Artificial stock market for testing price prediction models

Extensive research in multi-agent simulation of financial markets has been carried out to study various market models. Professionals extensively analyze financial markets in order to make profitable trading strategies, resulting from the price prediction models. We hypothesize that artificial markets can effectively be used to provide a real-time testing environment for the price prediction models. Much attention has not been paid to changing market conditions during the simulation. Here we develop an environment that effectively imitates the real world, by making artificial market dynamically configurable during the simulation. Flexibility is provided to change market composition and agent behavior during the run. It thus provides an artificial testing environment for profitability measurement of numerous prediction models that are being developed continuously around the globe. We also extend standard interfaces in order to embed a prediction model in an artificial trader. This market shall extend the usability and effectiveness of agent based simulation environments to new levels.