Profit-maximizing strategies for an artificial payment card market

Is learning possible?

Biliana Alexandrova-Kabadjova, Edward Tsang, Andreas Krause

Research output: Contribution to journalArticle

Abstract

In this paper, we study the dynamics of competition in the payment card market. This is done through a multi-agent based model, which captures explicitly the commercial transactions at the point of sale between consumers and mer-chants. Through simulation, we attempt to model the demand for payment instruments on both sides of the market. Con-strained by this complex demand, a Generalised Population Based Incremental Learning (GPBIL) algorithm is applied to find a profit-maximizing strategy, which in addition has to achieve an average number of card transactions. In the present study we compare the performance of a profit-maximizing strategies obtained by the GPBIL algorithm versus the performance of randomly selected strategies. We found that under the search criteria used, GPBIL was capable of improving the price structure and price level over randomly selected strategies.
Original languageEnglish
Pages (from-to)70-81
JournalJournal of Intelligent Learning Systems and Applications
Volume3
Issue number2
Early online date7 Apr 2011
DOIs
Publication statusPublished - May 2011

Fingerprint

Payment card
Profit
Incremental
Learning algorithm
Simulation
Point of sale
Agent-based model
Price level
Payment instruments

Cite this

Profit-maximizing strategies for an artificial payment card market : Is learning possible? / Alexandrova-Kabadjova, Biliana; Tsang, Edward; Krause, Andreas.

In: Journal of Intelligent Learning Systems and Applications, Vol. 3, No. 2, 05.2011, p. 70-81.

Research output: Contribution to journalArticle

@article{b7fad2478f52465c9a92849133108e4b,
title = "Profit-maximizing strategies for an artificial payment card market: Is learning possible?",
abstract = "In this paper, we study the dynamics of competition in the payment card market. This is done through a multi-agent based model, which captures explicitly the commercial transactions at the point of sale between consumers and mer-chants. Through simulation, we attempt to model the demand for payment instruments on both sides of the market. Con-strained by this complex demand, a Generalised Population Based Incremental Learning (GPBIL) algorithm is applied to find a profit-maximizing strategy, which in addition has to achieve an average number of card transactions. In the present study we compare the performance of a profit-maximizing strategies obtained by the GPBIL algorithm versus the performance of randomly selected strategies. We found that under the search criteria used, GPBIL was capable of improving the price structure and price level over randomly selected strategies.",
author = "Biliana Alexandrova-Kabadjova and Edward Tsang and Andreas Krause",
year = "2011",
month = "5",
doi = "10.4236/jilsa.2011.32009",
language = "English",
volume = "3",
pages = "70--81",
journal = "Journal of Intelligent Learning Systems and Applications",
issn = "2150-8402",
number = "2",

}

TY - JOUR

T1 - Profit-maximizing strategies for an artificial payment card market

T2 - Is learning possible?

AU - Alexandrova-Kabadjova, Biliana

AU - Tsang, Edward

AU - Krause, Andreas

PY - 2011/5

Y1 - 2011/5

N2 - In this paper, we study the dynamics of competition in the payment card market. This is done through a multi-agent based model, which captures explicitly the commercial transactions at the point of sale between consumers and mer-chants. Through simulation, we attempt to model the demand for payment instruments on both sides of the market. Con-strained by this complex demand, a Generalised Population Based Incremental Learning (GPBIL) algorithm is applied to find a profit-maximizing strategy, which in addition has to achieve an average number of card transactions. In the present study we compare the performance of a profit-maximizing strategies obtained by the GPBIL algorithm versus the performance of randomly selected strategies. We found that under the search criteria used, GPBIL was capable of improving the price structure and price level over randomly selected strategies.

AB - In this paper, we study the dynamics of competition in the payment card market. This is done through a multi-agent based model, which captures explicitly the commercial transactions at the point of sale between consumers and mer-chants. Through simulation, we attempt to model the demand for payment instruments on both sides of the market. Con-strained by this complex demand, a Generalised Population Based Incremental Learning (GPBIL) algorithm is applied to find a profit-maximizing strategy, which in addition has to achieve an average number of card transactions. In the present study we compare the performance of a profit-maximizing strategies obtained by the GPBIL algorithm versus the performance of randomly selected strategies. We found that under the search criteria used, GPBIL was capable of improving the price structure and price level over randomly selected strategies.

UR - http://dx.doi.org/10.4236/jilsa.2011.32009

U2 - 10.4236/jilsa.2011.32009

DO - 10.4236/jilsa.2011.32009

M3 - Article

VL - 3

SP - 70

EP - 81

JO - Journal of Intelligent Learning Systems and Applications

JF - Journal of Intelligent Learning Systems and Applications

SN - 2150-8402

IS - 2

ER -