Data Mining Techniequs that aware social fairness

• Project/Area Number: 24500194
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: KAMISHIMA Toshihiro 独立行政法人産業技術総合研究所, ヒューマンライフテクノロジー研究部門, 主任研究員 (50356820)
• Co-Investigator(Kenkyū-buntansha): AKAHO Shotaro 独立行政法人産業技術総合研究所, ヒューマンライフテクノロジー研究部門, 研究グループ長 (40356340)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Project Status: Completed (Fiscal Year 2014)
• Budget Amount: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000); Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2013: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000); Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
• Keywords: データマイニング / 機械学習 / 統計 / 独立性 / 公正性 / 中立性 / 推薦システム / フィルタバブル / 統計的独立性 / フィルターバブル

Outline of Final Research Achievements

As the improvement of data mining technologies, such technologies are being used for determinations that seriously affect individual' lives, such as employment applications, credit, insurance rates, and so on. Needless to say, such serious determinations must be unbiased and fair in terms of socially sensitive information, such as gender or race. For this purpose, we develop the technique to avoid the use of such sensitive information in the serious determinations. The simple elimination of sensitive information from the calculations is insufficient for avoiding inappropriate determination process, due to the indirect influence of sensitive information. This phenomena is called the read-lining effect. We treat this red-lining effect by introducing the methodologies based on the notion of the statistical independence.

Research Products

• [Journal Article] Absolute and Relative Clustering (2013)
  • Author(s): T. Kamishima and S. Akaho
  • Journal Title: Proc. of the 4th MultiClust Workshop on Multiple Clusterings, Multi-view Data, and Multi-source Knowledge-driven Clustering Volume: なし Pages: 1-6
  • DOI: 10.1145/2501006.2501013
  • Peer Reviewed
• [Journal Article] Efficiency Improvement of Neutrality-enhanced Recommendation (2013)
  • Author(s): T. Kamishima, S. Akaho, H. Asoh, and J. Sakuma
  • Journal Title: Proc. of the 3rd Workshop on Human Decision Making in Recommender Systems Volume: なし
  • Peer Reviewed
• [Journal Article] The Independence of the Fairness-aware Classifiers (2013)
  • Author(s): 神嶌敏弘、赤穂昭太郎、麻生英樹、佐久間淳
  • Journal Title: Proceedings of the 4th IEEE International Workshop on Privacy Aware Data Mining Volume: なし Pages: 849-848
  • DOI: 10.1109/icdmw.2013.133
  • Peer Reviewed
• [Journal Article] Enhancement of the Neutrality in Recommendation (2012)
  • Author(s): T. Kamishima, S. Akaho, H. Asoh, and J. Sakuma
  • Journal Title: Proc. of the 2nd Workshop on Human Decision Making in Recommender Systems Volume: なし Pages: 8-14
  • Peer Reviewed
• [Journal Article] Fairness-aware Classifier with Prejudice Remover Regularizer (2012)
  • Author(s): T. Kamishima, S. Akaho, H. Asoh, and J. Sakuma
  • Journal Title: Proc. of the {ECML PKDD 2012}, Part~{II} Volume: なし Pages: 35-50
  • DOI: 10.1007/978-3-642-33486-3_3
  • ISBN: 9783642334856, 9783642334863
  • Peer Reviewed
• [Presentation] Correcting Popularity Bias by Enhancing Recommendation Neutrality (2014)
  • Author(s): T. Kamishima, S. Akaho, H. Asoh, and J. Sakuma
  • Organizer: The 8th ACM Conference on Recommender Systems
  • Place of Presentation: Foster City, Calfornia, USA
  • Year and Date: 2014-10-06 – 2014-10-10
• [Presentation] 公正配慮型分類器の公正性に関する分析 (2014)
  • Author(s): 神嶌 敏弘，赤穂 昭太郎，麻生 英樹，佐久間 淳
  • Organizer: 電子情報通信学会 情報論的学習理論と機械学習研究会
  • Place of Presentation: 筑波大学，つくば市
  • Year and Date: 2014-09-01
• [Presentation] 情報中立推薦システムの高速化 (2014)
  • Author(s): 神嶌 敏弘，赤穂 昭太郎，麻生 英樹，佐久間 淳
  • Organizer: 2014年度人工知能学会全国大会
  • Place of Presentation: ひめぎんホール，松山市
  • Year and Date: 2014-05-12 – 2014-05-15
• [Presentation] 中立性・公正性に配慮したデータ分析 (2013)
  • Author(s): 神嶌 敏弘
  • Organizer: 2013年度人工知能学会全国大会
  • Place of Presentation: 富山県，富山市，富山国際会議場等
• [Presentation] 情報中立推薦での中立性項の改良 (2013)
  • Author(s): 神嶌 敏弘，赤穂 昭太郎，麻生 英樹，佐久間 淳
  • Organizer: 電子情報通信学会 第13回情報論的学習理論と機械学習(IBISML)研究会
  • Place of Presentation: 東京都，早稲田大学 西早稲田キャンパス
• [Presentation] 情報中立推薦システム (2012)
  • Author(s): 神嶌 敏弘，赤穂 昭太郎，麻生 英樹，佐久間 淳
  • Organizer: 人工知能学会全国大会
  • Place of Presentation: 山口市，山口県教育会館他
• [Presentation] 公正・差別配慮型マイニングのサーベイ (2012)
  • Author(s): 神嶌 敏弘，赤穂 昭太郎，麻生 英樹，佐久間 淳
  • Organizer: 第10回 電子情報通信学会 情報論的学習理論と機械学習研究会
  • Place of Presentation: 東京農工大学小金井キャンパス
• [Book] 統計的学習の基礎 ―データマイニング・推論・予測― (2014)
  • Author(s): 著者：T.Hastie 他，監訳：神嶌 敏弘 他；翻訳：井尻 善久 他
  • Total Pages: 888
  • Publisher: 共立出版
• [Book] ビッグデータ・マネジメント --- データサイエンティストのためのデータ利活用技術と事例，3.2.1章 (2014)
  • Author(s): 神嶌 敏弘
  • Total Pages: 7
  • Publisher: エヌ・ティー・エス出版
• [Remarks] Fairness-Aware Data Mining (Soft & Data)
  • URL: http://www.kamishima.net/fadm/
• [Remarks] Information-neutral Recommender Sys. (Soft & Data)
  • URL: http://www.kamishima.net/inrs/
• [Remarks] Fairness-Aware Data Mining (Soft & Data)
  • URL: http://www.kamishima.net/fadm/
• [Remarks] Information-neutral Recommender System
  • URL: http://www.kamishima.net/inrs/