Best Customer Selection Decision Support System With Elimination And Choise Translation Reality (Electre) Method

Currently, many companies still use manual in doing any one of them is an office job CV. Independent cooperative. Based on the results of research on the CV. Koperasi Mandiri to determine the best customer still does not have a conventional and special methods and are less effective. Based on the results of this research make customer Election Decision Support System Best with ELECTRE method. Where the method ELECTRE perform testing based on criteria sort by value and ranking obtained using pairwise comparison of alternatives based on any appropriate criteria.


Introduction
Advances in information technology is growing in all aspects of life in its application can facilitate the job of man, and the more opportunities and challenges within an organization or company to obtain its objectives. One important factor that is fundamental to achieve the goal of a company is the role of the Human Resources (HR) quality and high performance that was instrumental in the company to achieve the objective, therefore, companies need to know and evaluate how much potential Human Resources owned and continually strive to improve the quality of Human Resources (HR), which can be measured from the performance appraisal customer to choose the best customers.
CV. Koperai Mandirione of the lending and borrowing located at Jl. Pemasyaraktan cape gusta Terrain Yang has customers with an unlimited number. In the selection of the best in the Company's customers obtained by the assessment team that is a leader directly based on criteria specified by the Company. The problems that exist in the company to determine client selection best is conventional and does not have special methods to resolve this problem and selection of election nasaah best is still less effective, so the authors would like to help in the process of data processing will be constructed decision support system for client selection the best method ELECTRE.

Decision Support Systems (DSS)
McLeod DSS is a system producing information aimed at a problem that must be made by the manager, untukmempermudahpekerjakaryawan. (Dr.Heny Pratiwi 2016). Moore and Chang (2014), CMS can be described as a system capable of supporting the data analysis and decision modeling, decision-oriented, the orientation of future planning and are used at times of unusual .. Radiant and colleagues (2016) DSS is an interactive system which supported the decision in the decision making process through alternatives derived from the processing of data, information and design of the model.

Methods ELECTRE
ELECTREis one of multiple criteria decision making method based on the concept of outranking using pairwise comparison of alternatives based on any appropriate criteria. (Dr.Heny Pratiwi, 2016). The procedure is done to solve the problem using ELECTRE method is as follows a. Normalizing the decision matrix.
Thus obtained R result of normalization, R = To determine the value of the elements in concordance matrix is by adding weights are included in the set of concordance, is mathematical is as follows: = ∈ 2) Calculating the matrix disordance To determine the value of the elements in the matrix disordance is by dividing the maximum difference of criteria which included into subsets disordance with a maximum difference in the value of all the criteria, it mathematically is as follows:

3) Determine the dominant matrix of concordance and disordance e. Calculating the dominant matrix concordance
The matrix F as dominant concordance matrix can be constructed with the aid of a threshold value, ie by comparing each value of the matrix element concordance with the threshold value. And elements of the matrix G is determined as follows: Determining aggregate matrix dominance. Specifying E as aggregate dominance matrix is a matrix which each element is the multiplication between the matrix elements F with the corresponding elements of the matrix G, mathematically can be expressed as: = x , g. The elimination of the less favorable alternative.
The matrix E gives the preferred order of each alternaatif, namely when = 1 then the alternative is better than the alternative. Thus, rows in a matrix E which has the fewest number = 1 can be eliminated. Thus, the best alternative is that dominates other alternatives. Rating determine the suitability of each alternative on each criterion, rated with one to five, namely: 1 = very poor 2 = 3 = 4 = Pretty Good 5 = Very good. The table below shows the rating the suitability of each alternative on each criterion.rating suitability for each criterion are shown in Table 2 to Table 6.  In this study, the sample data used as an alternative best prospective customer to perform manual calculations with ELECTRE method. In the selection of the best customers and showed the value of each alternative on the criteria of each sample are shown in Table 7. The stages in the process of ELECTRE are steps in the run using ELECTRE methods are:

a. Normalization Decision Matrix
At this stage of the normalization of the decision matrix as in equation (2.1   Then the user will be determining the weights for each criterion. Examples of weight values that the user entered example is as follows:

g. Alternative Elimination Less Favorable
The matrix E gives the order of selection of each alternative, ie when Ekl Ak = 1 then the alternative is a better alternative than Al. Thus, rows in a matrix E which has a number Ekl = 1 at least be in the elimination. Thus the first line, second, and fourth lines can be eliminated and the remaining third. Rated E32 = 1 indicates that the third alternative is better than the alternative of unity, second, and fourth. So that the decision makers will take the third alternative (3).

Conclusion
Under the background of the research is to find problems in the CV. Cooperative Independent difficult to determine the best customers. So with that penulisakan offers a method of decision-making system with ELECTRE method. Based on the results of the implementation and testing system in ELECTRE Decision Pendukukung able melesaikan problem of selecting the best customers. In this system uses four customers in each test -each acquire a different value -different and still define two customers liveable best customers based on the ranking that was obtained from the calculation system.