Curriculum Vitaes

Yusuke Ikuta

  (生田 祐介)

Profile Information

Affiliation
Associate professor, Faculty of Business Management, Department of Commercial Science, Osaka Sangyo University
Degree
博士(経済学)(神戸大学)

Researcher number
70801489
J-GLOBAL ID
201901017686184744
researchmap Member ID
7000028794

External link

Papers

 11
  • 安達晃史, 生田祐介, 永田靖, 松本宗谷
    大阪産業大学経営論集, 24(2) 15-36, Mar, 2023  
  • Yusuke Ikuta, Takashi Yanagawa
    International Journal of Economic Policy Studies, 17(1) 307-330, Dec 28, 2022  Peer-reviewedLead authorCorresponding author
  • Kazuhiro Seki, Yusuke Ikuta, Yoichi Matsubayashi
    INFORMATION PROCESSING & MANAGEMENT, 59(2), Mar, 2022  Peer-reviewed
    This paper presents an approach to measuring business sentiment based on textual data. Business sentiment has been measured by traditional surveys, which are costly and time-consuming to conduct. To address the issues, we take advantage of daily newspaper articles and adopt a self-attention-based model to define a business sentiment index, named S-APIR, where outlier detection models are investigated to properly handle various genres of news articles. Moreover, we propose a simple approach to temporally analyzing how much any given event contributed to the predicted business sentiment index. To demonstrate the validity of the proposed approach, an extensive analysis is carried out on 12 years' worth of newspaper articles. The analysis shows that the S-APIR index is strongly and positively correlated with established survey-based index (up to correlation coefficient r = 0.937) and that the outlier detection is effective especially for a general newspaper. Also, S-APIR is compared with a variety of economic indices, revealing the properties of S-APIR that it reflects the trend of the macroeconomy as well as the economic outlook and sentiment of economic agents. Moreover, to illustrate how S-APIR could benefit economists and policymakers, several events are analyzed with respect to their impacts on business sentiment over time.
  • Kazuhiro Seki
    Journal of Information Processing Society of Japan, 62(5) 1288-1297, May 1, 2021  Peer-reviewed
    Business sentiment indices released regularly by the government or the central bank play a crucial role in decision making for governmental/monetary policies, industrial production planning, and so on. However, these indices rely on traditional surveys, which are costly and time-consuming to conduct. This paper propose an approach to predicting an inexpensive and timely business sentiment index reusing daily newspaper articles. We adopt the Bidirectional Encoder Representation from Transformers (BERT) to predict a business sentiment score of a given text and aggregate the scores to define an index, named S-APIR. Also, a one-class support vector machine is applied to filter out texts irrelevant to business and economy. Moreover, we propose a simple yet useful approach to temporally analyzing how much any given factor influenced the predicted business sentiment. The validity and utility of the proposed approach are demonstrated through our experiments on 12-years-worth of newspaper articles.
  • Yusuke Ikuta, Kazuhiro Seki, Yoichi Matsubayashi
    APIR Discussion Paper Series No.48, Feb, 2021  Lead authorCorresponding author
  • Yusuke Kinoshita, Yoichi Matsubayashi
    APIR Discussion Paper Series No.47, Nov, 2020  Lead authorCorresponding author
  • Kazuhiro Seki, Yusuke Ikuta
    Proceedings of the 24th European Conference on Advances in Databases and Information Systems, Aug, 2020  Peer-reviewed
    This paper describes our work on developing a new business sentiment index using daily newspaper articles. We adopt a recurrent neural network (RNN) with Gated Recurrent Units to predict the business sentiment of a given text. An RNN is initially trained on Economy Watchers Survey and then fine-tuned on news texts for domain adaptation. Also, a one-class support vector machine is applied to filter out texts deemed irrelevant to business sentiment. Moreover, we propose a simple approach to temporally analyzing how much and when any given factor influences the predicted business sentiment. The validity and utility of the proposed approaches are empirically demonstrated through a series of experiments on Nikkei Newspaper articles published from 2013 to 2018.
  • 関和広, 生田祐介, 松林洋一
    第24回人工知能学会金融情報学研究会, Mar, 2020  Peer-reviewed
  • Kazuhiro Seki, Yusuke Ikuta
    2019 IEEE SECOND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND KNOWLEDGE ENGINEERING (AIKE), 55-56, 2019  Peer-reviewed
    Business sentiment indices play a crucial role in government's policy decisions, production planning in industries, and individual/institutional investment decisions. However, such indices require large-scale surveys, which are costly and laborious to conduct. As an alternative, this paper reports our ongoing work on estimating business sentiment based on abundant, ordinary newspaper articles. Our proposed framework is composed of a recurrent neural network for regression, a one-class support vector machine to filter out topically irrelevant articles, and fine-tuning for domain adaptation. The effectiveness of the framework is empirically demonstrated by experiments on Nikkei newspaper.
  • Yusuke Ikuta
    International Journal of Economic Policy Studies, 12(1) 1-22, Jan 1, 2017  Peer-reviewed
  • Yusuke Ikuta
    International Journal of Economic Policy Studies, 9(1) 96-112, Jan 1, 2014  Peer-reviewed

Misc.

