In this paper an experiential work done on in-house mushroom and their growth studied under room temperature and under monotub temperature. It proposes the Internet of Things (IoT) based system designed to collect the parameters of mushroom cultivation, such as temperature and humidity. Subsequently, data collection phase, pre-processing methodologies, including the identification and elimination of outliers, are employed to refine the dataset. The random forest classifier is trained on the generated dataset, and its performance is assessed utilizing metrics derived from the confusion matrix, which encompass accuracy, precision, recall, and f1-score. In the growth of agricultural products each crop depends upon various parameters, however in this paper we have used temperature variation for the study which is crucial for the mushroom production vertically. Growth of mushroom depends upon parameters like temperature, humidity, carbon dioxide and other gases. It is necessary to first classify the temperature and compare the forecasts with the actual data. By using this method, it is possible to assess the temperature range forecasts accuracy and ascertain how effectively the mycelium grows and accordingly scale up the mushroom production. The concept mentioned in this paper is adoption of machine learning based confusion model in the frame of RAMI 4.0 information and functional layer with a focus on mushroom growth. It contributes to the requirement of advanced technologies in mushroom growth with the help of Industry 4.0 standards. The paper is intended to contribute to the implementation of RAMI 4.0 in mushroom production with the help of machine learning related models of classification techniques.