Current microparticle (MP) development still strongly relies on the laborious trial-and-error approach. Herein, we developed a systemic method to evaluate the significance of MP formulation factors and predict drug loading efficiency (DLE) using design of experiment (DoE) and machine learning modeling. A first-in-class 3D printing concept was initially employed to fabricate polymeric MPs by a 3D printer. Sprayed Multi Adsorbed-droplet Reposing Technology (SMART) was developed to combine extrusion-based printing with emulsion evaporation technique to fabricate a small molecule drug i.e., 6-thioguanine (6-TG) loaded poly (lactide-co-glycolide) (PLGA) MPs. Compared to conventional emulsion evaporation method, SMART employs the shear force exerted by the printing nozzle rather than the sonication energy to generate smaller emulsion droplets in a single step. Furthermore, the applied shear force in the 3D printing process reported herein is controllable since the emulsion is extruded through the nozzle under preset printing conditions. The formulated MPs exhibited spherical structure with size distribution ∼ 1-3μ m in diameter and reached ∼ 100 % drug release at 10 h. Also, the papain-like protease (PLpro) inhibition efficacy of 6-TG in formulated MPs was maintained even after the printing process under different printing conditions. Furthermore, the formulation factor importance was assessed by DoE statistical analysis and further validated by machine learning modeling. Among the four process parameters (drug amount, printing speed, printing pressure, and nozzle size), drug amount was the most influential formulation factor. Moreover, it is interesting that nearly all the machine learning models, especially decision tree (DT), demonstrated superior performance in predicting DLE compared to DoE regression models. Overall, incorporating DoE and machine learning modeling shows great promises in the prediction and optimization of MP formulations factors by means of a novel SMART technology. Moreover, this systemic approach helps streamline the development of MP with programmable pharmaceutical attributes, representing a new paradigm for digital pharmaceutical science.