The Development of a Performance Appraisal System Using Decision Tree Analysis and Fuzzy Logic

Abstract

Abstract:The establishment of highly qualified faculty has become the core work of human resource management in State Universities and Colleges. Also, faculty add value to higher education institutions and performance evaluation is the best way to keep track of them. This study presents the development of a performance appraisal system which aims at studying the HR specific to the educational environment and brings out the role of data mining in achieving quality enhanced development in its faculty. The researchers utilized CRISP-DM and Extreme Programming methodologies, focusing on generating models for the Decision Tree algorithm, combined with Fuzzy Logic Controller in predicting faculty performance. J48-generated IF-THEN rules is utilized in conjunction with FLC to predict individual or institutional faculty performance. Also, the generated output of the prototype meets substantial standards. Finally, main users found the system to be Very Acceptable through IS0/IEC 20510:2011 software quality tool.

When technology meets people: the interplay of artificial intelligence and human resource management

“…Managing performance refers to systematically specifying the performance goals and subsequently examining these goals' realization (Devanna et al, 1982). Being the next largest subcategory after staffing (n 5 12), it mainly discussed employee performance prediction (Huang et al, 2006;Jantan et al, 2009;Lamarca and Ambat, 2018;Lopes et al, 2018;Nazri et al, 2019). Apart from the prediction of employee performance, performance evaluation was also the subject of study in some of the articles, which was based either on comparative ranking (Moon et al, 2010;Paladini, 2009) or positive or negative factors influencing the performance (Akhondzadeh-Noughabi et al, 2016;Zhang et al, 2012).…”

“…Apart from the prediction of employee performance, performance evaluation was also the subject of study in some of the articles, which was based either on comparative ranking (Moon et al, 2010;Paladini, 2009) or positive or negative factors influencing the performance (Akhondzadeh-Noughabi et al, 2016;Zhang et al, 2012). A significant number of studies related to employee segments, namely, lawyers (Lopes et al, 2018), bank employees (Zhang et al, 2012), call center employees (Akhondzadeh-Noughabi et al, 2016) and academicians (Lamarca and Ambat, 2018;Nazri et al, 2019). Discussions on performance from an organizational perspective were meant to forecast how a group of HRM practices affects future organizational performance (Manafi and Subramaniam, 2015;Stavrou et al, 2007).…”

“…Data mining has been used for employee selection (Chien and Chen, 2008;Ranjan et al, 2008), performance evaluation (Akhondzadeh-Noughabi et al, 2016;Lamarca and Ambat, 2018;Nazri et al, 2019), competency evaluation (Danping and Jin, 2011), talent management (Jantan et al, 2009) and various other HR functions.…”

“…For any other element having a value between 0 and 1, this value shows the level of its belongingness to the set (Karatop et al , 2015). With these sets, fuzzy logic can quantify the data’s uncertainty and forecast future scenarios, which further facilitates decision-making (Lamarca and Ambat, 2018).…”

Data Stream Clustering Using Fuzzy-based Evolving Cauchy Algorithm

“…Several membership functions are used by researchers such as Gaussian, trapezoidal, triangular and others [22]. Furthermore, the membership functions can be coupled with a conjunction operator, this situation is known as t-norms [23]. In order to complete the implementation of designed model perfectly, any previous membership function don't use.…”