The purpose of stock market investment is to obtain more profits. In recent years, an increasing number of researchers have tried to implement stock trading based on machine learning. Facing the complex stock market, how to obtain effective information from multisource data and implement dynamic trading strategies is difficult. To solve these problems, this study proposes a new deep reinforcement learning model to implement stock trading, analyzes the stock market through stock data, technical indicators and candlestick charts, and learns dynamic trading strategies. Fusing the features of different data sources extracted by the deep neural network as the state of the stock market, the agent in reinforcement learning makes trading decisions on this basis. Experiments on the Chinese stock market dataset and the S&P 500 stock market dataset show that our trading strategy can obtain higher profits compared with other trading strategies.

Option pricing based on data-driven methods is a challenging task that has attracted much attention recently. There are mainly two types of methods that have been widely used, respectively, the neural network method and the ensemble learning method. The option pricing model based on the neural network has high complexity, and a large number of hyper-parameters will be generated during training, resulting in difficult model adjustment. Furthermore, a lot of training data are needed. The option pricing model based on ensemble learning is not ideal for data feature extraction, because each calculation of the ensemble learning method is mainly to reduce the final residual. Therefore, this paper adopts a learning framework that embeds the modular ensemble learning methods into the network learning structure, and an option pricing model based on deep ensemble learning is proposed. The model is mainly composed of two parts: features reorganization based on random forest, used to calculate the importance of features, combined with the original data as training input; the multilayer ensemble data training structure is based on network learning structure and embeds two ensemble learning methods as network modules, and it also designs a stop algorithm to automatically determine the number of layers. This enables the model to retain the effect of data feature extraction and adapt to small and medium data sets without generating many hyper-parameters. Moreover, in order to make the model fully absorb the advantages of the two ensemble learning methods, we adopt cross-training for data. From the experimental results, it can be concluded that compared with the current optimal method, the prediction performance of the proposed model is improved by 36% in the root mean square error (RMSE), which proves the superiority of the proposed model from the quantitative direction.

Unbalanced data classification is a major challenge in the field of data mining. Random forest, as an ensemble learning method, is usually used to solve the problem of unbalanced data classification. For the existing random forest-based classification prediction model, its hyperparameters are dependent on empirical settings, which leads to the problem of unsatisfactory model performance. In order to make random forest find the optimum modelling corresponding to the character of unbalanced data sets and improve the accuracy of prediction, we apply the improved particle swarm optimization to set reasonable hyperparameters of the model. This paper proposes a random forest-based adaptive particle swarm optimization on data classification, and an adaptive particle swarm used to optimize the hyperparameters in the random forest to ensure that the model can better predict the unbalanced data accurately. Aiming at the premature convergence that appears in the particle swarm optimization algorithm, the population is adaptively divided according to the population fitness and the adaptive update strategy is introduced to enhance the ability of particles to jump out of the local optimum. Experimental results show that our proposed algorithms outperform the traditional ones, especially regarding the evaluation criterion of F1-measure and accuracy. The results on the six keel unbalanced data set the advantages of our proposed algorithms are presented.