E-COMMERCE NEGOTIATION BASED ON ARTIFICIAL INTELLIGENCE

Abstract

Negotiation is the emergent functionality of automated E-Commerce. There are several approach deployed by various researcher in there automated E-Commerce model. In this research review paper we provide a review on various negotiation mechanism which are deployed in various E-Commerce model

Full text

242 | P a g e
E-COMMERCE NEGOTIATION BASED ON
ARTIFICIAL INTELLIGENCE
Dinesh Kumar Singh1, R.K.Srivastava2
1,2Faculty of Computer Science & Information Technology, DSMNR University Lucknow, UP, (India)
ABSTRACT
Negotiation is the emergent functionality of automated E-Commerce. There are several approach deployed by
various researcher in there automated E-Commerce model. In this research review paper we provide a review
on various negotiation mechanism which are deployed in various E-Commerce model
Keywords: Negotiation, Agent, multi-agent trust, Data mining, Co-operation.
I. INTRODUCTION
E-Commerce negotiation is one of the established processes for an interaction between a buyer and a seller to
reach at an agreement stage where both of them are at profitable state of business. Various classical as well as
modern intelligent computing methods such as knowledge based systems (KBS), case based reasoning (CBR),
artificial neural network (ANN) and genetic algorithm (GA) have been deployed to implement the various steps
in a negotiation process. Multi agent systems (MAS) have also been used to represent the buyers and sellers as
agents and the broker as a coordinator agent. In this model the job of the coordinator agent is to take the
required items of the buyer agent and to find out the proper seller agent(s) who can supply the items to satisfy
the constraints on the requirement of the buyer agent as well as on the seller agents in supply of the items. The
buyer agent constraints are related with price, quality, quantity, brand, payment mode etc. The seller agent
constraints are related with the price and quality (Jennings 2003). Negotiation is needful business activity and
important part of traditional business or in e-commerce but it has not been extensively discussed in both types of
business and no adequate tools are available. In the present study, we have paid attention to the cognitive
parameter such as preference, desire, intention, commitment, capability, trust etc. as cognitive parameters for the
selection of buyer and seller agents. Many different approaches for the selection of buyer agent have been
reported in the literature. These approaches differ in procedures, technologies and methods. Each approaches
cannot be used for complete cognitive parameters based agent selection and classification for negotiation in B2C
e-commerce. This paper is based on the negotiating paradigm between buyer agents and seller agents through
broker agent and customer orientation based selection of potential buyer agent for valuable seller agent for
negotiation in e-commerce. We will describe the application of cognitive parameters based agent selection for
negotiation in the purchase domain in a cooperative system. In this domain the buyer agent has a set of seller
agent fulfill the buyer agent‟s requirements and set of seller agent fulfill the buyer agent‟s requirements through
cooperative negotiation mechanism. We will further describe customer orientation based Multi-agent system in
negotiation process. The customer orientation is of three type domains: profit centric, customer understanding,
and customer relationship for selecting the most profitable buyer agent for potential seller agent. Further we

243 | P a g e
have made a study to determine the rules, importance of the cognitive and business parameters such as
preference, commitment, intention, desire, price, payment mode, quantity and quality and address mode etc.,.
For classification and categorization of profitable buyer agents and potential seller agents using data mining
(DM) techniques like ANN, C&RT and feature selection method. Finally we will try to develop trust building
strategies using data mining method integrated multi-agent system for cooperative and competitive e-market
with the help of logical combination of predictive results of features selection, and computational results.
II. NEGOTIATION
Basically negotiation studied as behavioural science and it is involved in e-commerce in narrow perspective of
new market. Objective of business negotiation is to obtain the combination of choices for the different issues
like low price, high quality and short delivery time that will promote the business to increase market share and
profit after evaluating the available offer. Negotiations involve various activities between buyer and sellers to
interact and exchange their information. The outcome of the negotiation is a formal agreement between buyers
and sellers followed by purchase order placement and maintain the relation between both of them. There are
mainly three steps of negotiations, that are fixed the objective, discussion on different issues of negotiation and
compromise on issue for final mutual agreement between buyers and sellers.
There are two types of negotiation involved in e-commerce that is distributive negotiation and integrative
negotiation. Distributive negotiation initiated with objective of each party with strong opposition. In a simple
way this type of negotiation is bargain over each issue one by one in order to get the best settlement as
acceptable offer. In integrative negotiation all the issues and options are raised during negotiations which are
only cause of different issues developed during discussion of negotiations.
III. TYPES OF B2C AGENT INVOLVE IN VARIOUS NEGOTIATION
Agents are people who represent the interests of the principal decision makers. They act on the principal's behalf
with varying degrees of authority. They are employed in negotiations specifically because of their expertise,
specialized knowledge, and experience.
3.1 Independent Agents
Independent agents must be compensated for their services [16]. Many of these independent agents earn their
income through commissions. The more an agent sells, then the more they earn in commission. It is not
uncommon for an independent agent to inflate the sale to increase their commission. Independent agents are also
interested in the enhancement of their professional reputation. Obviously these agents desire, to not only attract
more clients, they want to get the best clients. Some examples would include a real estate agent, or a broker who
negotiates the buying and selling of goods and services on behalf of another party.
3.2 Non Independent Agents
This type of agent works directly for a company or organization. An example „would be a company's purchasing
department whose staff negotiates the lease or acquisition of supplies or equipment [16]. Another example
would be a union representative acting on behalf of a union. The agent's know-how is clearly the most
constructive reason why they are employed by decision makers to best represent their interests. The other side of
the coin reveals that agents may have other self-serving interests of their own. These contrary interests might be

