Minh Tran

• John von Neumann Institute

In this paper, we propose a novel approach to optimize parameters for strategies in automated trading systems. Based on the framework of Reinforcement learning, our work includes the development of a learning environment, state representation, reward function, and learning algorithm for the cryptocurrency market. Considering two simple objective fu...

In this paper, we propose different objective functions to tune hyperparameters in an agent-based simulation of the stock market. To reproduce the stylized facts of the real market, Bayesian optimization is introduced to find the calibrated set of parameters. The experimental results of Bayesian calibration have provided a stable and low-cost hyper...

In this research, an agent-based model (ABM) of the stock market is constructed to detect the proportion of different types of traders. We model a simple stock market which has three different types of traders: noise traders, fundamental traders, and technical traders, trading a single asset. Bayesian optimization is used to tune the hyperparameter...

In this paper, we study a discrete time hedging and pricing problem using Garman-Kohlhagen model in a market with liquidity costs. We prove that delta hedging is an unique optimal strategy. In particular, the hedging strategy will have expected hedging error is the infinitesimal of the length of the revision interval with order of 3/2. An implicit...