We developed an order-driven agent-based artificial stock market to analyze the liquidity costs of market orders in the Taiwan Stock Market (TWSE). The agent-based stock market was based on the DFGIS model proposed by Daniels, Farmer, Gillemot, Iori and Smith . When tested on 10 stocks and securities in the market, the model-simulated liquidity costs were higher than those of the TWSE data. We identified some possible factors that have contributed to this result: 1) the overestimated effective market order size; 2) the random market orders arrival time designed in the DFGIS model; and 3) the zero-intelligence of the artificial agents in our model. We continued improving the model so that it could be used to study liquidity costs and to devise liquidation strategies for stocks and securities traded in the Taiwan Stock Market.
Natural Computing in Computational Finance Studies in Computational Intelligence Volume 380, 2012, pp 163-179