244 | P a g e
in conflict with the aims of the people who engage their services. Let's unravel this tangle. So that we are aware
of potential contrary interests that agents might bring to the table.
3.3 Intelligent Agents
In this type of agent we attempt to achieve one-to-many negotiation by conducting a number of coordinated
simultaneous one-to-one negotiations. The previous version (Kowalczyk and Bui 2000) was directed at
facilitating one-to-one multi-attribute negotiation. In our current prototype, a number of agents, all working on
behalf of one party, negotiate individually with other parties. Each agent conducts a direct negotiation with a
prospective seller or buyer. After each negotiation cycle, these agents report back to a coordinating agent which
evaluates how well each agent has done and issues new instructions accordingly. Each individual agent conducts
its reasoning by using constraint-based techniques for evaluating and generating offers. The intelligent agents
autonomously negotiate multi-attribute terms of transactions in an e-commerce environment tested with the
personal computer trading problem.
3.4 Software Agents
A software agent is a piece of software that functions as an agent for a user or another program, working
autonomously and continuously in a particular environment [16]. It is inhibited by other processes and agents,
but is also able to learn from its experience in functioning in an environment over a long period of
time.Software agents offer various benefits to end users by automating repetitive tasks. The basic concepts
related to software agents are:
1. They are invoked for a task.
2. They reside in "wait" status on hosts.
3. They do not require user interaction.
4. They run status on hosts upon starting conditions.
5. They invoke other tasks including communication.
There are a number of different software agents,Including:
3.4.1 Buyer Agents
These agents revolve around retrieving network information related to good and services.
3.4.2 Monitoring and Surveillance Agents
These agents observe and report on equipment.
3.4.3 Data-Mining Agents
These agents find trends and patterns in many different sources and allow users to sort through the data to find
the information they are seeking.
3.5 Interface Agents
An interface agent to be a program that can also affect the objects in direct manipulation interface, but without
explicit instruction from the user [16]. The interface agent reads input that the user presents to the interface, and
it can make changes to the objects the user sees on the screen, though not necessarily one-to-one with user
actions. The agent may observe many user inputs, over a long period of time, before deciding to take a single
action, or a single user input may launch a series of actions on the part of the agent, again, possibly over an
extended period of time. An interface agent could be considered to be a "robot" whose sensors and effectors are
the input and output capabilities of the interface and for that reason are sometimes also referred to as "softbots".

