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

2021 Fiscal Year Final Research Report

Development of Methodology for Geographic Crime Prediction -Establishment of academic infrastructure and system development through interdisciplinary research and industry-academia collaboration

Research Project

  • PDF
Project/Area Number 17H02046
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Social systems engineering/Safety system
Research InstitutionUniversity of Tsukuba

Principal Investigator

Amemiya Mamoru  筑波大学, システム情報系, 准教授 (60601383)

Co-Investigator(Kenkyū-buntansha) 高木 大資  東京大学, 大学院医学系研究科(医学部), 講師 (10724726)
島田 貴仁  科学警察研究所, 犯罪行動科学部, 室長 (20356215)
村上 大輔  統計数理研究所, データ科学研究系, 助教 (20738249)
梶田 真実  東京大学, 空間情報科学研究センター, 客員研究員 (10825376)
Project Period (FY) 2017-04-01 – 2021-03-31
Keywords犯罪 / 地理的予測 / 空間統計学 / 予防 / 警察
Outline of Final Research Achievements

This study developed a method of "geographic crime prediction" that predicts when and where crimes will occur. First, we clarified the nature of crime as a precondition for prediction, especially environmental factors and spatio-temporal concentration of crime. Second, we developed a prediction model that is more suitable for the crime situation in Japan, taking into account the characteristics of low frequency (low number of crimes) and over-dispersion (weak geographical concentration). Third, based on discussions with practicing police officers, the feasibility of effective implementation of the geographic crime prediction method in police practice was examined.

Free Research Field

社会工学

Academic Significance and Societal Importance of the Research Achievements

本研究の結果,日本における犯罪の様々な性質が明らかになるとともに,その性質に基づく予測の可能性と実務への適用可能性が示された.本研究の成果は,50本の一般論文(うち査読付き26本)と69本の口頭発表として公表された.また,国際学術イベントでのセッション設定など国際的な情報発信も行われた.一連の研究の過程において,研究者と各地の警察実務者とのコネクションが創出され,将来の研究の発展につながる研究者と実務家の協働の基盤が築かれた.以上のように,本研究は,学術・実務双方において大きな成果を生むことができた.

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi