This word extends the DBA method to a large number DMU evaluation process, called "DEA assessment machine", for evaluating consecutive data. The authors identify the intersection form of the production possibility set for a given set of DMUs, which is called "training set". The process can then easily assess a newly coming DMU for its different properties, such as technical efficiency, returns to scales and evidence of congestion, by simply checking on a set of linear inequalities. It thus provides an efficient and effective method for dealing with large number of data and can be regarded as a complementary approach for data mining