245 | P a g e
Sometimes the interface agent is actually represented anthropomorphically as a face on the screen, such as in the
Apple film Knowledge Navigator.
3.6 Autonomous Agents
An autonomous agent is an agent program that operates in parallel with the user. Autonomy says that the agent
is, conceptually at least, always running [16]. The agent may discover a condition that might interest the user
and independently decide to notify him or her. The agent may remain active based on previous input long after
the user has issued other commands or has even turned the computer off.
IV. TYPES OF NEGOTIATION IN B2C E-COMMERCE
4.1 Automated Negotiation
T. Bosse stated that automated negotiation plays an important role in dynamic trading in e-commerce. Its
research largely focuses on negotiation protocol and strategy design. There is a paucity of further scientific
investigation and a pressing need on the implementation of multi-strategy selection, which is crucially useful in
human–computer negotiation to achieve better online negotiation outcomes. The lack of such studies has
decelerated the process of applying automated negotiation to real world problems With the rapid growth of
global emarkets, there has been a significant interest in designing Automated Negotiation System (ANS) [35]
that can serve as surrogates for human business decision-makers, where software agents are designed to
autonomously act on behalf of the real-world parties [38, 5]. According to T. Bosse automated negotiation is
becoming crucially important and pervasive and agents promise exciting opportunities to turn conventional
transactions into an automated, cost-efficient manner, the study of ANS has piqued increasing interest in the
scholarly fields of e-commerce and artificial intelligence [37]. While the e-commerce and AI literatures mirror
that the ANS can be used in computer–computer and human–computer negotiations, extant studies on ANS
primarily focus on the former, leaving the latter comparatively unexplored [24]. In fact, human involvement in
decision-making is still required in most of present online negotiations, and with the ever mushrooming growth
of e-commerce and e-markets, there is an increasing potential for the use of software agents to more effectively
and efficiently negotiate with human negotiators [38,23]. The human–computer negotiation plays a paramount
role in the e-commerce oriented applications, especially in the B2C context where software agents act as
business provider [34]. Compared with the traditional online sales mode where customers view the basic
product or service information on the website and often need to negotiate with human salespeople through a
“contact us” link, a human–computer ANS can help business organizations to reduce the labour cost for
negotiation and greatly increase the transaction efficiency to the optimum extent. Prior work have been
conducted to design various human–computer negotiating agent [24,23] which demonstrate that a software
agent can proficiently negotiate with and even outperform people.
4.2 Fact-Based Negotiation
P. Braun, et al proposed a model for intelligent agent in negotiation between buyer and seller in B2C Commerce
using big data analytics. The developed model is used to conduct negotiations on behalf of prospective buyers
and sellers using analytics to improve negotiations to meet the practical requirements. The objective of this
model is to explore the opportunities of using big data and business analytics for negotiation, where big data
analytics can be used to create new opportunities for bidding. Using big data analytics sellers may learn to

246 | P a g e
predict the buyers‟ negotiation strategy and therefore adopt optimal tactics to pursue results that are to their best
interests. An experimental design is used to collect intelligent data that can be used in conducting the
negotiation process. Such approach will improve quality of negotiation decisions for both parties. Negotiation
is one of the major components of many e-commerce activities, such as auctions, scheduling, contracting, and so
on, and is one area that can greatly benefit from intelligent automation.
E-commerce negotiation is a decision-making process that seeks to find an electronic agreement, which will
satisfy the requirements of two or more parties in presence of limited information and conflicting preferences
[17]. In e-commerce negotiations buyers and sellers search for possible solutions until agreement is reached or
negotiations fail. Both buyers and sellers can conduct their own utility assessment for every solution. The goal
of negotiation is to seek a solution that optimizes utility value for both of them. The success of e-negotiation in
B2C commerce depends on volume of provided data and information, and how they are used to optimize the
negotiation operations. The size of data is big enough to extract huge volumes of valuable knowledge that may
determine firm„s success or failure [2]. Using big data analytics a seller may learn to predict the buyer„s
negotiation strategy and develop and adopt optimal tactics to achieve results that are to his best interests. The
ability to manage and transform data into useful information and utilize it as a strategic differentiator is a key
contributor to the success of B2C negotiation. The B2C negotiation process must be designed to take advantage
of large volumes of consumer data that have become available in recent years due to the Internet, social
networking, mobile telephony applications, RFID and sensor applications, and new technologies that create and
capture data, size of which is growing exponentially. Collected data are mainly unstructured and contain
valuable customer‟s opinion and behavioural information. Big data analytics can be defined as integrated
Technology, technology, practices, methologies, and applications that analyse critical business data to help an
organization better understand its business and make real time decisions [7]. In this work a description of B2C
e-commerce negotiation model is presented. The primary job of this model is to conduct negotiations on behalf
prospective buyers and sellers representatives. It employs multiple software agents that represent specific
functional of the system and applies big data analytics. Based on analytics results, agents are able to improve
their behaviours over time and take proactive and reactive negotiation actions. From that analytics knowledge,
they may get better with selecting and achieving goals and taking correct actions.
4.3 Multi-Issue Negotiation T. Baarslag, et al implemented multi-issue negotiation, with information
available about the agents' preferences, a negotiation may result in a mutually beneficial agreement. In a
competitive negotiation environment, however, self-interested agents may not be willing to reveal their
preferences, and this can increase the difficulty of negotiating a mutually beneficial agreement. In order to solve
this problem, this work proposes a Bayesian-based approach which can help an agent to predict its opponent's
preference in bilateral multi-issue negotiation. The proposed model employs Bayesian theory to analyse the
opponent's historical offers and to approximately predict the opponent's preference over negotiation issues.
Agent negotiation is a form of decision making where agents jointly explore possible solutions in order to reach
an agreement [33, 25, 11, 8]. In recent decades, agent negotiation technology has been widely developed to
solve issues in different areas, such as business transactions in e-commerce [3, 9] and service management in
cloud computing [32, 13]. With the support of agent negotiation technology, many operations which originally
required human intervention can be conducted automatically and intelligently by autonomous agents, and this

