Manpower projection of the information technology sector using neural networks

Pao Yue-kong Library Electronic Theses Database

Manpower projection of the information technology sector using neural networks

 

Author: Suen, Gar-yun Garry
Title: Manpower projection of the information technology sector using neural networks
Degree: M.Sc.
Year: 1998
Subject: Electronic data processing personnel -- Supply and demand -- Computer simulation
Information technology -- Employees -- Supply and demand -- Computer simulation
Neural networks (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Pages: v, 104 leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1421122
URI: http://theses.lib.polyu.edu.hk/handle/200/344
Abstract: This dissertation aims at developing a neural network (NN) model that can learn and project manpower of the information technology (IT) sector for the years ahead based on previous years performance factors/variables (such as IT vacancy rate, IT manpower growth rate, IT wastage rate, emigrant growth rate, economic growth rate, wages/earnings index, labour force participation rate, and employment growth rate) which might have an influence on the IT manpower requirement. The effectiveness of the NN model is evaluated by the comparison of the statistical model in relation to earlier IT manpower survey data and its forecast. The statistical model is developed using Pascal language whereby the random fluctuations in past data can be effectively smoothed out by the weighted exponential process to give a trend. An adaptive filtering method is used to devise an optimum solution for manpower projection in the IT sector. Both neural network and statistical models are amenable to processing by an IBM-compatible personal computer whereby the optimum trend (i.e. minimum absolute or mean squared error) can be obtained automatically, and the forecast can otherwise be optimized to suit decisions based on assumption of future market trends or other relevant information. The time series and the computational speed in both methods are described and compared. By going through the whole process of system development, the neural network and statistical models can be deeply understood and investigated. Advantages and risks of using these models will also be discussed in this dissertation. As IT is a rapidly changing and developing field, an accurate manpower projection model is required by the government and other organizations, together with other relevant information, for the formulating of IT education policies and plans. Other than the prediction on rise and fall of companies, products and technologies, I believe the underlining trends in the growth of IT manpower will continue as described in this dissertation.

Files in this item

Files Size Format
b14211221.pdf 3.083Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information