Predicted price-to-book value ratios (P/BV) are widely used for the valuation of listed common stocks. However, with the application of automated trading system (ATS), the existing indicators that are applied in the method are losing their effectiveness in the Chinese market. Combining qualitative research with the text mining method, this study explores and validates those ignored factors to improve the accuracy of the stock valuation. On the basis of the principal of the existing valuation method, we clarify the scope of the factors that affects the P/BV ratio prediction. Through semi-structured interviews that are designed with six first-level factors which are taken from the literature, we then excavate some second-level factors. After that, with three corpuses including samples form Sina.com.cn, Xueqiu.com, and CSDN.net, four first-level factors and thirteen second-level factors have been verified step by step through the Latent Dirichlet Allocation (LDA) model. In the process, two other new factors and three sub-factors are also found. Furthermore, based on the factor correlation that was found in a data analysis, a factor relationship model was built. The results can be used in a stock valuation in future work as the basis of the indicator system for the prediction of P/BV ratio.

Automated trading system (ATS) is a computer program that combines different trading rules to find optimal trading opportunities. The objects of ATS, which are financial assets, need evaluation because that is of great significance for stakeholders and market orders. From the perspectives of dealers, agents, external environment, and objects themselves, this study explored factors in evaluating and choosing the object of ATS. Based on design science research (DSR), we presented a preliminary evaluation framework and conducted semi-structured interviews with twelve trading participants engaged in different occupations. By analyzing the data collected, we validated eight factors from literatures and found four new factors and fifty-four sub-factors. Additionally, this paper developed a relationship model of factors. The results could be used in future work to explore and validate more evaluation factors by using data mining.