Design and Research of Intelligent Quantitative Investment Model Based on PLR-IRF and DRNN Algorithm

Due to the subjective nature of human behavior, Artificial Intelligence (AI) has less research and application in this field. This paper selects the most representative financial investment field of human social behavior as the object, and proposes an algorithm of turning point prediction named Piecewise Linear Representation-Improved Random Forest (PLR-IRF) for macro trend analysis. Then according to the Deep Learning (DL) theory, which adopts a Deep Recursive Neural Network (DRNN) to design the investment decision model. Finally, 489 days stock exchange data of the Shanghai Stock Exchange were used for verification. The results show that compared with the existing quantitative investment models, the prediction accuracy of this model is relatively high, and the investment strategy is relatively novel.