Investment Efficiency Prediction and Dynamic Optimization Based on Deep Learning Algorithm

Traditional investment efficiency evaluation methods have problems such as low accuracy, slow response speed, and static analysis in terms of multi-dimensional feature processing, dynamic prediction, and real-time optimization. To this end, this paper introduces the convolutional neural network (CNN) model in artificial intelligence, by constructing an imagelike investment data input structure. At the same time, combined with the dynamic optimization mechanism, a resource allocation strategy driven by the CNN output results is designed to cope with the efficiency differences of investment projects under different time, region, and policy environments. Experimental results show that the CNN model is significantly better than traditional regression and time series methods in prediction accuracy, and the average prediction error is reduced by 34.7 %., effectively realizing the refined dynamic control of investment efficiency.