www.ijird.

com

March, 2015

Vol 4 Issue 3

ISSN 2278 0211 (Online)

Employee Performance Appraisal System Using Fuzzy Logic

Dr. V. Anbarasu
Associate Professor, Department of Information Technology, Jeppiaar Engineering College, Chennai, India
A. Jenitha
Student, Department of Information Technology, Jeppiaar Engineering College, Chennai, India
J. Jerin Yulit
Student, Department of Information Technology, Jeppiaar Engineering College, Chennai, India
Abstract:
Performance Appraisal is the systematic evaluation of the performance of an employee under certain aspects of consideration
and to understand the potential of a person for further growth and development of an employee in an organization with specific
ratings. This paper presents a design and implementation of a performance appraisal system using the fuzzy logic. It extracts the
performance of an employee at each level, thereby generating the ratings automatically with respect to the amount of work
completed by them. An automated employee rating system is used for this purpose to track the employee work performance. The
performance will be measured based on certain factors such as technical knowledge, quality and quantity of output, etc. Based
on these attributes, it automatically separates them into three categories such as high-level performers, mid-level and low-level
performers.
Keywords: Employee evaluation, fuzzy logic controller, performance appraisal and performance criteria, rating
1. Introduction
Performance Appraisal may be defined as a structured, formal interaction between a subordinate and a supervisor that usually takes
the form of a periodic interview (annual or semi-annual) in which the work performance of subordinate is discussed and examined to
identify strengths& weaknesses, opportunities for improvement and skills development. The main aim o0oof a performance appraisal
system is to identify the performance gap. This gap occurs when performance does not meet the standards set by the organization as
acceptable. Secondly, a feedback system is supposed to inform the employee about the quality of his/her performance. Fuzzy logic has
rapidly become one of the most successful of todays technologies for developing sophisticated control systems. The reason for which
is simple. Fuzzy logic addresses such applications perfectly as it resembles human decision making with an ability to generate precise
solutions from certain or approximate information. It fills a gap in engineering design methods left vacant by purely mathematical
approaches and purely logic-based approaches in system design. While other approaches have equations to model real world
behaviors, fuzzy design can handle the ambiguities of real-world human language and logic. It provides a method for describing
systems in human terms and automates the conversion of those system specifications into effective models. This paper presents
literature review, the methodology, the detailed system components, process workflow, recommended parts for future development
and conclusion.
2. Related Work
Fuzzy logic describes the qualitative nature aspects of the object while conventional logic systems focus on their quantitative aspects.
Two fuzzy approaches are used to construct performance appraisal. The first is the conventional fuzzy approach. This evaluates
overall rating from many linguistic fuzzy input variables without any intermediate fuzzy reasoning using if-then rules. In this
approach, it generates too many rules and it is difficult for the expert to take into account all aspects and formulates rules with accurate
weight. The organization may need to weight some factors such as employee safety observation over quantity, any critical element and
employee attitude. In this situation, the whole process will become extremely complicated.The function of designing inference rules
need to use customize high level language. The second approach defines the relationship between the performance critical elements
and accordingly specifies new large groups [1].These groups are used in fuzzy reasoning to determine intermediate parameter Work.
Similarly, Reliability and Relationship are used in fuzzy reasoning to determine intermediate parameter persons attitude and then
both group work and attitude are combined in second stage to build workattitude analysis which is then finally combined with

