Method and system for predicting stocks based on big data published by internet

Abstract

The invention discloses a method and system for predicting stocks based on big data published by the internet. The method comprises the following steps: crawling related information of the stocks before a business day; and then performing the feature extraction using the crawled data, constructing a training dataset, and using a Group Lasso to perform prediction model training, wherein the evaluation standard of the model is yield rate in a period of time in the operation mode of selling stocks purchased in late trading day and purchasing the stocks recommended at the current trading day at the opening every day; and then constructing a new testing set according to the data crawled at the trading day, predicting using the prediction model trained in former step to obtain the finally recommended stocks. Through the adoption of the method and system disclosed by the invention, a new, useful and reliable information source is provided for quantitative stock selection or stock prediction, the adding of above information can more reflect the market in combination with the traditional information; on the basis of method and system, the stock prediction model obtained using the machine learning technique can more capture the internal operation mechanism of the market, and the benefit of the investor can be effectively improved.

Description

technical field [0001] The present invention relates to a big data stock forecasting method, and in particular to a big data stock forecasting method and system based on Internet-based stockholder operations, analyst forecasts, stockholder comments, news, announcements, historical stock prices, capital flows, and fundamentals. Background technique [0002] Before the 1970s, stock investment was a qualitative analysis without data application, but a subjective art. With the popularization of computers, many people began to study the laws driving stock price changes, and replaced the traditional fundamental research methods with models. The concepts of price-earnings ratio and price-to-book ratio were born, and quantitative investment emerged. [0003] From subjective judgment to quantitative investment is a process from art to science. Before the 1970s, a fundamental researcher could only pay attention to 20 to 50 stocks, and the coverage was very limited. With quantitative...

AI Technical Summary

Problems solved by technology

He believes that the market itself has subjective judgment factors, investor sentiment will affect investment behavior, and investment behavior directly affects asset prices

Images