Staff View: Determining the best-FIT programmers using prognostic attributes / Sorada Prathan

Determining the best-FIT programmers using prognostic attributes / Sorada Prathan

The software development industry depends significantly on human capital to maintain competitiveness through the development of quality software systems and project a company’s operational and service excellence. However, software companies find it difficult to identify and employ the best-fit compu...

Full description

Saved in:

Bibliographic Details
Main Author:	Sorada , Prathan
Format:	Thesis
Published:	2018
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://studentsrepo.um.edu.my/10811/2/Sorada_Prathan.pdf http://studentsrepo.um.edu.my/10811/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.stud.10811
record_format	eprints
spelling	my.um.stud.108112021-06-15T19:40:13Z Determining the best-FIT programmers using prognostic attributes / Sorada Prathan Sorada , Prathan QA75 Electronic computers. Computer science The software development industry depends significantly on human capital to maintain competitiveness through the development of quality software systems and project a company’s operational and service excellence. However, software companies find it difficult to identify and employ the best-fit computer programmers. This research is aimed at using a data mining technique to identify the best-fit programmers who fulfil the relevant eligibility criteria. The best-fit programmers were predicted using both the Bayes’ Theorem and Artificial Neural Network (ANN). The predicted best-fit programmers were compared to the good programmers who were identified based on the past annual performance appraisal results of two software companies in India. The datasets from the two companies (Company 1 and Company 2) covered the years 2010-2015. The Bayes’ Theorem was used to analyse the relevant programmer’s attributes, while, the Artificial Neural Network (ANN) was used to predict the best-fit programmers. The research established that the Bayes’ Theorem is useful in recognising the prognostic attributes of the best-fit programmers for software companies while Artificial Neural Network (ANN) classifier was effective in the predicting the best-fit programmers. Using a confusion matrix, the Artificial Neural Network (ANN) classifier performance is 97.2% and 87.3%, 95.8% and 54.5%, and 100% and 75% with regard to accuracy, precision, and recall on the two test datasets of Company 1 and Company 2, respectively. The results are satisfactory enough to introduce a new technique to identify relevant attributes for predicting the best-fit programmers. Software companies can use this technique in their recruitment and selection process to determine the best-fit employees for the programmer posts. The proposed technique can be adapted to be applied in other disciplines such as sports, education, etc, to identify and employ the most suitable person to fill a particular position. 2018-11 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/10811/2/Sorada_Prathan.pdf Sorada , Prathan (2018) Determining the best-FIT programmers using prognostic attributes / Sorada Prathan. Masters thesis, University of Malaya. http://studentsrepo.um.edu.my/10811/
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Student Repository
url_provider	http://studentsrepo.um.edu.my/
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Sorada , Prathan Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
description	The software development industry depends significantly on human capital to maintain competitiveness through the development of quality software systems and project a company’s operational and service excellence. However, software companies find it difficult to identify and employ the best-fit computer programmers. This research is aimed at using a data mining technique to identify the best-fit programmers who fulfil the relevant eligibility criteria. The best-fit programmers were predicted using both the Bayes’ Theorem and Artificial Neural Network (ANN). The predicted best-fit programmers were compared to the good programmers who were identified based on the past annual performance appraisal results of two software companies in India. The datasets from the two companies (Company 1 and Company 2) covered the years 2010-2015. The Bayes’ Theorem was used to analyse the relevant programmer’s attributes, while, the Artificial Neural Network (ANN) was used to predict the best-fit programmers. The research established that the Bayes’ Theorem is useful in recognising the prognostic attributes of the best-fit programmers for software companies while Artificial Neural Network (ANN) classifier was effective in the predicting the best-fit programmers. Using a confusion matrix, the Artificial Neural Network (ANN) classifier performance is 97.2% and 87.3%, 95.8% and 54.5%, and 100% and 75% with regard to accuracy, precision, and recall on the two test datasets of Company 1 and Company 2, respectively. The results are satisfactory enough to introduce a new technique to identify relevant attributes for predicting the best-fit programmers. Software companies can use this technique in their recruitment and selection process to determine the best-fit employees for the programmer posts. The proposed technique can be adapted to be applied in other disciplines such as sports, education, etc, to identify and employ the most suitable person to fill a particular position.
format	Thesis
author	Sorada , Prathan
author_facet	Sorada , Prathan
author_sort	Sorada , Prathan
title	Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
title_short	Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
title_full	Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
title_fullStr	Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
title_full_unstemmed	Determining the best-FIT programmers using prognostic attributes / Sorada Prathan
title_sort	determining the best-fit programmers using prognostic attributes / sorada prathan
publishDate	2018
url	http://studentsrepo.um.edu.my/10811/2/Sorada_Prathan.pdf http://studentsrepo.um.edu.my/10811/
_version_	1738506413778403328
score	13.211869

Determining the best-FIT programmers using prognostic attributes / Sorada Prathan

Similar Items