A combined machine learning algorithms and Interval DEA method for measuring predicting the efficiency

One of the best methods for computing the efficiency of decision-Making Units (DMU) is Data Envelopment Analysis (DEA) that is useful for improving organizational performance. If we added a new unit to our observation sets, we have to run the model again. Nowadays, datasets from many organizations in the real world have been growing. So, we need a huge amount of computation for examining efficiency for new dataset. To overcome this problem, we combine Machine Learning (ML) and DEA. We consider organizations have interval data. According to we have interval data set, so we use interval DEA. Actually, we link between interval DEA and ML algorithms. First, we compute the efficiency score of these organizations by using Interval DEA. Second, we compute two scores that come in the first stage. Then, use these scores in ML. The empirical results show that the average accuracy of the predicted efficiency of DMUs is about 89%.