Largemouth bass, a cultured sportfish species, is valued for its economic value and holds potential for food fish production. To modulate stress that negatively affects both growth and disease resistance in farmed largemouth bass, this study investigates the effects of five nutraceuticals: Fresta Protect (FP), Actifor Protect (AP), Actifor Power (APO), Enviro QS (EQ), and Syrena Boost (SY). Over an 8-week feeding trial, total biomass and feed intake were measured bi-weekly to monitor growth across treatments. At trial termination, various physiological and immunological parameters were also assessed, including blood glucose levels, hepatosomatic index (HSI), lysozyme activity, and macrophage phagocytosis. Results indicated no differences in growth (p > 0.05) and physiology (p > 0.05) parameters among treatments. However, immunological metrics revealed treatment differences: serum lysozyme activity (p = 0.001) and macrophage phagocytosis (p = 0.007), indicating their effects in enhancing immune responses. Given that these findings demonstrate that these nutraceuticals did not impair growth or physiological health, we aimed to project growth trajectories over extended periods (up to 24 weeks) using predictive modeling to evaluate the long-term impact of nutraceutical supplementation. We hypothesized that largemouth bass receiving nutraceutical-enhanced diets would demonstrate improved growth performance and nutrient utilization over time. We employed time-series analysis for the approach, supported by machine learning (ML) techniques such as Random Forest, Gradient Boosting, and logistic and Gompertz growth curve models that best fit according to treatments and performance metrics. Key input variables for these models included feed conversion ratio (FCR), specific growth rate (SGR), protein efficiency ratio (PER), and protein production value (PPV). Supervised learning approaches (logistic and Gompertz growth curve models) and machine learning models (Random Forest and Gradient Boosting) were incorporated. This dual framework revealed that growth curve models excel in long-term forecasting, while ML models performed better for short-term trend analysis. The predictive growth curve models with the best fit indicated that at week 24, fish provided with APO would have the greatest growth (203.00 g/fish), followed by AP (53.98 g/fish) and EQ (45.47 g/fish). This also provides insight into the positive correlation between the feed given and maximum growth. Providing nutrient-supplemented feed over a more extended period, especially APO, AP and EQ could enhance the growth of largemouth bass substantially. Real-world applications could confirm the outcomes of the growth curve prediction models, as this could be included in the physiological parameter determination.