![](bg5.png)
for that good. We will consider bid displacement
factor ΔP as a fuzzy set of values p
1
,p
2
,……..p
n
,
assessment of the attributes A as a fuzzy set of
values a
1
,a
2
………a
n
and competition C as a fuzzy
set of values c
1
,c
2
,……..c
n
. According to Mamdani’s
Method for fuzzy relations and compositional rule of
inference the rule a
i
and cj→ pk can described by
µR(A,C,ΔP)= µa
i
(A)^ µc
j
(C )^ µp
k
(ΔP)
(8)
For n no. of rules, the compiled fuzzy relation R is
given as
R=R
1
UR
2
U……………..UR
n
For the input of fuzzy set A’ on A and fuzzy set C’
on C , the output fuzzy set ΔP’ on ΔP can be
obtained as follows
ΔP’=(A’andC’)o R=A’o (C’ oR)= C’o(A’oR)
(9)
And then the final price for the bid will be Final
bid= Current bid + ΔP’
3 CONCLUSIONS
In this paper we have designed a fuzzy attribute and
competition based bidding strategy (FAC-Bid),
which uses a soft computing method i.e. fuzzy logic
technique to compute the final bid price based on the
assessment of the attributes and the competition in
the market. Another unique idea presented in this
paper is that to deal quantitatively the imprecision or
uncertainty of multiple attributes of items to acquire
in auctions, fuzzy set technique is used. The bidding
strategy also allows for flexible heuristics both for
the overall gain and for individual attribute
evaluations. Specifically, the bidding strategy is
adaptive to the environment as the agent can change
the bid amount based its assessment of the various
attributes of item, and the competition in the auction
.The competition is calculated based on the number
of bidders and the time elapsed for the auction. It
was noticed that the strategies in which agent’s
behaviour depends on attributes and competition, are
easily adaptable to the dynamic situations of the
market. In future we will investigate about the
development of the bidding strategies for multiple
auctions. We will also compare our bidding
techniques with the other strategies to find out the
relative strengths and the weaknesses.
REFERENCES
Rahman, S. M, Robert J., 2001: Internet Commerce and
Software Agents: Cases, Technologies Opportunities,
Idea Group Publishing.
Murugesan, S., 2000.Negotiation by Software agents in
Electronic Marketplace, in:TENCON’00, Proceedings
of the 2000 IEEE Region 10 Conference on Intelligent
Systems and Technologies for the new Millennium,
Kuala Lumpur, Malaysia, pp.286--290.
Ma, H. Y., Leung, H. F., 2007: An Adaptive Attitude
Bidding Strategy for Agents in Continuous Double
Auctions. Electronic Commerce Research
Applications, 6 (4). Elsevier, 383—398.
Kwang, S. M., Wang, S. Y., 2004 In IEEE Transactions
on Systems, Man and Cybernetics- Part B:
Cybernetics. Vol.34, No.3.
Faratin, P., Sierra, C. and Jennings, N. R., 1998.
Negotiations decision functions for autonomous
agents, In International Journal of Robot Autonomous
System, Vol. 24, no.3, pp 159--182,.
Goyal, M. L., Jun, M., 2009. Using Agents’ Attitudes and
Assessments in Automated Fuzzy Bidding Strategy.
Proceeding of First International Conference on
Agents and Artificial Intelligence, Porto, Portugal.
Reddy, S. K., Dass, M., 2006.Modeling On-Line Art
Auction Dynamics Using Functional Data Analysis
Statistical Science Vol. 21, No. 2, 179--193 Institute
of Mathematical Statistics.
Bapna, R., Jank, W. and Shmueli, G., 2004. Price
formation and its dynamics in online auctions.
Working paper RHS-06-003, Smith School of
Business, Univ. Maryland (2004).
Tanaka, K., 1991. An Introduction to Fuzzy Logic for
Practical Applications, Axel Springer Verlag.
USING FUZZY SET APPROACH IN MULTI-ATTRIBUTE AUTOMATED AUCTIONS
85