 6
  • 生田 祐介
    Kyodo Weekly, (2019年2月11日号)-10, Feb, 2019  
    企業が消費者からデータを収集することと引き換えに、無料サービスを提供することに対して、米国では競争政策上の問題としない理由を説明した。
  • 生田 祐介
    Kyodo Weekly, (2018年11月19日号) 8, Nov, 2018  
    少数のデジタルプラットフォーマ―に対して、新たな政策介入や規制の必要性が問われる中、いかにして市場画定を行うのかを紹介した。
  • 生田 祐介
    Kyodo Weekly, 2018年No.33 14, Aug, 2018  
    グーグルが欧州委員会に課徴金支払いを命じられたことを踏まえ、グーグルの行為の何が、競争法違反と判断されたのかを支配的地位の濫用という観点から解説した。
  • 生田 祐介
    Kyodo Weekly, 2017年No.41 17, Oct, 2017  
    データの収集がどういった場合に独禁法上問題となり、データの活用がどういった場合に知的財産権で守られるのかを紹介した。
  • 生田 祐介
    Kyodo Weekly, 2018年No.22 143, May, 2017  
    個人データ保護がどういった場合に必要なのかについて、企業と消費者との間にある個人データの利用を巡る情報格差の観点から、経済学的に説明した。

Presentations

 13
  • Economics seminar, Mar 6, 2024, Department of Economics, Kwansei Gakuin University.  Invited
  • Mar 4, 2024, Department of Business Administration, Nanzan University.
  • Dec 15, 2023, Asia Pacific Industrial Organization Society
  • The 36th research workshop on industrial organization and competition policy,, Oct 14, 2023, Institute of Social and Economic Research, Osaka University  Invited
    Motivated by the GDPR as opt-in regime for privacy this paper;examines how privacy disclosure affects consumers through value-enhancing data analytics. Artificial Intelligence (AI) can help firms to provide products or services to consumers with personalization. This paper considers product personalization when consumers provide their personal data to the AI-enabled firm for improving the value of matching taste under the Hotelling type duopoly. While firms are interested in exploit consumer surplus through personalized pricing, consumers may disclose their personal information to improve quality of matching taste. Chen et al.,(2022) focus on the situation where a post-merger firm available a personalized offer can identify consumers' location between two firms based on personal information collected through the acquired firm. For this reason, they analyze in a model that the target of personalized offering starts from consumers with higher preferences in order. However, they treated data analytics quality is exogenous. We therefore develop their idea in terms of making the quality of data analysis endogenous. Specifically, consumers choose the amount of personal data to improve data analytics quality with considering privacy cost. Model setting and its result are as follows. The two firms (firm 1 and firm 2) are each located at the endpoints of the hoteling line, where unit mass consumers have the same evaluation of the stand-alone product. Assume that firm 1, which is capable of personalization, already know the consumer’s location. Given that, we consider the situation where consumers targeted for personalization are price discriminated according to their location position, but on the other hand, they can also expect to improve their matching taste. We then consider a situation in which the target consumer may disclose personal information to update the quality of matching. Disclosing privacy may not be costless for the sake of security protection or psychologically. Since consumers incur privacy cost to disclose their personal data, the targeted consumers do not provide so much personal data that improves the quality of matching. However, as also considered in Lefouili et al. (2023), consumers increase their incentive to provide more data when investments in AI technology are made. They study monopolist who provides the free online service at the exchange of personal data which is monetized to third party. Contrary to them, this paper assume competition. Provision of personal information affects the maximus scale of personalization non-monotonically depending on the degree of privacy cost. When the targeted consumer is large, the AI investment is not implemented.
  • 関和広, 生田祐介, 松林洋一
    日本経済研究センター 第 13 回「AI・ビッグデータ経済モデル研究会」, Aug 5, 2022  Invited

Teaching Experience

 8

Professional Memberships

 4

Research Projects

 2

研究テーマ

 3
  • 研究テーマ(英語)
    ネットワーク型産業(電力・電気通信)の経済分析
    研究期間(開始)(英語)
    2013/04/01
  • 研究テーマ(英語)
    テキストデータを利用した景況感の推定
    研究期間(開始)(英語)
    2017/04/01
  • 研究テーマ(英語)
    人工知能に関する損害賠償責任制度の経済分析
    研究期間(開始)(英語)
    2020/04/01