Machine Learning and Synthetic Minority Oversampling Techniques for Imbalanced Data: Improving Machine Failure Prediction

Prediction of machine failure is challenging as the dataset is often imbalanced with a low failure rate.The common approach to han-dle classification involving imbalanced data is to balance the data using a sampling approach such as random undersampling,random oversampling,or Synthetic Minority Oversampling Technique(SMOTE)algorithms.This paper compared the classification performance of three popular classifiers(Logistic Regression,Gaussian Naïve Bayes,and Support Vector Machine)in predicting machine failure in the Oil and Gas industry.The original machine failure dataset consists of 20,473 hourly data and is imbalanced with 19945(97%)‘non-failure’and 528(3%)‘failure data’.The three independent variables to predict machine failure were pressure indicator,flow indicator,and level indicator.The accuracy of the classifiers is very high and close to 100%,but the sensitivity of all classifiers using the original dataset was close to zero.The performance of the three classifiers was then evaluated for data with different imbalance rates(10%to 50%)generated from the original data using SMOTE,SMOTE-Support Vector Machine(SMOTE-SVM)and SMOTE-Edited Nearest Neighbour(SMOTE-ENN).The classifiers were evaluated based on improvement in sensitivity and F-measure.Results showed that the sensitivity of all classifiers increases as the imbalance rate increases.SVM with radial basis function(RBF)kernel has the highest sensitivity when data is balanced(50:50)using SMOTE(Sensitivitytest=0.5686,Ftest=0.6927)compared to Naïve Bayes(Sensitivitytest=0.4033,Ftest=0.6218)and Logistic Regression(Sensitivitytest=0.4194,Ftest=0.621).Overall,the Gaussian Naïve Bayes model consistently improves sensitivity and F-measure as the imbalance ratio increases,but the sensitivity is below 50%.The classifiers performed better when data was balanced using SMOTE-SVM compared to SMOTE and SMOTE-ENN.