The work aims to investigate the wettability properties of gelatin solutions with different charge-to-mass ratios and establish a prediction model. With the edible gelatin film-forming droplet as the research object, an external electrostatic field was applied through induction charging to improve the wettability properties and explore the effect of electric field voltage on the charge-to-mass ratio and surface tension of the gelatin droplets and the contact angle of droplets on hydrophobic surfaces. Machine learning was used to establish predictive models between the charge-to-mass ratio, surface tension, and contact angle of gelatin droplets. The charge-to-mass ratio of gelatin droplets continued to increase with the increase of voltage, and the gelatin droplets had the highest charge-to-mass ratio (−50 nC/g) when only Span20 was used as the surfactant (tw0 group). In the range of 0-7 kV, the surface tension of gelatin droplets decreased from 35.99-40.65 mN/m to 31.38-35.65 mN/m with the increasing voltage, with the tw0 group showing the most significant decrease in surface tension. The contact angle of gelatin droplets on the surface of paraffin also decreased with the increasing voltage and had a minimum value at a 1:1 ratio of surfactant Tween 20:Span20 (64.99° at a voltage of 7 kV). The decision coefficient of the deep neural network (DNN) prediction model was close to 1, the mean square error was less than 0.08, and the average absolute error was less than 0.15, indicating the best prediction performance. Electrostatic spraying can effectively improve the wettability properties of the film on the surface of food and enhance the preservation effect of the film. The DNN has the best prediction effect on the relationship between the charge-to-mass ratio of gelatin droplets, surface tension, and contact angle.