Superior quality crops and large production yield always remained the foremost objective of any farmer. The primary objective of large production can never be fulfilled by following the traditional methods of agriculture. The Meteorological parameters like temperature, humidity, rainfall, soil macronutrients (Nitrogen, Phosphorus, Potassium), and soil PH are among the most crucial parameters whose uneven composition mainly hinders crop growth dynamics. A farmer mainly focuses on adding more fertilizers and irrigation for nurturing the crop. But do not have much concern about the optimum level of the ecological factors, which suits the crop more than the adopted traditional methods. However, the combination of all the factors, maintaining their optimum balance, can only decide the crop type and its growth. Every crop requires a different ecological regime for its sustainable development and that is very important for the understanding of any farmer. This paper proposes an Intelligent Learning System (ILS) that can guide a farmer, to cultivate the most felicitous crop suitable under the available resources. ILS is an IoT-enabled machine learning system that works on the real-time data input of 7 different attributes for prediction. In this paper, the comparison ofvarious machine learning models is conducted and the maximum accuracy is evaluated. The accuracy for KNN, DT, RF, GB, and XGB classifiers are found to be 0.9772, 0.9931,0.9972,0.9954,and 0.9931 respectively

Internet of Things (IoT), Intelligent Learning System (ILS), Machine Learning (ML) classifiers, agriculture attributes, Felicitous crop