Quantitative investment model based on LightGBM algorithm

Quantitative investment refers to the trading method through quantitative way and computer program issued orders, in order obtain stable income. Firstly, this paper completes Pearson correlation analysis. Finally, coefficients of 50 indicators were calculated according relevant data, 8 with highest obtained. Secondly, LightGBM model, multiple linear regression model BP neural network three prediction models are used forecast volume "digital economy" plate from January 4, 2022 28, respectively. Thirdly, mean absolute value error, square R other evaluation indexes analyzed. accuracy is better, followed by worst.