Consumer model

Lee G. Dove (Inventor), Graham I. Johnson (Inventor)

Research output: Patent

Abstract

A model of consumer behavior in a transaction environment such as customers moving around a bank branch, is generated from an artificial life algorithm to create a number of agents. In each agent, a genetically encoded drive, equivalent for example to hunger, is defined so as to correspond to a transaction need such as the need for cash. Interaction rules, such as navigation rules, are set for interaction between the agents and a first representation of an environment, and the program is run and the agents observed, then compared with real human behavior. The best matched agents are selected and the program run again, the steps being repeated until a required level of comparison with real behavior is reached. The model can then be used with different transaction environments to study customer behavior and to select the best branch layout or the like.
Original languageEnglish
Patent numberUS 6,741,973 B1
Filing date14/10/97
Publication statusPublished - 25 May 2004
Externally publishedYes

Fingerprint

Consumer behavior
Navigation

Cite this

Dove, L. G., & Johnson, G. I. (2004). Consumer model. (Patent No. US 6,741,973 B1). USPTO (United States Patent and Trademark Office).
Dove, Lee G. (Inventor) ; Johnson, Graham I. (Inventor). / Consumer model. USPTO (United States Patent and Trademark Office). Patent No.: US 6,741,973 B1. Oct 14, 1997.
@misc{c01ab7cd87d54cb4b95f80bdfe0947a8,
title = "Consumer model",
abstract = "A model of consumer behavior in a transaction environment such as customers moving around a bank branch, is generated from an artificial life algorithm to create a number of agents. In each agent, a genetically encoded drive, equivalent for example to hunger, is defined so as to correspond to a transaction need such as the need for cash. Interaction rules, such as navigation rules, are set for interaction between the agents and a first representation of an environment, and the program is run and the agents observed, then compared with real human behavior. The best matched agents are selected and the program run again, the steps being repeated until a required level of comparison with real behavior is reached. The model can then be used with different transaction environments to study customer behavior and to select the best branch layout or the like.",
author = "Dove, {Lee G.} and Johnson, {Graham I.}",
year = "2004",
month = "5",
day = "25",
language = "English",
publisher = "USPTO (United States Patent and Trademark Office)",
type = "Patent",
note = "US 6,741,973 B1",

}

Dove, LG & Johnson, GI Oct. 14 1997, Consumer model, Patent No. US 6,741,973 B1.

Consumer model. / Dove, Lee G. (Inventor); Johnson, Graham I. (Inventor).

USPTO (United States Patent and Trademark Office). Patent No.: US 6,741,973 B1. Oct 14, 1997.

Research output: Patent

TY - PAT

T1 - Consumer model

AU - Dove, Lee G.

AU - Johnson, Graham I.

PY - 2004/5/25

Y1 - 2004/5/25

N2 - A model of consumer behavior in a transaction environment such as customers moving around a bank branch, is generated from an artificial life algorithm to create a number of agents. In each agent, a genetically encoded drive, equivalent for example to hunger, is defined so as to correspond to a transaction need such as the need for cash. Interaction rules, such as navigation rules, are set for interaction between the agents and a first representation of an environment, and the program is run and the agents observed, then compared with real human behavior. The best matched agents are selected and the program run again, the steps being repeated until a required level of comparison with real behavior is reached. The model can then be used with different transaction environments to study customer behavior and to select the best branch layout or the like.

AB - A model of consumer behavior in a transaction environment such as customers moving around a bank branch, is generated from an artificial life algorithm to create a number of agents. In each agent, a genetically encoded drive, equivalent for example to hunger, is defined so as to correspond to a transaction need such as the need for cash. Interaction rules, such as navigation rules, are set for interaction between the agents and a first representation of an environment, and the program is run and the agents observed, then compared with real human behavior. The best matched agents are selected and the program run again, the steps being repeated until a required level of comparison with real behavior is reached. The model can then be used with different transaction environments to study customer behavior and to select the best branch layout or the like.

M3 - Patent

M1 - US 6,741,973 B1

Y2 - 1997/10/14

PB - USPTO (United States Patent and Trademark Office)

ER -

Dove LG, Johnson GI, inventors. Consumer model. US 6,741,973 B1. 2004 May 25.