• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

適応学習機能を持つ非対面取引判定システムの開発

Research Project

Project/Area Number 16K00428
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Web informatics, Service informatics
Research InstitutionYamaguchi University

Principal Investigator

高橋 雅和  山口大学, 大学院技術経営研究科, 准教授 (20621105)

Co-Investigator(Kenkyū-buntansha) 津田 和彦  筑波大学, ビジネスサイエンス系, 教授 (50302378)
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Granted (Fiscal Year 2017)
Budget Amount *help
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords不正検知 / 通信販売 / パターン解析 / 機械学習
Outline of Annual Research Achievements

本研究は,通信販売業界における複雑化・多様化する不正取引手口に対処するために,出荷時の不正検知を支援する事前知識生成を目標としている.H29年度は,研究の結果以下のとおりの論文をはじめとして国際会議で研究成果の発表を行うことができた.
1)Masakazu Takahashi, Hiroaki Azuma, and Kazuhiko Tsuda: A Study on Validity Detection for Shipping Decision in the Mail-order Industry
査読:1,国際会議:3

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

本研究の目的は,通信販売業界における受注時の与信精度向上である.顧客との商品取引のパターン解析をもとにした受注時点での取引安全についての事前知識生成である.取引分析からの特徴抽出を行う際に管理システムの不備を突いた取引など多種多様な取引形態を発見した.
特徴抽出のために様々な学習器を用いて解析を行うことや,同じ学習器を用いて別分野のデータを用いて予測評価を行うことに注力した.論文や学会発表を通じて成果をまとめることができた.よっておおむね順調に到達している.

Strategy for Future Research Activity

不正取引の検出のために取引情報解析だけではなく様々な学習器を用いた解析や,同じ学習器を用いて別分野のデータを用いて予測評価実験を行う.取引リスク管理に関わるシステムや管理体制の不備による想定外の動きにも呼応できるよう研究を進める.実務家からのヒアリングを引き続き行い研究の際の参考とする.

Report

(2 results)
  • 2017 Research-status Report
  • 2016 Research-status Report

Research Products

(9 results)

All 2018 2017 2016

All Journal Article Presentation

  • [Journal Article] A Study on Validity Detection for Shipping Decision in the Mail-order Industry2017

    • Author(s)
      Takahashi Masakazu, Azuma Hiroaki, Tsuda Kazuhiko
    • Journal Title

      Procedia Computer Science

      Volume: 112 Pages: 1318-1325

    • DOI
      10.1016/j.procs.2017.08.007
    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] A Study on the Efficient Estimation of the Payment Intention in the Mail Order Industry2016

    • Author(s)
      Masakazu Takahashi , Hiroaki Azuma, and Kazuhiko Tsuda
    • Journal Title

      Procedia Computer Science

      Volume: 96 Pages: 1122-1128

    • DOI
      10.1016/j.procs.2016.08.154
    • Related Report
      2016 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] A Study on the Efficient R&D Theme Selection Method with Machine Learning2016

    • Author(s)
      Masashi Shibata, Koichi Inoue and Masakazu Takahashi
    • Journal Title

      Proceedings of the 11th International Knowledge Management in Organizations (KMO2016) Conference on The changing face of Knowledge Management Impacting Society

      Volume: 16

    • DOI
      10.1145/2925995.2926031
    • Related Report
      2016 Research-status Report
    • Peer Reviewed
  • [Presentation] A Study on Classifying the Store Positioning from the Transactional Data2018

    • Author(s)
      Masakazu Takahashi and Yuji Tanaka
    • Organizer
      The International Research Conference on Smart Computing and Systems Engineering (SCSE) 2018
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Study on Clustering of Technological Fields through Patent Analyses with Link Mining2017

    • Author(s)
      Masashi Shibata, and Masakazu Takahashi
    • Organizer
      2nd International Workshop of Artificial Intelligence of and for Business (AI-Biz 2017)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Toward an Efficient Search Method to Capture Future MOT Curriculum based on Next Generation IoT World, Society 5.0 in Japan2017

    • Author(s)
      Masashi Shibata, Yuichi Ohtsuka, Kazuya Okamoto, and Masakazu Takahashi
    • Organizer
      Portland International Conference on Management of Engineering & Technology (PICMET)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Study on Comparative Evaluation of Payment Rate Prediction Methods in the Mail Order Business2016

    • Author(s)
      Hiroki Azuma, Masakazu Takahashi, Norihiro Yoshida, and Kazuhiko Tsuda
    • Organizer
      The Fifth Asian Conference on Information Systems (ACIS 2016)
    • Place of Presentation
      Krabi, Thailand
    • Year and Date
      2016-10-27
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Study on the Efficient Estimation of the Payment Intention in the Mail Order Industry2016

    • Author(s)
      Masakazu Takahashi , Hiroaki Azuma, and Kazuhiko Tsuda
    • Organizer
      20th International Conference on Knowledge Based and Intelligent Information and Engineering Systems (KES2016)
    • Place of Presentation
      York, UK
    • Year and Date
      2016-09-05
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Study on the Efficient R&D Theme Selection Method with Machine Learning2016

    • Author(s)
      Masashi Shibata, Koichi Inoue and Masakazu Takahashi
    • Organizer
      The Eleventh International Conference on Knowledge Management in Organizations (KMO2016)
    • Place of Presentation
      Hagen, Germany
    • Year and Date
      2016-07-25
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2016-04-21   Modified: 2018-12-17  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi