Ant Colony Optimization and Reinforcement Learning-Based System for Digital Economy Trend Prediction and Decision Support

Abstract

With the acceleration of the global digitalization process, the digital economy has become a key force driving economic development. However, the rapid changes and high levels of uncertainty in the digital economy pose great challenges to trend forecasting and decision support. Based on the ant colony algorithm and reinforcement learning, this study studies the trend prediction and decision support system of the digital economy. It provides effective prediction and decision-making tools for the development of the digital economy. In this study, a prediction and decision support system based on an ant colony algorithm and reinforcement learning is constructed. Through the analysis of a large number of experimental data, the results show that the system has significant advantages in predicting digital economy trends. The experimental data show that the ant colony algorithm can effectively extract key information from complex economic data. At the same time, reinforcement learning optimizes the prediction model through self-learning and improves the prediction accuracy. Experiments show that when the system predicts key indicators of the digital economy, the average prediction error is reduced by about 20% compared with traditional prediction methods, and the prediction stability is improved by 15%. In terms of decision support, the average yield of the strategy recommended by the system in the simulated market environment is 10% higher than that of the benchmark strategy.