750 The International Arab Journal of Information Technology, Vol. 17, No. 5, September 2020 Performance Evaluation of Industrial Firms Using DEA and DECORATE Ensemble Method Hassan Najadat 1 , Ibrahim Al-Daher 2 , and Khaled Alkhatib 1 1 Computer Information Systems Department, Jordan University of Science and Technology, Jordan 2 Computer Science Department, Jordan University of Science and Technology, Jordan Abstract: This study introduces an approach of combining Data Envelopment Analysis (DEA) and ensemble Methods in order to classify and predict the efficiency of Decision Making Units (DMU). The approach includes applying DEA in the first stage to compute the efficiency score for each DMU, then a variables’ ranker was utilized to extract the mos t important variables that affect the DMU’s performance, then J48 was adopted to build a classifier whose outcomes will be enhanced by Diverse Ensemble Creation by Oppositional Relabeling of Artificial Training Examples (DECORATE) Ensemble method. To examine the approach, this study utilizes a dataset from firms’ financial statements that are listed on Amman Stock Exchange. The dataset was preprocessed and turned out to include 53 industrial firms for the years 2012 to 2015.The dataset includes 11 input variables and 11 output ratios. The examination of financial variables and ratios play a vital role in the financial analysis practice. This paper shows that financial variable and ratio averages are points of reference to evaluate and measure firms’ future financial performance as well as that of other similar firms in the same sector. In addition, the results of this work are for comparative analyses of the financial performance of the industrial sector. Keywords: Data Envelopment Analysis, Decision Trees, Ensemble Methods, Financial Variables, Financial Ratios. Received October 12, 2019; accepted April 8, 2020 https://doi.org/10.34028/iajit/17/5/8 1. Introduction It is widely believed in the field of finance that future financial performance of firms can be determined, or at least forecasted, relying on their performance in the previous years. The examination of financial variables and ratios, which are normally collected from firms’ financial statements and reports play a vital role in the financial analysis practice. Financial variables and ratios collected over different years can be useful as they provide information on the firms’ sales, profitability, cash, and liquidity. More specifically, financial variable and ratio averages represent a point of reference to evaluate and measure firms’ future financial performance as well as that of other similar companies in the same sector. Moreover, financial variables and ratios are used to predict the success or failure of a particular firm. In addition, they are used for comparative analyses of the financial performance of different sectors such as the industrial sector. Despite the clear importance of financial predictions, this process is not an easy task, and it has formed a challenge for many researchers and practitioners. One reason for that is the variation in the empirical results. The variation in predicting results of firms’ performance is attributed to the use of different financial variables and Ratios. Even using a single financial variable or ratio to predict the firms’ performance, it may yield some variation due to the different potential directions and capabilities of the predicting process. The prediction of firms’ performance requires processing datasets that contain a group of firms as well as their financial variables and ratios over a particular number of previous years. This necessitates the use of analytical/statistical computer algorithms, softwares and techniques. One of these techniques is the Data Envelopment Analysis (DEA), which is a mathematical programing model that has several applications in various domains. For example, it has been employed in IT risk assessment [15]. DEA is also widely used in measuring the performance of Decision Making Units (DMUs) especially when the comparisons become difficult because of the presence of multiple inputs and outputs for the organizational units during the measuring relative performance task for these units [12]. It is also used for measuring the efficiency based on multiple inputs and multiple outputs for different DMUs. These DMUs could be departments, firms, institutions or any comparable units in any sector (e.g., hospitals, universities, banks and firms). The simple efficiency equation represents the ratio of the outputs of the desirable DMU to the input for that DMU, as illustrated in Equation (1).  =   Data mining techniques are also used in analyzing datasets in the field of finance. The ensemble methods are learning algorithms that construct a set of (1)