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 232

www.ijird.com

March, 2015

Vol 4 Issue 3

regulatory requirement like safety to generate the overall performance rating. This process is known as stagewise fuzz reasoning
where it will be possible & flexible to give different degree of weight to different performance group. The proposed application of
multifactorial evaluation was designed to be as a demonstrative example that inspires the application of one of the fuzzy set theory in
the multi-criteria performance appraisal system. C.C. Yee and Y.Y. Chen proposed a performance appraisal system using multifactorial evaluation model in dealing with appraisal grades, which are often expressed vaguely in linguistic terms [2]. Accordingly, a
performance appraisal system has been developed using performance appraisal criteria from information and communication base
company (Malaysia). The system uses multifactorial assessment model in helping top-level management to evaluate their
subordinates. In fuzzy interference technique [3],handling different kinds of vague data was proposed. It is reasoning based on fuzzy
models that replicate the way the people meditate and make judgments. As the result of evaluation, discrepancy in outcome is
observed between classes using traditional non-fuzzy method and the new proposed fuzzy method. The non-fuzzy traditional methods
follow the exact mathematical rules. The assessment for performance appraisal using fuzzy logic provides excellent flexibility. The
fuzzy logic was utilized as calculating technique to appraise the students academic performance. Performance appraisal system is
essential for evaluating the employees contribution to the organization. Most of the performance appraisal criteria are based on
quantitative, qualitative elements. The proposed fuzzy assessment methodology [4] specifies substantial assessment parameters and
presents system architecture that establishes a reliable assessment standard for smoothing a decision process. It is a comprehensive
method for managing vagueness inherent in performance appraisal. It is common to use discrete scales with sharp real values in the
evaluation process. The theory of fuzzy sets allows for the use of such linguistic fuzzy scales. The various scale values are expressed
linguistically and modeled by fuzzy numbers. The purpose of using the linguistic fuzzy modelling is an exact mathematic data
processing that excludes unwanted subjective influence. On the other hand, the expression of the expertly defined vague evaluations
using natural language [5]. The project was carried out in collaboration with one of the Information and Communication Technology
Company in Malaysia with reference to its performance appraisal process. Gin-Shuh Liang and Ming-Shin Kuo presented a
performance evaluation method for tackling fuzzy multi-criteria decision-making (MCDM) problems based on combining VIKOR and
interval-valued fuzzy sets [6]. To illustrate the effectiveness, a case study of this method for evaluating the performances of three
major intercity bus companies from an intercity public transport system is conducted. G Meenakshi proposed a Multi source feedback
or 360-degree feedback based performance appraisal system using Fuzzy logic and implemented it in academics especially
engineering colleges [7]. The 360 degree appraisal system includes self, superiors, subordinates, students and peers appraisal.
Adam Golec and Esra Kahya presented a comprehensive hierarchical structure for selecting and evaluating a right employee [8]. The
process of matching an employee with a certain job is performed through a competency-based fuzzy model. The main aim of
performance assessment is to reward an employee who achieves the organizational goals and to determine which goals are not
fulfilled, and to maintain plans to make sure they are achieved in future.
3. Methodology
Fuzzy logic that has been used in this paper is a superset of Boolean logic that has been extended to handle the concept of partial truthtruth values between completely true and completely false. A Fuzzy Inference System (FIS) is a way of mapping an input space to
an output space using fuzzy logic. It tries to formalize the reasoning process of human language by means of fuzzy logic (that is, by
building fuzzy IF-THEN rules). FIS make a decision and act accordingly. In general, a fuzzy inference system consists of four
modules: Fuzzification, Rule base, Inference engine, Defuzzification. Also, MySQL database was used to maintain the data.
4. System Components
4.1. Structure of a Fuzzy Logic Controller
Fuzzification: It transforms the system inputs (crisp numbers) into fuzzy sets by applying a fuzzification function.
Fuzzy Rule base: stores IF-THEN rules provided by experts.
Fuzzy Inference engine: It simulates the human reasoning process (by making fuzzy inference on the inputs and IF-THEN
rules).
Defuzzification: transforms the fuzzy set (obtained by the inference engine) into a crisp value.

