The quality of semen in pig farms is a key factor for the efficiency of artificial insemination programs. Semen quality is influenced by genetic, environmental, and management factors that affect parameters such as sperm motility, viability, or morphology. However, boar selection for semen collection is usually based on the technician’s experience. Therefore, this study aimed to develop an artificial intelligence-based model to predict ejaculate quality and support data-driven decision-making. A database comprising 6,899 semen samples collected from 78 Duroc boars was used, including information on animal (age), handling during collection and semen preparation, sperm quality parameters, season, and environmental conditions (temperature and humidity). A Big Additive Model (BAM) was applied to capture nonlinear relationships and temporal trends. The model was used to predict the “number of good sperm” in an ejaculate, calculated from sperm concentration (spz/mL), ejaculate volume (mL), and the percentage of motile and morphologically normal sperm (divided by 100). Additionally, semen samples were categorized into four quality groups (low, medium–low, medium–high, and high) to evaluate the model’s ability to predict boar semen quality. The model achieved a coefficient of determination (R²) of 0.485, with a root mean square error (RMSE) of 17730.56 and a mean absolute error (MAE) of 13832.95, indicating moderate predictive performance. In the categorical classification, the BAM showed an overall accuracy of 48.79%, with greater consistency in the extreme categories (low—58.38% and high—63.59%). Interestingly, the model reached an accuracy of 88.87% when classifying medium–high/high semen samples and 86.03% for low/medium–low samples. In conclusion, the BAM achieved moderate predictive accuracy but high reliability in distinguishing two categories of semen quality. This study forms part of the Agroalnext programme and was supported by MCIU with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Comunidad Autónoma de la Región de Murcia - Fundación Séneca.