More and more extensive data

Basically, it can be considered that the higher the level of quantitative trading, the more data needs to be processed behind it. Behind the top-level quantitative strategy is often a huge amount of data.

At present, some companies not only use traditional financial data, but also use satellite images and other picture information of port containers, or get clues about economic development from news reports, blogs and celebrity speeches. With the technical support of image recognition and natural language processing, many unstructured data can also be analyzed. Big data, unstructured data and training models all need the intervention of artificial intelligence technology. Patrick, the head of FRM hedge fund in London, has a good explanation for this: In this Internet age, the data we get far exceeds the possible processing capacity of human beings. The only way to analyze and identify patterns in this huge ocean of information is to use machine learning tools and technologies. This is the way to make a better investment strategy. "

Self-evolution and iterative trading strategy

In data processing, artificial intelligence technology broadens the data sources, so that more data can be included in the analysis. In terms of algorithm, artificial intelligence technology also enables financial instruments to automatically evolve and iterate trading strategies. Alexander, the chief investment officer of Rebellion, the pioneer of AI quantitative trading, said when introducing his products:

"We gave the system 20 years of global economic and market data, and let it learn the history of modern finance, and let it discover how different factors affect the prices of various asset classes, industries and regions. It doesn't follow any specific trading strategy according to the procedure, because we didn't tell it to look for these. The system will automatically identify concepts and associate concepts with performance under specific market conditions. "

In contrast, traditional quantitative investment methods often strictly apply the preset strategy, and its basic assumption is that the current correlation will last indefinitely. But this often brings great problems, because the market changes quickly. Therefore, the advantage of artificial intelligence system is that it can constantly evolve its investment strategy with the decline of old relationships and the emergence of new relationships.

Take treason as an example. After analyzing the financial and trade data, it is found that in the past 18 months, the cycle of commodity and foreign exchange markets has become shorter. Therefore, it will automatically recalibrate, calculate the impact of shorter cycles, and trade with new strategies.