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 233

www.ijird.com

March, 2015

Vol 4 Issue 3

Figure 1: Structure of Fuzzy Logic Controller

4.2. System Components List
This section demonstrates the application subprograms and functions related to it. The implementation for this system application
consists of five modules. Each module contains several applications as follows:
a. Inference Engine/System (Compute the output of the Mamdani model)
b. Performance Criteria Setting
c. Setting Functional Rules & Rules Report
d. Employee Performance Assessment Sheet & Evaluation Report
e. Employee Master Data: Performance Criteria Setting
4.2.1. Inference Engine/System
It consists of several sub-parts.. Each sub-parts computes one step in order to get the final result of the Mamdani model. The inference
engine module performs the following functions as given below:
1. Compute Relation (Min Operator or Algebraic product): This process computes the relations using MIN Operator or
algebraic product.
2. Compute Input (Input o R or Input x R): This process computes the outputs using the compositional rule of inference (Inputs
o Relation) with Sup-min operator or (Inputs x Relation) with Sup-product operator.
3. Aggregation (Max operator or Additive operator): This process calculates the final output by aggregating the outputs using
Max operator or the Additive operator (sum).
4. Defuzzification: This process computes the final output defuzzification using centroid for both methods.
4.2.2. Performance Criteria Setting
1. Define Appraiser- In this application; admin will be able to define Criteria types master data such as projects &soft skill.
Appraisal & objectives setting is one of the appraisal methods uses to evaluate employee where you need to define two types
of criteria: the employee objectives/projects for the specific period of time and the general requirements of employee soft
linguistic value. It also generates the required membership skill.
2. Define Criteria Type - enables the admin to define the criteria type.
3. Define Evaluation Criteria -In this application admin will define the criteria like attendance, training attended, conference
conducted, maintaining the file etc.
4. Define Scale (Linguistic Values)- In this application admin will be able to define the scale of the proficiency level which will
be used to evaluate the each criteria and the final employee evaluation.
5. Define Membership function - This part of the application allows you to set the degree of membership for each degree graph
for all linguistic values.
6. Define Setting Functional Rules & rules Report
Fuzzy inference system (FIS) allows you to set the calculation methods. (aggregation, defuzzification.)
4.2.3. Setting Functional Rules & Rules Report
The fuzzy inference engine (algorithm) combines fuzzy IFTHEN rules into a mapping from
fuzzy sets in the input space X to fuzzy sets in the output space Y based on fuzzy logic principles.In this window, Admin will be able
to maintain all fuzzy related rules. In our design, we use stage-wise fuzzy reasoning (group related critical factors). For example; the
element like Contributing to teamwork & Achieving Work Targets are combined to reflect Work Achievement.

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 234

www.ijird.com

March, 2015

Vol 4 Issue 3

4.2.4. Employee Performance Assessment Sheet & Evaluation Report

It allows appraisers to evaluate their subordinates as per agreed criteria and setting planned objectives.
4.2.5. Employee Master Data: Performance Criteria Setting
In this part of the application, HOD will be able to maintain the employee information (Employee Detail, Position, etc.)
5. Process Workflow
The process workflow of the performance Appraisal System in figure2 shows who and where the processes will be performed.
Therefore, it's easy to map the whole process, responsibilities, the roles and the interdependencies of a given individual or department.

Figure 2: Workflow of Performance Appraisal System

6. Experimental Results

Figure 3: Employee login

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 235

www.ijird.com

March, 2015

Vol 4 Issue 3

Figure 4

Figure 5: Employee Activities Details

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 236

www.ijird.com

March, 2015

Vol 4 Issue 3

EMPLOYEE PERFORMANCE RATING

LOGOUT
(Employee Ratings on the monthly basis activities)

EMPLOYEE NAME:

Ms.S.Geetha
PARAMETERS
ATTENDANCE
CONFERENCE
GUEST LECTURE
INDUSTRIAL VISIT
MAINTAINING FILE
SYMPOSIUM
TRAINING
ADDITIONAL
ACTIVITIES

POSITIVE

NEGATIVE

RATING :

GOOD

Figure 6

Figure 7: Employee Performance rating

The ratings for the employee will be given based on the inputs given by the employee. Figure3 shows that the employee must login
using his/her employee id to enter the inputs for each parameter. Figure 4 &5 shows the account of an employee where the employee
must enter the valid inputs. From these inputs, the system will automatically rate the employee and the system will generate appraisal.
For example the employee will enter the qualification, and as per the qualification the employee must enter other valid inputs such as

