Event-driven stock price prediction method, device and equipment and storage medium
A prediction method and event-driven technology, applied in the field of artificial intelligence, can solve problems such as inaccurate prediction of stock price trends, and achieve the effects of high efficiency, convenient use and improved accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] see figure 1 , figure 1 It is a schematic flowchart of an embodiment of the event-driven stock price prediction method of the present invention. figure 1 The forecasting method consists of steps:
[0035] S11: Based on the current news event, select stocks associated with the current news event;
[0036] Specifically, see figure 2 , step S11 includes the following steps:
[0037] S111: Obtain the current news event.
[0038]In step S111, the news event is the latest news event appearing on a certain website, such as the latest financial or current affairs news.
[0039] S112: Based on the news event, select a stock set corresponding to the news event;
[0040] The stock set may be all stocks in a certain market sector, such as real estate sector stocks or financial sector stocks.
[0041] S113: Input the current news event and the stock set into the calculation of the multi-way entity association network model, and select the stock associated with the current ne...
Embodiment 2
[0081] see Figure 7 , Figure 7 The stock prediction device comprises a stock selection module 71 and a price prediction module 72, the stock selection module 71 is used for selecting the stock associated with the current news event based on the current news event; the price prediction module 72 is used for selecting the stock associated with the current news event based on the current news event and the The historical financial time series data of the stock is used to predict the price fluctuation of the stock by using the heterogeneous information collaborative network model. Stock selection module 71 comprises acquisition news event unit 711, chooses stock collection unit 712 and stock calculation unit 713, news event unit 711 is used to obtain this current news event; Choose stock collection unit 712 based on this current news event, select stock collection; The computing unit 713 uses a multi-way entity-associated network model to calculate the stock set, and selects st...
Embodiment 3
[0084] The present invention also provides an event-driven stock price prediction device, the stock price prediction device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be processed by the at least one processor An instruction executed by a processor, the instruction is executed by the at least one processor, so that the at least one processor can execute the method of Embodiment 1.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 