247 | P a g e
means that very large amounts amount of time and money can be saved. Currently, one major research challenge
in this area is opponent modelling [30, 31, 28, 27]. More precisely, during a negotiation, agents usually need to
use a number of negotiation parameters (i.e. deadline, preference, reservation utility and concession strategy) to
make wise decisions so that a win-win agreement can be reached. Some cooperative negotiation strategies have
assumed that these negotiation parameters are public information. In a competitive environment (non-cooperate
negotiation), however, self-interested agents usually keep their negotiation parameters secret in order to avoid
being exploited by their opponents [28].
In this work, one of the most important negotiation parameters is the negotiation preferences on negotiation
issues, because the preferences can play a critical role in terms of agents utility gains and the success rate of a
negotiation. In recent years, many different approaches have been proposed to help agents to predict their
opponents' preferences. These include: genetic algorithm-based prediction [27], statistical analysis-based
prediction [29, 15] and machine learning-based prediction [26]. However, all these approaches have different
limitations. For example, the approaches in [15, 25] require previous negotiation data to make the prediction and
the approach in [31] may need a long training time before the prediction algorithm becomes effective. The
motivation for this approach was to produce mutually beneficial offers for agents through preference prediction
and issue trade-off. Specifically, a set of hypothesises about the opponent's preference is initialised before
negotiation starts, and then Bayesian theory is used to analyse the counter-offer proposed by the opponent in
each negotiation round and the most suitable hypothesis is chosen to help the agent to generate offers. The
proposed negotiation approach was tested in different scenarios, and the experimental results have proved that
their negotiation approach can help agents to reduce the time needed to reach an agreement. Agents who applied
their negotiation approach could get more utilities when the negotiation ended.
4.4 Agent-Based Negotiation
Jennings, et al. implemented Agent-based negotiation is about computational autonomous agents that attempt to
arrive at joint agreements in competitive consumer-provider or buyer–seller scenarios on behalf of humans
(Jennings et al., 2001). As one of the most fundamental and powerful mechanisms for solving conflicts between
parties of different interests, recent years have witnessed a rapidly growing interest in automated negotiation,
mainly due to its broad application range in fields as diverse as electronic commerce and electronic markets,
supply chain management, task and service allocation, and combinatorial optimization. As a result, agent-based
negotiation brings together research topics of artificial intelligence, machine learning, game theory, economics,
and social psychology (Chen, Hao, Weiss, Tuyls, & Leung, 2014).
Dependent on the assumptions made about the negotiating agents‟ knowledge and the constraints under which
the agents negotiate, negotiation scenarios show different levels of complexity. The following assumptions,
which are reasonable in view of real-world applications and which underly their work, induce high complexity
and raise particular demands on the abilities of the negotiators. First, the agents have no usable prior information
about their opponents – neither about their preferences (e.g., their preferences over issues or their issue value
ordering) nor about their negotiation strategies. Then, the negotiation is constrained by the amount of time being
elapsed, the participants therefore do not know at any time during negotiation how many negotiation rounds
there are left and they have to take into account at each time point (i) the remaining chances for offer exchange
and (ii) the fact that the profit achievable through an agreement decreases over time („„negotiation with deadline

