KAUST DepartmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
Young Talent Development
Applied Mathematics and Computational Science Program
KAUST Grant NumberOSR-CRG2021-4674
Permanent link to this recordhttp://hdl.handle.net/10754/676838
MetadataShow full item record
AbstractWe consider the mean-field game price formation model introduced by Gomes and Saúde. In this MFG model, agents trade a commodity whose supply can be deterministic or stochastic. Agents maximize profit, taking into account current and future prices. The balance between supply and demand determines the price. We introduce a potential function that converts the MFG into a convex variational problem. This variational formulation is particularly suitable for machine learning approaches. Here, we use a recurrent neural network to solve this problem. In the last section of the paper, we compare our results with known analytical solutions.
CitationAshrafyan, Y., Bakaryan, T., Gomes, D., & Gutierrez, J. (2022). The potential method for price-formation models. 2022 IEEE 61st Conference on Decision and Control (CDC). https://doi.org/10.1109/cdc51059.2022.9992621
SponsorsThe authors were supported by King Abdullah University of Science and Technology (KAUST) baseline funds and KAUST OSR-CRG2021-4674.
Conference/Event name2022 IEEE 61st Conference on Decision and Control (CDC)