2020/12/31 by Filippo Neri, Neri, Filippo
Economics, Econometrics and Finance · #Complex Systems and Time Series Analysis #Computational Engineering #FOS: Computer and information sciences #FOS: Economics and business #Finance #I.2.6 #Machine Learning (cs.LG) #Trading and Market Microstructure (q-fin.TR) #and Science (cs.CE)
paper · pdf · doi:10.48550/arxiv.2101.03127
openalex publication_date 2020/12/31 · openalex created_date 2022/09/17 · openalex updated_date 2026/07/28
The paper proposes a computational adaptation of the principles underlying\nprincipal component analysis with agent based simulation in order to produce a\nnovel modeling methodology for financial time series and financial markets.\nGoal of the proposed methodology is to find a reduced set of investor s models\n(agents) which is able to approximate or explain a target financial time\nseries. As computational testbed for the study, we choose the learning system L\nFABS which combines simulated annealing with agent based simulation for\napproximating financial time series. We will also comment on how L FABS s\narchitecture could exploit parallel computation to scale when dealing with\nmassive agent simulations. Two experimental case studies showing the efficacy\nof the proposed methodology are reported.\n