Agent-based modelling and simulation in the analysis of customer behaviour on B2C e-commerce sites

Abstract

This paper examines the development and application of agent-based modelling and simulation in the analysis of customer behaviour on B2C e-commerce websites as well as in the analysis of the effects of various business decisions regarding online sales. The methodology of the agent-based simulation used in this paper may significantly enhance the speed and quality of decision-making in electronic trade. The models developed for this research aim to improve the use of practical tools for the evaluation of the B2C online sales systems in that they allow for an investigation into the outcomes of varied strategies in the e-commerce site management as regards customer behaviour, website visits, scope of sales, income earned, etc. An agent-based simulation model developed for the needs of this research is able to track the interactions of key subjects in online sales: site visitors—prospective consumers, sellers with different business strategies, and suppliers.

Keywords:

• ABMS
• B2C
• e-commerce
• customer behaviour

Statement of contribution

This paper addresses the behaviour of consumers and business strategies of sellers in B2C e-commerce systems by applying the agent-based modelling and simulation (ABMS). It contributes to the theory and practice of simulation modelling by building the agent-based simulation models which could act as a tool supporting decision-making in electronic commerce. By linking the areas of modelling based on agents and electronic commerce, this paper addresses the new opportunities for a quality of assessment of consumer behaviour and reasons explaining this behaviour in e-commerce. The interactions of agents that make up this model are sublimated in the utility function that provides the basis for decision-making in the model and is the original contribution of this work. The rules of behaviour and interactions, included in the model through the utility function, denote the complexity of the decision-making process which occurs in evaluation and purchase of products in the part of B2C e-commerce. The utility function comprises four components. The first component relates to the price of the product. The second part implements the effects of different marketing activities of agent-sellers on B2C markets, whereby special attention is devoted to eWOM effects. The third component takes into account the demographic characteristics of consumers in making a purchase decision. The fourth component takes into consideration a site visitor perception of a product which is based on the information available at the website. The simulation model implemented in the software NetLogo enables the monitoring of all interactions between the SellerAgent, ConsumerAgent and BannerAgent by generating the indicators of B2C site business performance (market shares, surf share and profitability). This model represents the original contribution of this paper. It enables the model users to test different business decisions and monitor the behaviour of sellers, suppliers and consumers on sites dealing with B2C e-commerce.