Hybrid Intelligence Agents Architecture Design for Product Return Administration

Abstract:

Return is a critical but controversial issue. To deal with such a vague return problem, business must improve information transparency about end users’ return activities. This research proposed an agent-based architecture for return administration. The intelligent return administration expert system (iRAES) architecture consists of two KDD mechanisms and two intelligent agents that can predict the possibility of the end user will return the product (via return diagnosis agent, RDA) and provide return centre staff with recommendations for return administration (via return recommender agent, RRA). iRAES is implemented successfully and adopts hybrid artificial intelligent algorithms, including the following: data mining is employed to implement the RDA agent, and case-based reasoning is adopted to design the RRA agent. A demonstrated 3C-iShop scenario is presented to illustrate the feasibility and efficiency of iRAES architecture. As the experiment results show, iRAES can decrease the 70% effort for return administration evaluation and improve performance with return administration suggestions by 37%. Therefore, return administration and the knowledge management about product return can be accelerated via iRAES.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 3339-3343
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.3339
• Online since: November 2011
• Authors: Chen Shu Wang
• Keywords: Case-Based Reasoning (CBR), Intelligence Agent, Intelligence System Design, Product Return, Supply Chain Management (SCM)

References

[1] A. Aamodt, and E. Plaza,: Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches, AI Communications, 7(1), 1994, 39-59.

DOI: 10.3233/aic-1994-7104

[2] S. Davis, and M. Hagerty,: Gerstner, E.: Return Policies and the Optimal Level of Hassle, Journal of Economics and Business , 50(5), 1998, 445-460, (1998).

DOI: 10.1016/s0148-6195(98)00013-7

[3] M.P. de Brito, and E.A. van der Laan,: Inventory Control with Product Returns: The Impact of Imperfect Information, European Journal of Operational Research, 194(1), 2009, 85-101.

DOI: 10.1016/j.ejor.2007.11.063

[4] R.O. Eduardo, and R.P. Andres,: The regional return of public investment policies in Mexico, World Development, 32(9), 2004, 1545–1562.

[5] W. Hoffman, J. Keedy, and K. Roberts,: The Unexpected Return of B2B, The McKinsey Quarterly, 3, 2002, 97-105.

[6] S.K. Mukhopadhyay, S.K., and R. Setaputra,: A Dynamic Model for Optimal Design Quality and Return Policies, European Journal of Operational Research, 180(3), 2007, 1144-1154.

DOI: 10.1016/j.ejor.2006.05.016

[7] V. Padmanabhan, V., and I.P.L. Png,: Manufacturer's Returns Policies and Retail Competition, Marketing Science, 16(1), 1997, 81-94. A. Petersen, and V. Kumar,: Are Product Returns a Necessary Evil? Antecedents and Consequences, Journal of Marketing, 73(3), 2009, 35-51.

DOI: 10.1509/jmkg.73.3.35

[8] Y.W. Si, and S.F. Lou,: Fuzzy Adaptive Agent for Supply Chain Management, Web Intelligence and Agent System, 7(2), 2009, 173-194.

DOI: 10.3233/wia-2009-0161

[9] C.C. Yu, and C.S. Wang,: A Hybrid Mining Approach for Optimizing Returns Policies in e-Retailing, Expert Systems with Applications, 35(4), 2008, 1575-1582.

DOI: 10.1016/j.eswa.2007.08.099