248 | P a g e
and discount‟‟). Third, each agent has a private reservation value below which an offered contract is not
accepted. Thereby they adopt the common view that an agent obtains the reservation value even if no agreement
is reached in the end. This implies that breaking-off a negotiation session would be potentially beneficial
especially when the time-discounting effect is substantial and the other side is being very tough. Together these
assumptions make negotiations complicated (yet realistic), where efficiently reaching agreements are
particularly challenging. They refer to such type of negotiations as complex negotiations afterwards.
4.5 Multi Attributes Based Negotiation
Dastjerdi, et al proposed Cloud service level agreement negotiation is a process of joint decision-making
between cloud clients and providers to resolve their conflicting objectives. With the advances of cloud
technology, operations such as discovery, scaling, monitoring and decommissioning are accomplished
automatically. Therefore, negotiation between cloud clients and providers can be a bottleneck if it is carried out
manually. Their objective is to propose a state-of-the-art solution to automate the negotiation process for cloud
environments and specifically infrastructure as a service category. The proposed negotiation strategy is based on
a time-dependent tactic. For cloud providers, the strategy uniquely considers utilization of resources when
generating new offers and automatically adjusts the tactic‟s parameters to concede more on the price of less
utilized resources. In addition, while the previous negotiation strategies in literature trust offered quality of
service values regardless of their dependability, their proposed strategy is capable of assessing reliability of
offers received from cloud providers. Furthermore, to find the right configuration of the time-dependent tactic in
cloud computing environments, they investigate the effect of modifying parameters such as initial offer value
and deadline on negotiation outputs that include ratio of deals made, and inequality index. The proposed
negotiation strategy is tested with different workloads and in diverse market conditions to show how the time-
dependent tactic‟s settings can dynamically adapt to help cloud providers increase their profits.
In the Service Level Agreement Negotiation (SLAN) phase, discovered providers and the user negotiate on the
quality of services. Finally, an SLA contract will be achieved if two parties reach an agreement on a set of
quality of service (QoS) values. Then, the acquired service will be continuously monitored in the monitoring
phase. If the monitoring service detects that predefined thresholds are reached, services are scaled dynamically
in the scaling phase. Finally, in the decommissioning phase, last minute operations are carried out before the
service is terminated. With the advances of cloud technology, operations such as discovery [18, 4], scaling [36,
6], monitoring [1, 10] and decommissioning are accomplished automatically [12]. Therefore, negotiations
between cloud services clients and providers can be a bottleneck if they are carried out manually. Hence, the
objective of this work is to propose a solution that automates the negotiation process in cloud computing
(specifically infrastructure as a service) environments. Cloud SLAN is a process of joint decision-making
between cloud users and providers to resolve their conflicting objectives. Automated SLAN has attracted a great
deal of interest in the context of Service Oriented Architecture (SOA), grid computing and recently cloud
computing. Studies in these contexts mainly focused on offering negotiation strategies that maximize the user‟s
utility values and the number of signed contracts. However, they have not considered infrastructure management
issues in the bargaining strategy. It means that cloud providers are willing to concede on the price of resources
which are less utilized, and that has to be reflected in the negotiation tactics. In addition, previous works have

249 | P a g e
not considered reliability in the negotiation process. These researches assume that service requestors would trust
whatever QoS criteria values providers offer in the process of negotiation.
E-commerce systems are important systems widely used by internets. To automate most of commerce time-
consuming stages of the buying process, software agent technologies proved to be efficient when employed in
different e-commerce transaction stages. The FIPA Contract Net Protocol was developed to facilitate contract
negotiation in Multi-Agent Systems, it is therefore important to analyse the protocol to ensure that it terminates
correctly and satisfies other important properties. In this work the focus on agent interactions in e-commerce
oriented automated negotiation based on FIPA Contract Net Protocol.
An e-commerce MAS is a MAS that connects multiple sellers and buyers agents on a single electronic
marketplace called E-marketplace, where many interactions take place [14]. Agents involved are cognitive
agents, able to communicate intentionally. Contract Net creates a means for contracting as well as
subcontracting tasks (or jobs), in this sense Initiators are managers and Participants are contractors. An Initiator
could be an agent willing to buy some good or wanting to sell the right to supply some good. Participants, in
each case, would be agents wanting to sell the good or willing to buy the right to supply the good. The
Interaction Protocol is composed of a sequence of four main steps, the agents must go through the following
loop of steps to negotiate each contract.
1. The Initiator announces a "call for proposal" (CFP).
2. Participant Agents who receive the announcement can answer by either a Proposal, a reject or a not
understood response, indicating they did not understand the announcement.
3. Initiator receives and evaluates proposals; sends a Contract to participant agents whose proposals are
accepted refuse to other agents.
4. At the end of interaction, the participant sends to the buyer agent, an Inform message to confirm the action
achieving, or a failure message in a failure case.
4.6 Bilateral Agent Negotiation
Bilateral agent negotiation is considered as a fundamental research issue in autonomous agent negotiation, and
was studied well by researchers. Generally, a predefined negotiation decision function and utility function are
used to generate an offer in each negotiation round according to a negotiator's negotiation strategy, preference,
and restrictions. However, such a negotiation procedure may not work well when the negotiator's utility function
is nonlinear, and the unique offer is difficult to be generated. That is because if the negotiator's utility function is
non-monotonic, the negotiator may find several offers that come with the same utility at the same time; and if
the negotiator's utility function is discrete, the negotiator may not find an offer to satisfy its expected utility
exactly. In order to solve such a problem, they propose a novel negotiation model in this work. Firstly, a 3D
model is introduced to illustrate the relationships between an agent's utility function, negotiation decision
function and offer generation function. Then two negotiation mechanisms are proposed to handle two types of
nonlinear utility functions respectively, i.e. a multiple offer mechanism is introduced to handle non-monotonic
utility functions, and an approximating offer mechanism is introduced to handle discrete utility functions.
Lastly, a combined negotiation mechanism is proposed to handle nonlinear utility functions in general situations
by considering both the non-monotonic and discrete. The experimental results demonstrate the effectiveness and
efficiency of the proposed negotiation model.