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 237

www.ijird.com

March, 2015

Vol 4 Issue 3

number of leaves taken, guest lectures attended, Industrial visits, etc. If the inputs are up to the mark then the system will rate
accordingly indicating that the performance is good. Similarly, if the inputs entered are not up to the mark, then the system will rate
accordingly indicating that the performace is poor and has to be improved. From figure. 6 and 7 the performance of an employee is
rated as per the given parameters. According to the diagram shown above, if the employee fulfills the criteria given for each
parameter, then the employee will be rated with green color indicating that he/she is on the safer side. Similarly, if the employee does
not fulfill the criteria for each and every parameter, then the employee will be rated with red color indicating that he/she is in danger
zone and thus the employee must improve his/her performance. For example, if attendance is taken into consideration, the employee
will be given a certain number of days for taking leave. If the employee takes leave equal to or less than the specified number of days
then he is on the safer side and the rating will be given accordingly which is indicated in green color. But if the employee exceeds the
number of days, then he will be in the danger zone, thereby the rating will also be reduced. Similarly the other parameters will also be
measured in the same manner. The ratings, which is specified above is nothing but the points which is given to employees in
accordance with performance, taking into considerations each and every parameter. Finally the appraisal will be generated based on
the ratings given above.
7. Conclusion
This paper demonstrates the application of fuzzy logic in the employee evaluation process.. The system has been implemented using
MySQL database which was used to maintain the data. Employee evaluation represents the decision which often involves subjective
information about them based on many parameters like responsibility, attitude, leadership qualities, communication skills,
commitment, creativity, etc. While evaluating an employee for such parameters the scores given by the reviewer are approximated as
they are based on judgment making ability of the reviewer. The use of fuzzy logic, allows them to express themselves linguistically
and to make assessments that are subjective in nature and helps represent a higher level of abstraction originating from our knowledge
and experience, thereby providing a simple way to draw definite conclusions from ambiguous, vague, imprecise information
8. Future Work
The proposed approach can be used for other domains like student evaluation, production evaluation or software quality assurance,
etc. with small modifications. Also extend the system to use a combination of more than one input. This system can also be extended
to be used in hospitals to evaluate the hospital management and thereby generating the appraisal for the employees in the hospital by
taking certain parameters into consideration.
9. References
1. Adnan Shaout and Jaldip Trivedi, Performance Appraisal System Using a Multistage Fuzzy Architecture, International
Journal of Computer and Information Technology (ISSN: 2279 0764)Volume 02 Issue 03, May 2013
2. C.C.Yee, and Y.Y.Chen, Performance Appraisal System using Multifactorial Evaluation Model,International Journal of
Human and Social Sciences 5:12 2010
3. Shruti S Jamsandekar, R.R Mudholkar, Performance Evaluation by Fuzzy Inference Technique,International Journal of
Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-3,Issue-2, May 2013
4. Nisha Macwan1, Dr.Priti Srinivas Sajja2, Performance Appraisal using Fuzzy Evaluation
Methodology, International Journal of Engineering and Innovative Technology (IJEIT) Volume 3,Issue 3, September 2013
5. B. Zemkova, J. Talasova, Fuzzy Sets in HR Management, Acta Polytechnic Hungarica, vol. 8, no.3, pp.113- 124, 2011.
6. Ming-Shin Kuo, Gin-Shuh Liang, A Soft Computing method of performance evaluation with MCDM based on intervalvalued fuzzy numbers, Applied Soft Computing, vol. 12, no. 1, pp.476-485, Jan. 2012.
7. GMeenakshi, Multi source feedback based performance appraisal system using Fuzzy logic decision support system,
International Journal on Soft Computing ( IJSC ), vol.3, no.1, pp. 91-106, Feb. 2012
8. A. Golec, E. Kahya, A fuzzy model for competency based employee evaluation and selection, Computers and Industrial
Engineering, vol. 3, no.1, pp. 143-161

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH & DEVELOPMENT

Page 238