A Fusion Model for Securities Analysts' Stock Rating Information Based on the Evidential Reasoning Algorithm under Two-dimensional Progressive Recognition Framework

다국어 초록 (Multilingual Abstract)

Securities analysts' forecast information can effectively reduce the uncertainty of information in securities markets, and can also promote effective allocation in capital market. The personality difference of securities analysts will lead to different analysis results. In order to improve the utilization of analysts' forecast information, evidential reasoning algorithm under two-dimensional progressive framework and grouping method for combining evidence were used in this paper to fuse securities analysts' stock rating information. Based on the forecast earnings information and stock rating information of analysts, we constructed a two-dimensional progressive framework, and then fused stock rating information of multiple analysts into one piece of evidence information. Finally, we empirically verified the model in this paper by using Chinese analysts' forecast information. The analysis on the fusion results have shown that: compared to traditional statistic model, the accuracy, certainty and the discrimination of the fusion results in our model have been improved.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Theoretical Fusion Model for Analysts' Information under Two-dimensional Progressive Recognition Framework
• 2.1. Grouping Method for Combining Evidence under Two-dimensional Progressive Recognition Framework
• 2.2. Fusion Model of Analysts' Information based on Grouping Method for Combining Evidence
• 3. Empirical Study
• 3.1. Data
• 3.2. Application of the Information Fusion Model
• 3.3. Analysis of the Fusion Results
• 4. Conclusion
• Acknowledgements
• References