Research Project
Recruitment and Benchmarking
Research Goal
The primary aim of this project is to design, develop and test adaptive
learning technology for recruitment and benchmarking of sales and customer
service personnel in the Australian industry.
Funding
$35000
Acknowledgements
Business Intelligence Technologies, Siemens, and President Ford Pty. Ltd.
Problem Space
Most organizations rely on interview as the main strategy for recruiting
sales and customer service personnel. Product knowledge, verbal skills,
hard work, self-discipline, and personality are generally assumed to be
well taken care of in the interview process. However, it is difficult
to objectively determine a candidate’s selling or customer service
behavior during an interview. More so existing recruiting procedures do
not have adequate benchmarking techniques (e.g., How do you benchmark
a good salesperson?) The hiring decision is made under the constraints
of time, human subjectivity, and information quality which are as good
as candidate’s CV. Further, a few computerized systems based on
psychometric techniques are too general in their design, have mostly been
developed in countries outside Australia and do not cater well for Australian
culture and conditions. As a result, the existing recruiting procedures
though useful have met with limited success. The high sales person turnover
and stress levels on sales and customer service managers while on the
job are good indicators of the limited success of these procedures.
The incremental learning technology based on intelligent techniques like
neural networks, fuzzy logic and genetic algorithms will enable a computerized
system for sales and customer service personnel to adapt to the Australian
culture and changing needs of organizations on a continuing basis.
Demonstrations
An earlier version of the Sales Recruitment and Benchmarking systems ahs
been commercialised in the Australian Industry
Publications
[1] R. Khosla, I. Sethi and E. Damiani, Intelligent Multimedia Multi-Agent
Systems
A Human-Centered Approach (includes aspects related to socio-technical
systems), Kluwer Academic Publishers, Massachusetts, USA, October 2000,
333 pages
[2] R. Khosla and T. Goonesekera, “Knowledge Engineering of Intelligent
Systems
Using Multi-Agent Methodology,” to appear in proceedings of 14th
International Symposium on Methodologies for Intelligent Systems, LNCS/LNAI,
Springer- Verlag, Maebashi, Japan, October 2003
[3] R.Khosla and T. Goonesekera, “Predicting Selling Behaviour
Profiling Using
Soft Computing Agents,” to appear in ANZAM 2003, Perth, Australia,
December
2003
[4] R. Khosla, T. Dillon and A. Parhar, 'Synthesis of Knowledge Based
Methodology
and Psychology for Recruitment and Training of Salespersons', in Lecture
Notes in
Computer Science (LNCS), Springer-Verlag, 18th German Annual Conference
on
Artificial Intelligence , Saarbr"ucken, Germany, September, 1994
[5] R. Khosla and T. Dillon , 'A Knowledge Based Approach for Recruiting
Salespersons', Sixth Artificial Intelligence Technology Transfer Conference
in
Industry and Business}, Monterrey, Mexico, Sept. 1993, pp.83-9
[6] R. Khosla and T. Dillon, 'An Intelligent Assistant for Improving
Sales/Customer
Service Performance' - in IEEE Workshop on Customer Service and Support,
San
Jose, California, U.S.A, July 1992
|
