Machine Learning is an application of artificial intelligence that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Some of the common areas where machine learning (ML) techniques applied are Fraud Detection , Spam email filtering, Classification of articles in Google news, etc. In this paper, we are presenting a case study on the application of an ML approach to recognize the parameters that cause an anomaly in a multivariate process, with a view to both prediction as well as diagnosis of the root cause. The quality of the approach has been assessed based on the high levels of precision, recall and ultimate overall accuracy.