Predictive maintenance using sensor information and analysis methods to measure and predict degradation and future component capability. The idea behind predictive maintenance is that failure patterns are predictable and if component failure can be predicted accurately and the component is replaced before it fails, the costs of operation and maintenance will be much lower. This repo attempts to utilise two powerful ensemble models, Random forest and Gradient Boosting to Predict the failure patterns of machinery.the data recieved from the sensors are 40,000 observation points fro trainig our model and 10,000 observation points for testing the efficasy of the ensemble models the Random forest model and boosting gradient models were further tunned using hyperparameter tunning techniques to search for the best model performance parameters, the results were compared and the best model is productionized..