• Aug 25, 2016 News!Vol.4, No.3 has been published with online version. 15 peer reviewed articles from 3 specific areas are published in this issue.   [Click]
  • May 03, 2016 News!Vol. 3, No. 3 has been indexed by EI (Inspec).   [Click]
  • May 03, 2016 News!Vol. 3, No. 2 has been indexed by EI (Inspec).   [Click]
General Information
    • ISSN: 2301-3559
    • Frequency: Quarterly
    • DOI: 10.18178/LNSE
    • Editor-in-Chief: Prof. Jemal Antidze
    • Executive Editor: Ms. Cherry L. Chen
    • Abstracting/ Indexing: EI (INSPEC, IET), DOAJ, Electronic Journals Library, Engineering & Technology Digital Library, Ulrich's Periodicals Directory, International Computer Science Digital Library (ICSDL), ProQuest and Google Scholar.
    • E-mail: lnse@ejournal.net
Editor-in-chief
Prof. Jemal Antidze
I. Vekua Scientific Institute of Applied Mathematics
Tbilisi State University, Georgia
I'm happy to take on the position of editor in chief of LNSE. We encourage authors to submit papers concerning any branch of Software Engineering.

LNSE 2016 Vol.4(3): 184-188 ISSN: 2301-3559
DOI: 10.18178 /LNSE.2016.V4.247

Human Resource Utilization Analysis and Recommendations Using Software Analytics

Subhash Ajmani, Satya Sai Prakash K., and D. S. U. M. Prasad
Abstract—Software organizations induct employees belonging to diverse backgrounds with varied work experience. Resources work on different projects with varied complexity. We propose a formalism to identify the significant parameters that contribute to evaluate the resource utilization and contribution in the projects. Proposed formalism was tested with a sample project data consisting of 23 employees, 11 measured parameters across 10 product releases. Parameters such as individual effort, product level experience, defect percentile, complexity level, and manager rating have been captured for each release. Once data is pre-processed, principal component analysis (PCA) and K-means clustering were used to assess the relative association of employees based on experience to complexity. The PCA analysis helped in identifying two parameters i.e., ‘product level experience’ and ‘defect percentile’ that captures the major variation in the data. In addition, k-means provided 3, 5, and 9 clusters for further investigation. This analysis helped in identifying the impact of various parameters such as product level experience, project complexity etc. on resource utilization. Based on the present analysis recommendations could be made for future resource allocation and areas of improvement.

Index Terms—Human resource utilization analysis, K-means clustering, principal component analysis, software analytics.

The authors are with HCL Technologies Hyderabad, India (e-mail: subhash-a@hcl.com, satyasaiprakash.k@hcl.com, prasad@hcl.com).

[PDF]

Cite:Subhash Ajmani, Satya Sai Prakash K., and D. S. U. M. Prasad, "Human Resource Utilization Analysis and Recommendations Using Software Analytics," Lecture Notes on Software Engineering vol. 4, no. 3, pp. 184-188, 2016.

Copyright © 2008-2015. Lecture Notes on Software Engineering. All rights reserved.
E-mail: lnse@ejournal.net