2021 Fiscal Year Final Research Report
Development of a system to predict further ahead about the effects of the law
| Project/Area Number |
19K22899
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 62:Applied informatics and related fields
|
|---|
| Research Institution | Niigata Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
的場 隆一 富山高等専門学校, その他部局等, 准教授 (30592323)
萩原 信吾 富山高等専門学校, その他部局等, 准教授 (50635224)
|
|---|
| Project Period (FY) |
2019-06-28 – 2022-03-31
|
| Keywords | 労働契約法 / マルチエージェント / シミュレーション / 雇い止め / Ｑ学習 |
|---|
| Outline of Final Research Achievements |
The purpose of this study is to propose a model that predicts two moves ahead after a law is enacted, and to predict the social and economic effects of the law several years later, thereby providing new decision-making tools for policy making. Here, the effect immediately after the law is enacted is called one move ahead, and the state reflecting human behavior further ahead is called two moves ahead. In this study, we take up the Labor Contract Act and construct a multi-agent model of an artificial labor market consisting of company agents with Q-learning and worker agents. The experimental results confirmed that the employment termination of fixed-term workers occurred due to the amendment of the law.
|
| Free Research Field |
知能情報システム
|
| Academic Significance and Societal Importance of the Research Achievements |
法律は，政府が主導する政策に沿って制定され，社会的，経済的効果をもたらすことが期待される．しかし，必ずしも当初の予想通りの効果がもたらされるとは限らない．この原因は，政策を決定した段階において，法律施行直後の効果の予測（一手先の予測）ができても，さらにその先の人間の行動を反映した予測（二手先の予測）が事前にできないことにある．すなわち，これが実現できれば，それを補うべくより効果的な政策が期待できる．雇い止めの問題は，昨今大きく騒がれている問題である．この問題をシミュレーションによってその原因を確認したことは，社会的意義が大きいと考えることができる．
|
