Reproducing Stylized Facts in Artificial Stock Markets with Price-Data-Trained Neural Agents

Agent-based models of financial markets often rely on a small set of hand-crafted trading rules, making it difficult to relate model heterogeneity to information that is observable in market data. We take a different standpoint and treat the design of heterogeneity as a representation problem under limited observations. In our framework, each agent’s decision rule is implemented as a neural-network mapping from recent price histories to order decisions, trained on historical index or stock price series. To describe and manipulate heterogeneity without pre-assigning mechanism labels, we introduce Fit Quality (FQ), an ex post effect-defined index summarizing how strongly each learned rule fits the price patterns it was trained on, and we use FQ solely as a coordinate for organizing agent populations and constructing controlled changes in agent composition, rather than as a measure of forecasting skill or economic performance. Using this representation, we examine whether simulations can reproduce several stylized features of return series. We also perform simple ablation experiments to assess how far the observed properties depend on the data-trained decision rules rather than on the market mechanism alone. Taken together, the framework is intended as a step toward more data-linked, representation-conscious agent-based models, in which alternative ways of organizing heterogeneity can be compared within a common market environment.