250 | P a g e
In this work, a bilateral single-issue negotiation model was proposed to handle nonlinear utility functions. A 3D
model was proposed to illustrate the relationships between an agent's utility function, negotiation decision
function, and time constraint. A multiple offer mechanism was introduced to handle non-monotonic utility
functions, and an approximating offer mechanism was introduced to handle discrete utility functions. Finally,
these two mechanisms were combined to handle nonlinear utility functions in more general situations. The
procedure of how an agent generated its counter offers by employing the proposed 3D model and negotiation
mechanisms was also introduced. The experimental results indicated that the proposed negotiation model and
mechanisms can efficiently handle nonlinear utility agents, and successfully lead the negotiation to an
agreement.
To date, a variety of automated negotiation agents have been created. While each of these agents has been
shown to be effective in negotiating with people in specific environments, they lack natural language processing
support required to enable real-world types of interactions. In this work they present NegoChat, the first
negotiation agent that successfully addresses this limitation. NegoChat contains several significant research
contributions. First, they found that simply modifying existing agents to include an NLP module is insufficient
to create these agents. Instead, the agents‟ strategies must be modified to address partial agreements and issue-
by-issue interactions. Second, they present NegoChat‟s negotiation algorithm. This algorithm is based on
bounded rationality, and specifically Aspiration Adaptation Theory (AAT). As per AAT, issues are addressed
based on people‟s typical urgency, or order of importance. If an agreement cannot be reached based on the value
the human partner demands, the agent retreats, or downwardly lowers the value of previously agreed upon
issues so that a “good enough” agreement can be reached on all issues. This incremental approach is
fundamentally different from all other negotiation agents, including the state-of-the-art KBAgent. Finally, we
present a rigorous evaluation of NegoChat, showing its effectiveness.
NegoChat, an agent that contains the following three key contributions: First, NegoChat successfully
incrementally builds agreements with people, something current automated negotiators do not do. Second,
NegoChat integrates natural language into its agent, allowing people to practice his or her negotiation skills
from anywhere, without installing any complicated software. Third, Negochat performs better than the current
stateof- the art agent, achieving better agreements in less time. Users are also happier with NegoChat and think
the agent is fairer.
4.7 Competitive Negotiation
R.H. Frank, et al proposed that negotiation is a form of decision-making where two or more parties jointly
search a space of possible solutions with the goal of reaching a consensus [20]. Economics and Game Theory
describe such an interaction in terms of protocols and strategies. The protocols of a negotiation comprise the
rules (i.e., legitimate actions) of the game. An example of a simple negotiation protocol is the non-
discriminatory English auction where (in one form) the only legal action is to (publicly) bid higher than the
current highest bid by at least the minimum bid amount before the auction closes.
Competitive negotiations can be described as the decision-making process of resolving a conflict involving two
or more parties over a single mutually exclusive goal. The Economics literature describes this more specifically
as the effects on market price of a limited resource given its supply and demand among self-interested parties

251 | P a g e
4.8 Cooperative Negotiation
R. Lewicki, et al implemented the degree of cooperation among negotiators falls within a continuum. After all,
even in competitive negotiations, all parties need to cooperate sufficiently to engage in negotiation as well as
agree on the semantics of the negotiation protocols. However, one clear distinction that can be made between
competitive and cooperative negotiations concerns the number of dimensions that can be negotiated across. For
example, all of the competitive negotiation protocols discussed in the previous section allow for negotiation
only within the price dimension. The cooperative negotiation protocols that we discuss in this section, on the
other hand, allow agents (and humans) to negotiate over multiple dimensions. Therefore, cooperative
negotiations can be described as the decision-making process of resolving a conflict involving two or more
parties over multiple interdependent, but non-mutually exclusive goals [22]. The study of how to analyze multi-
objective decisions comes from economics research and is called multi-attribute utility theory (MAUT) [21].
The game theory literature describes cooperative negotiation as a nonzero-sum game where as the values along
multiple dimensions shift in different directions, it is possible for all parties to be better off.
In essence, cooperative negotiation is a win-win type of negotiation. This is in stark contrast to competitive
negotiation which is a win-lose type of negotiation. Desired retail merchant-customer relationships and
interactions can be described in terms of cooperative negotiation the cooperative process of resolving multiple
interdependent, but non-mutually exclusive goals. A merchant‟s primary goals are long term profitability
through selling as many products as possible to as many customers as possible for as much money as possible
with as low transaction costs as possible. A customer‟s primary goals are to have their personal needs satisfied
through the purchase of well-suited products from appropriate merchants for as little money and hassle (i.e.,
transaction costs) as possible. A cooperative negotiation through the space of merchant offerings can help
maximize both of these sets of goals.
From a merchant‟s perspective, cooperative negotiation is about tailoring its offerings to each customer‟s
individual needs resulting in greater customer satisfaction. From a customer‟s perspective, cooperative
negotiation is about conversing with retailers to help compare their offerings across their full range of value
resulting in mutually rewarding and hassle-free shopping experiences.
V. CONCLUSION
As the negotiation is key instrument of e-commerce followed by perfect competition on the basis of trading
between buyers and sellers. At this paper we tried to review the e-commerce negotiation tools and work. This
review work provides an exhaustive review on automated negotiation based E-Commerce. The review work
basically based upon co-operative and competitive negotiation paradigm in B2C E-Commerce. Most of the co-
operative negotiation models provide win-win situation where as competitive negotiation lack this win-win
situation.
REFERENCES
[1] Alhamazani, K., Ranjan, R., Mitra, K., Jayaraman, P., Huang, Z.,Wang, L. and Rabhi, F. (2014) Clams:
Cross-layer Multi cloudApplication Monitoring-as-a-Service Framework. Proc. 2014 IEEE Int. Conf.
Services Computing (SCC), Anchorage, Alaska, USA, June 27–July 2, pp. 283–290. IEEE Computer
Society,Washington, DC, USA.

