Abstract:

computerbecome an essential component in all the domains including health care. Liver disorder is one of the extremelife-threatening medical conditionthatcompete with cancer and leading death cause in us. More than 10 percent of the american population are affected by liver disorders due to heavy alcohol consumption and unhealthy food habits. Prediction of liver disorders helps in patient diagnosis to increase the survival. In this paper, we analyze the liver disorder datasetgradient boosting and random forest algorithm and compare their performance in terms of accuracy and error.

Keywords—big data,apache spark, machine learning , random forest and gradient booster algorithms.;