Abstract: Aiming at the difficulties in initial well productivity forecast after volumetric fracturing, the article analyzes the influencing factors of initial well productivity after fracturing based on the data of geology, engineering and production performance by volumetric fracturing process in District Long-26 and Yuanping-1 of Daqing oilfield. Gray correlation analysis method, multiple correlation coefficient method and entropy evaluation method are used to analyze the degree of correlation between the initial well productivity after volumetric fracturing and the influencing factors, then the main factors are determined. The study result shows that the main factors influencing the initial well productivity after volumetric fracturing include sand adding volume, liquid adding volume, formation pressure and permeability, based on which the support vector machine (SVM) method is used to forecast the initial well production after fracturing. The actual fracturing effect verifies that SVM method can more accurately forecast the initial production after fracturing than conventional multiple linear regression (MLR) method, which may provide guidance and reference for similar tight oil and gas reservoir development