成者や分析者の間で，当該多義性を低減することが重要となる．なぜならば，双方の接近法の間での議論やコミュニケーションを活発化し，効率的な事例比較を行うために不可欠だからである．本稿では，ビジネスケースに係る抽象的記述言語を用いることで，実在のビジネスケースと組織シミュレーションのシミュレーション・ログにつき，それぞれの意思決定プロセスを可視化し，形式的に記述・表現しうることを例示する．
In organization research, there are approaches using business cases and organizational simulations. Business cases described in natural language and numerous simulation logs may have ambiguity in interpretation and recognition. Therefore, it is important for creators and analysts of cases and models to reduce such ambiguity. This is because activating discussions and communication between the two approaches, which is indispensable for efficient case comparisons. In this paper, we demonstrate that each decision making process are able to be visualized and formally described for actual business cases and simulation logs of organizational simulation by using an abstract description language for business cases.

ビジネスケース記述言語を用いたエージェントシミュレーションログの分析手法

菊地剛正，國上真章，高橋大志，鳥山正博，寺野 隆雄

シミュレーション＆ゲーミング  2019

Research paper (scientific journal), Joint Work, Accepted

自然言語処理による景況感ニュース指数の構築とボラティリティ予測への応用

五島圭一, 高橋大志, 山田哲也

金融研究 (日本銀行金融研究所)  38 ( 3 ) 1 - 41 2019

Research paper (scientific journal), Joint Work, Accepted,  ISSN  0287-5306

Agent-based Simulation of Financial Institution’s Investment Strategy under Easing Monetary Policy on Operative Collapses

Takamasa Kikuchi, Masaaki Kunigami, Takashi Yamada, Hiroshi Takahashi, Takao Terano

Journal of Advanced Computational Intelligence and Intelligent Informatics 22 ( 7 ) 1026 - 1036 2019

Joint Work

Capturing Corporate Attributes in a New Perspective through Fuzzy Clustering

Yusuke Matsumoto, Aiko Suge, Hiroshi Takahashi

In: Kojima K., Sakamoto M., Mineshima K., Satoh K. (eds) New Frontiers in Artificial Intelligence, Lecture Notes in Computer Science (Springer)  11717 LNAI   19 - 23 2019

Research paper (international conference proceedings), Joint Work, Accepted,  ISSN  9783030316044

　View Summary

© 2019, Springer Nature Switzerland AG. Although industrial classification plays an important role in various contexts, it is rarely questioned. However, as diversification and business transformation are ongoing, it is becoming difficult to recognize company’s real business. Therefore, there is not enough to allocate one type of business class to express the situation of the company, and a new type of industrial classification system is required. Through the analysis, we construct a new industrial classification system with Fuzzy C Means (FCM). This study also confirms the validity of proposed method through composite variance and absolute prediction error (APE). As the result, we present that there is a possibility that we are able to represent one company with overlapping industry, so to speak, assign one company more than two industries.

• Access to Document (DOI)

Improvement of classification accuracy by large-scale language generation model:Classification analysis of TOPIX Core30 companies through LSTM

Nishi Yoshihiro, Suge Aiko, Takahashi Hiroshi

Proceedings of the Conference of Transdisciplinary Federation of Science and Technology (Transdisciplinary Federation of Science and Technology)  2019 ( 0 ) B - 5-6 2019

Joint Work

　View Summary

News has great impacts on asset prices in the financial markets. Many attempts have been reportedto ascertain how news influences stock prices. However, the limitations in the number of available data sets usuallybecome the hurdle for the model accuracy. In this study, Reuter's news texts were classified based on eachreturn through LSTM models. As a result of the analysis, we found the prediction accuracy could be improvedby using texts generated by GPT-2. Further examination of the classification model will be planned.

• Access to Document (DOI)

日本の労働分配率の低下を防ぐための政策提言の可能性について

高橋 大志

 2019

Single Work

大規模言語生成モデルによる分類精度の向上 LSTM による TOPIX Core30 企業の分類分析

横幹連合コンファレンス予稿集 第 10 回横幹連合コンファレンス  2019

ニュースによるナレッジグラフの構築

高橋 大志

 2019

Single Work

ニュースおよび高頻度データを用いたディープラーニングによる株式変動の分析

高橋 大志

 2019

Single Work