Method and system for predicting financial product sales volume based on light GBM algorithm

The invention discloses a method and system for predicting the sales volume of financial products based on a light GBM algorithm, and relates to the field of artificial intelligence, and the method comprises the steps: screening a first-class customer set, and obtaining a second-class customer set and a third-class customer set; inputting the to-be-evaluated customer set into the machine learning model to obtain a fourth-class customer set; performing intersection calculation on the third-class customer set and the fourth-class customer set to obtain a fifth-class customer set, and merging non-intersection users to obtain a sixth-class customer set; screening the sixth customer set to obtain a seventh customer set; and obtaining a financial product sales prediction result based on various customer sets. The technical problems that in the prior art, due to the fact that a financial product sales prediction algorithm is traditional, overfitting occurs, operation is not fast enough, a large amount of memory is o