An Optimization Model of Financial Management Teaching Strategies Based on Reinforcement Learning

In this paper, a deep reinforcement recommendation algorithm based on the attention mechanism is constructed based on the reinforcement learning model and combined with the attention mechanism as well as the recurrent network. Using this algorithm, a financial management teaching material recommendation system is developed. The optimization effect of this paper’s system in financial management teaching is evaluated through a number of experiments, such as model training and performance testing. The training speed and effect of the model in this paper are better than the comparison model, and the loss function value can converge to 0.15 in only 17 minutes, and the average recommendation accuracy is about 0.972. Users accessing this paper’s financial management teaching system concurrently all return correct results and have a response time of 267ms. This paper’s system can be optimized to obtain higher cumulative rewards by optimizing its strategy, and the level of financial management knowledge after applying this paper’s teaching system in the experimental class increased by 7.58 compared to the control class. In addition, the system in this paper can provide accurate financial management teaching materials for different students. The deep reinforcement recommendation algorithm based on attention mechanism designed in this paper can be used as a strategy optimization model for financial management teaching.