The week's pick
Reseach Article
Expert System based on Back propagation Network for evaluating Motivational Strategies on Human Resources
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 2 - Number 3 |
| Year of Publication: 2012 |
| Authors: Viral Nagori, Bhushan Trivedi |
10.5120/ijais12-450295
|
Viral Nagori, Bhushan Trivedi . Expert System based on Back propagation Network for evaluating Motivational Strategies on Human Resources. International Journal of Applied Information Systems. 2, 3 ( May 2012), 27-33. DOI=10.5120/ijais12-450295
Abstract
The employee turnover ratio is comparatively very high in Information Technology industry. Because of time constraint, HR managers are not able to identify the preferences of each employee in the process of designing motivational strategies. Hence, there is need for an expert system, which can help HR managers in designing motivation strategies. We are working on development of expert system on Human Resource domain, which can help in reducing employee turnover ratio by knowing the employee's preferences on motivational strategies. Evaluation of motivational strategies is a real world problem where we try to evaluate whether an employee will prefer motivational strategies or not. It is extremely difficult to generalize the employees' preferences on motivational strategies, and when generalization is difficult, literature suggest that back propagation network is the best-suited method. The paper presents the use of back propagation network for developing an expert system for evaluating motivational strategies on human resources. We use MATLAB for implementing our Expert system based on Back propagation algorithm. The personal data of around 200 employees are collected from six companies to form an input. Current implementation is a prototype with two motivational strategies is evaluated. The output would be yes or not for each motivational strategy for each individual employee. The yes indicates that employee will prefer the motivational strategy, and no indicates that employee will not prefer the motivational strategy. The back propagation network used the record set of 200 employees for learning. Then we tested additional 20 records based on the weight set generated while learning. We repeated the entire process twice to compare the results for accuracy and consistency. To generate two different weight set, we make algorithm learn on the same input record set twice. We observed 85% to 90% consistency while comparing the results for both motivational strategies. It indicates that employees' preferences are correctly identified in favour of motivational strategies by using our expert system. The record set used as an input has private and confidential information of employees, so we are not in a position to disclose those details in the paper.
References
- chakraborthy, R. (2010, August 10). http//www. myreaders. info/html/soft_computing. html. Retrieved Jan 26, 2012, from www. myreaders. info: http//www. myreaders. info/html/soft_computing. html
- Elaine Rich, K. K. (2009). Artificial Intelligence. The Mcgraw Hill Companies.
- F. D. Nittis, G. T. (1998). Consumer Loan classifcation using Artificial Neural Network. ICSC EIS, Spain .
- Jamshid Nazari, O. E. (1992). Implementation of back propagation Neural network with MATLAB. ECE Technical reports, Purde univeristies.
- Nagori, V. (2007). Analysis of impementation of incentive strategies based on motivational theories in the Indian IT inudstry. Indian conference on management. Gandhinagar.
- Nagori, V. (2009). Training and development activities: A tool for employee retention, analysis of SME of Indian IT industry. National conference on transforming present economic challenges into global prosperity. Idnore: Maharaja Ranjit singh college of professional science.
- Negnevitsky, M. (2008). Artificial Intelligence - A guide to Intelligent systems. Pearson Education.
- Networks, A. N. (2007). Artificial Neural Networks. Retrieved 2 11, 2012, from learn artificial neural networks: http://www. learnartificialneuralnetworks. com
- Norgarrd, M. (2001, June). Motivating people. Executive excellence , p. 19.
- Padhy, N. (2005). Artificially Intelligence and Intelligent systems. Oxford press.
- Sharda, R. W. (1994). Bankruptcy prediction using neural networks. Decisin support system , 545-557.
- Swansor, R. (2001). The Challenge facing human resource development profession. AHRD Annual Conference.
- Viral Nagori, D. B. (Dec, 2011). Expert system implemented for problem solving on commrece/ business domain. National journal of system and information Technology , 132-142.
- Zhang Zhiyu, L. X. (2010). Customer relationship evaluation systm based on BP neural network in electroonic commerce. E- business and E-Government (pp. 3098-3101). Guangzhou : ICEE.
Index Terms
Keywords