252 | P a g e
[2] A. Rajpurohit, Big data for business managers -Bridging the gap between potential and value Big Data‖,
2013 IEEE International Conference on Digital Object, 2013 , pp. 29-31.
[3] C.-C. Huang, W.-Y. Liang, Y.-H. Lai, Y.-C. Lin, The agent-based negotiation process for b2c e-
commerce, Expert Systems with Applications 37 (1) (2010) 348–359.
[4] Dastjerdi, A.V., Tabatabaei, S. and Buyya, R. (2010) An Effective Architecture for Automated Appliance
Management System Applying Ontology-based Cloud Discovery. Proc. 2010 10thIEEE/ACM Int. Conf.
Cluster, Cloud and Grid Computing(CCGrid), Melbourne, Australia, May 17–20, pp. 104–112.IEEE
Computer Society, Washington, DC, USA.
[5] G. Adomavicius, A.Gupta, D.Zhdanov, Designing intelligent software agents forauctions with limited
information feedback, Information Systems Research 20 (4) (2009) 507–526.
[6] Hasan, M., Magana, E., Clemm, A., Tucker, L. and Gudreddi,S. (2012) Integrated and Autonomic Cloud
Resource Scaling.Proc. 2012 IEEE Network Operations and Management Symp. (NOMS), Hawaii, USA,
April 16–20, pp. 1327–1334. IEEE Computer Society, Washington, DC, USA.
[7] H. Chen, R.H.L. Chiang, and V.C. Storey, Business intelligence and analytics: from big data to big
impact‖, MIS Quarterly, vol. 36(4), 2012, pp. 1165-1188.
[8] H. Jazayeriy, M. Azmi-Murad, N. Sulaiman, N. IzuraUdizir, The learning of an opponent‟s approximate
preferences in bilateral automated negotiation, Journal of Theoretical and Applied Electronic Commerce
Research 6 (3) (2011) 65–84.
[9] I. Rahwan, R. Kowalczyk, H. H. Pham, Intelligent agents for automated one-to-many e-commerce
negotiation, in: Australian Computer Science Communications, Vol. 24, 2002, pp. 197–204.
[10] Jehangiri, A., Yahyapour, R., Wieder, P., Yaqub, E. and Lu, K.(2014) Diagnosing Cloud Performance
Anomalies using Large Time Series dataset Analysis. Proc. 2014 IEEE 7th Int. Conf.Cloud Computing
(CLOUD), Anchorage, Alaska, USA, June 27–July 2, pp. 930–933. IEEE Computer Society,
Washington, DC, USA.
[11] J. Gwak, K. M. Sim, Bayesian learning based negotiation agents for supporting negotiation with
incomplete information, in: Proceedings of the International Multi-conference of Engineers and
Computer Scientists, 2011, pp. 163–168.
[12] Joshi, K., Yesha, Y. and Finin, T. (2014) Automating cloud services life cycle through semantic
technologies. IEEE Trans. Serv. Comput., 7, 109–122.
[13] J. Yan, R. Kowalczyk, J. Lin, M. B. Chhetri, S. K. Goh, J. Zhang, Autonomous service level agreement
negotiation for service composition provision, Future Generation Computer Systems 23 (6) (2007) 748–
759.
[14] Lawley, R., Luck, M., Decker, K., Payne, T. and Moreau, L. (2003) Automated negotiation between
publishers and consumers of grid notifications. Parallel Process. Lett., 13, 537–548. To appear,
Knowledge Engineering Review, June 1998.
[15] L. Pan, X. Luo, X. Meng, C. Miao, M. He, X. Guo, A two-stage win-win multiattribute negotiation
model: Optimization and then concession, Computational Intelligence 29 (4) (2013) 577–626.
[16] Michael J. Wooldridge: An introduction to Multiagent systems, wiley publication 2nd nd edition.
[17] P. Braun, J. Brzostowski, G. Kersten, J. B. Kim, R. Kowalczyk, et al., "Intelligent decision-making
support systems: foundations, applications and challenges", Springer, London, 2006, pp. 271-300.

