4 results about "Stock forecasting" patented technology

The invention discloses a stock prediction method and system based on time constraint comparative learning, and the method comprises the steps: obtaining the historical daily frequency transaction data of a stock, including an opening price, a closing price, a highest price, a lowest price, and a trading volume; preprocessing the data and dividing the data into a training set, a verification set and a test set; constructing a time sequence prediction model with independent fragments; constructing positive and negative samples based on time constraints; designing a loss function and training the model; and the model predicts and outputs the stock yield. Through the time sequence encoder with independent segments, the problem of data offset existing in the stock market can be effectively solved, generalization on a test set is improved, positive and negative samples are constructed through comparative learning, stock modes with similar incomes can be effectively captured, and through time constraint, the influence of big trend on stock incomes in different periods can be eliminated.

The invention discloses a stock prediction system and method based on a CEEMDAN-CNN-BiLSTM-Attention hybrid algorithm, in the system, a data acquisition module is used for acquiring stock data to be predicted; the data preprocessing module preprocesses the acquired stock data; the model building module is used for building a CEEMDAN-CNN-BiLSTM-Attention model, and training and adjusting the built CEEMDAN-CNN-BiLSTM-Attention model by using the stock data, so as to learn the characteristics and rules of the change of the stock price; the trained CEEMDAN-CNN-BiLSTM-Attention model is used for stock prediction, and the model is used for stock prediction; and the prediction output module is used for outputting a prediction result of the CEEMDAN-CNN-BiLSTM-Attention model. Through signal decomposition and recombination and deep learning model collaborative optimization, the problems of nonlinearity, non-stationarity and multi-scale noise interference of the stock price sequence are solved, and high-precision end-to-end prediction is realized.

The application discloses a stock analysis method based on order transaction volume, and steps include: 1) determining a first price and a second price, wherein the first price is a price which is more than 1h from real time and order transaction volume is more than 80 hands for the first time; 2) when the first price is higher than the second price, if the stock real-time price is between the first price and the second price, the first index is stable; 3) when the first price is lower than the second price, if the stock real-time price is between the first price and the second price, the first index is stable, and the trend of the stock is estimated to be stable; the technical scheme brings at least the following beneficial effects: the history data of transaction orders and the stock order information in a short period are used to estimate the trend of the stock, and the success rate of the stock prediction method and system for estimating the stock trend is high.

The invention discloses a stock prediction method based on two-stage causal-industry graph fusion, and is applied to the technical field of financial time series prediction. Comprising the following steps: acquiring feature vectors of stocks, and constructing original input features; performing trend-fluctuation decomposition on the original input features to obtain trend components and fluctuation components; constructing a static industry graph and a dynamic causal graph; fusing the static industry graph and the dynamic causal graph through a two-stage cause-fruit industry graph fusion mechanism, and constructing a heterogeneous propagation graph; extracting trend component features and fluctuation component features; trend component coding and fluctuation component coding are carried out based on heterogeneous time sequence coding, and the yield relative ranking of the stock at the future target moment is expressed and predicted through additive fusion integration coding. The prediction method provided by the invention can adapt to market state changes, and is excellent in prediction performance and investment portfolio income.