Li, S.,

From Digital Culture & Society

Jump to: navigation, search

<AgentsInternational: Integration of multiple agents, simulation, knowledge bases and fuzzy logic for international marketing decision making:

Li, S., & Li, J. Z. (2010). AgentsInternational: Integration of multiple agents, simulation, knowledge bases and fuzzy logic for international marketing decision making. Expert Systems With Applications, (3), 2580.

Globalization has enabled large corporations to expand their business offerings beyond national borders, which has created increasingly complex challenges for advertisers and brand managers. Marketers working for large multinationals are tasked with developing intercultural marketing campaigns and messages that appeal to broad audiences, and can engage several distinctly different reference groups simultaneously. The AgentsInternational System, is the first marketing software of its kind to take advantage of advances in computing power. The AgentsInternational System applies machine learning concepts to understand the unique challenges of marketing products across multiple reference groups, and assist managers with the development effective International Marketing Plans.

In their article, AgentsInternational: Integration of multiple agents, simulation, knowledge bases and fuzzy logic for international marketing decision making, authors Li and Li suggest the automated intelligence systems currently being used by marketers to solve international marketing problems are restricted to the use of a single individual technique or technology, mainly traditional expert systems, and stand-alone delivery and deployment. Li and Li discuss the progress researchers have made in exploring the use of various types of computerised support/machine learning systems for solving International Marketing Problems, and based on their assessment, assert that even with considerable advances towards developing hybrid systems for formulating general marketing strategies, none of the current available softwares are designed to specifically support the evolving challenges presented by International Marketing Planning.

The purpose of the study is to investigate the potential and assess the effectiveness of of their newly developed multiagent-based hybrid intelligent system, the AgentsInternational System, which was designed to address problems specifically associated with international marketing strategy. Li and Li created the AgentsInternational System, the first software of its kind to integrate the strengths of multiple intelligent agents, knowledge bases, Monte Carlo simulations, and fuzzy logic, to assist several key stages of international marketing decision making: go vs. no go decisions, entry mode selection, and marketing strategy formulation.

The underlying goal of AgentsInternational is the embodiment of knowledge from human marketing experts, making that knowledge available to others facing similar challenges, and consistently producing effective recommendations for solving unique International Marketing Problems. After users input the parameters detailing the context of a unique International Marketing Problem, the AgentsInternational System performs several analysis related to go vs. no go decisions, entry mode selection, and marketing strategy development.

The AgentsInternational System’s decision making processes is initially informed by McDonald’s (2006) ten-step strategic marketing planning process covering mission, corporate objectives, marketing audit, SWOT analysis, assumptions, marketing objectives and strategies, estimate expected results, identify alternative plans and mixes, budget, and the first year detailed implementation programme. Referencing Mellers, Schwartz, and Cooke (1998), and Mintzberg (1994a, 1994b), Li and Li discuss the significance of and roles of human judgement in decision making, and argue that because managers may have experience and specific knowledge about their products and markets which computers currently are unable to understand, strategic planning softwares must be coupled with managers’ judgement and personal vision. Referring to Zadeh, 1988, Li and Li propose including “Fuzzy Logic” as an analysis technique to handle imprecise fuzzy terms or linguistic concepts using membership functions when creating recommendations for solving specific marketing problems.

In the context of software programming, “Classical Logic” only permits the computer to draw conclusions which are either true or false. However, International Marketing problems can create propositions with variable answers. In such instances, the recommendation is created as the result of reasoning from inexact or partial knowledge, where all sampled answers are mapped across a spectrum. Degrees of truth, or the effectiveness of potential solutions range between 0 and 1 and hence may seem similar at first, but fuzzy logic uses this truth scale to deliver the most accurate analysis possible back to the end user. Citing Usable, 1998, Li and Li also coded a Monte Carlo simulation into the AgentsInternational System as an unbiased and consistent point estimator. Combining Fuzzy Logic with simulation and McDonald’s ten-step strategic marketing planning process, the AgentsInternational System determines relevant factors related to go vs. no go decisions, entry mode selection, and marketing strategy development.

The AgentsInternational System was tested by carrying out evaluation work in October and November of 2008 with eight managers in London including one company marketing director, one company managing director, one company analyst, and five university course leaders/managers. Of the eight managers involved in the evaluation studies, most of them assess the AgentsInternational System as effective with regards to; Help marketers understand the factors that affect decision making, help marketers decision making by providing relevant knowledge, analytical models and guidelines, help marketers with strategic analysis, help marketers couple analysis with judgment, intuition and creativity, help marketers supplement judgment and intuition, help marketers deal with uncertainty in the process of decision making, help marketers generate relevant alternatives or options in the process of decision making, and help marketers improve the quality of decision making.

Through coordinating communications amongst the user and various agents, and connecting supporting techniques and technologies together, the AgentsInternational System combines the decision making process, human judgement, and supporting techniques and technologies, to consistently deliver effective analysis of go vs. no go decisions, entry mode selection, and marketing strategy development, related to unique International Marketing Problems.

However Li and Li feel it necessary to mention that the potential of machine learning technology is not fully taken advantage of in the AgentsInternational System. Although intelligent agents are created to post messages, represent various analytical models, store relevant expertise, perform intelligent reasoning and manage different stages of international marketing decision making, other agent features such as automatic search for information, autonomy, and interaction among group decision making members are not fully implemented by the software. >

Personal tools
Bookmark and Share