The global demand for aquaculture has significantly grown, now accounting for 50% of the total fish food supply. As aquaculture is anticipated to overtake capture fisheries in fish production, it has become a key driver of economic growth, particularly in coastal and rural areas. However, ensuring sustainable practices in aquaculture requires careful management of environmental conditions to maintain the health and quality of aquatic species. Advanced technologies, such as IoT-based monitoring systems, are essential for improving productivity and addressing the challenges posed by climate change and overfishing. This paper introduces a cost-effective IoT model that monitors key aquaculture parameters: turbidity and water temperature. Data from sensors are uploaded to cloud platforms like ThingSpeak, enabling storing of environment data. A machine learning model was developed to predict the most optimal fish species. The model used a stacking classifier, which demonstrated strong predictive performance with an accuracy of 94.89%. Notably, it achieved this while using one fewer sensor variable compared to existing approaches. Despite this, the model outperformed most models reported in related articles. This IoT model helps small businesses enhance yields, reduce mortality, and promote sustainable aquaculture by selecting suitable fish breeds or optimizing aqua-farm conditions for their comfort.