253 | P a g e
[18] Redl, C., Breskovic, I., Brandic, I. and Dustdar, S. (2012) Automatic SLA Matching and Provider
Selection in Grid and CloudComputing Markets. Proc. 2012 ACM/IEEE 13th Int. Conf. GridComputing
(GRID), Beijing, China, September 20–23, pp. 85–94. IEEE Computer Society, Washington, DC, USA.
[19] R. Guttman, A. Moukas, and P. Maes. “Agent-mediated Electronic Commerce: A Survey.”
[20] R.H. Frank. Microeconomics and Behavior, 3rd ed. McGraw-Hill, Inc., 1996.
[21] R. Keeney and H. Raiffa. Decisions with Multiple Objectives: Preferences and Value Tradeoffs. John
Wiley & Sons, 1976.
[22] R. Lewicki, D. Saunders, and J. Minton. Essentials of Negotiation. Irwin, 1997.
[23] R. Lin, et al., Training with automated agents improves people's behavior in negotiation and coordination
tasks, Decision Support Systems 60 (IS) (2014) 1–9.
[24] R. Lin, S. Kraus, Can automated agents proficiently negotiate with humans? Communications of the
ACM 53 (1) (2010) 78–88.
[25] R. M. Coehoorn, N. R. Jennings, Learning on opponent‟s preferences to make effective multi-issue
negotiation trade-offs, in: Proceedings of the 6th International Conference on Electronic Commerce,
2004, pp. 59–68.
[26] R. Ros, C. Sierra, A negotiation meta strategy combining trade-off and concession moves, Autonomous
Agents and Multi-Agent Systems 12 (2) (2006) 163–181.
[27] S. Chen, G. Weiss, An approach to complex agent-based negotiations via effectively modelling unknown
opponents, Expert Systems with Applications 42 (5) (2015) 2287–2304.
[28] S. Chen, G. Weiss, An intelligent agent for bilateral negotiation with unknown opponents in continuous-
time domains, ACM Transactions on Autonomous and Adaptive Systems (TAAS) 9 (3) (2014) 1–24.
[29] S. Kraus, Negotiation and cooperation in multi-agent environments, Artificial Intelligence 94 (1) (1997)
79–97.
[30] S.-S. Leu, P. V. H. Son, P. T. H. Nhung, Hybrid bayesian fuzzy-game model for improving the
negotiation effectiveness of construction material procurement, Journal of Computing in Civil
Engineering.
[31] S.-S. Leu, P. V. H. Son, P. T. H. Nhung, Optimize negotiation price in construction procurement using
bayesian fuzzy game model, KSCE Journal of Civil Engineering (2014) 1–7.
[32] S. Son, K. M. Sim, A price-and-time-slot-negotiation mechanism for cloud service reservations, Systems,
Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on 42 (3) (2912) 713–728.
[33] T. Baarslag, K.V. Hindriks, Accepting optimally in automated negotiation with incomplete information,
in: Proceedings of the 12th International Conference on Autonomous Agents and Multi-agent systems,
2013, pp. 715–722.
[34] T. Bosse, C.M. Jonke, Human vs. computer behavior in multi-issue negotiation,Rational, Robust, and
Secure Negotiation Mechanisms in Multi-Agent Systems2005.
[35] W. Ketter, et al., Real-time tactical and strategic sales management for intelligent agents guided by
economic regimes, Information Systems Research 23 (4) (2012)1263–1283.
[36] Xiao, Z., Chen, Q. and Luo, H. (2014) Automatic scaling of internet applications for cloud computing
services. IEEE Trans. Comput., 63, 1111–1123.

254 | P a g e
[37] X. Luo, et al., KEMNAD: a knowledge engineering methodology for negotiating agent development,
Computational Intelligence 28 (1) (2012) 51–105.
[38] Yang, S. Sharad, C.X. Yunjie, Alternate strategies for a win–win seeking agent in agent–human
negotiations, Journal of Management Information Systems 29 (3) (2013) 223–255.