Predicting Volatile Consumer Markets using Multi-Agent Methods

This article illustrates the use of multi-agent modelling and prediction of consumer goods markets. A behavioral model incorporating utility based rational choice enhanced with psychological drivers is presented to study a typical market, characterized by repeat purchase incidences by households. The psychological drivers incorporate purchase strategies of loyalty and change-of-pace, which affect the choice set of consumer agents in an agent based simulation environment. Agent specific memories of past purchases drive these strategies, while attribute specific preferences and prices drive the utility based choice function. Transactions data from a category in a supermarket is used to initialize, calibrate and test the accuracy of predictions of the model. Results indicate that prediction accuracy at both macro and micro levels can be significantly improved with the incorporation of purchase strategies. Moreover, increasing the memory length beyond a certain limit does not improve pr...

An agent based behavioral model incorporating utility based rational choice enhanced with psychological drivers is presented to study a typical consumer market. The psychological drivers incorporate purchase strategies of loyalty and change-of-pace, using agent specific memory of past purchases. Attribute specific preferences and prices drive the utility based choice function. Transactions data is used to calibrate and test the model. Results indicate that prediction accuracy at both macro and micro levels can be significantly improved with the incorporation of purchase strategies. Moreover, increased agent memory does not improve predictions in the model beyond a threshold, indicating that consumer memory of past shopping instances is finite and recent purchase history is more relevant to current decision making than the distant past. The article illustrates the use of agent based simulations to model changes or interventions in the market, such as new product introductions, for which no past history exists.

Journal of Business Research, 2007

Consumer behavior research involves various areas: psychology, marketing, sociology, economics and engineering. This paper presents an agent-based model (ABM) of consumer purchase decision-making. The core of this model is a motivation function that combines consumers' psychological personality traits with two important kinds of interactions in a competitive market. The model reveals the inner psychological mechanism on the basis of which consumers make their choices when facing competing brands on the market. By creating a large number of heterogeneous consumer agents in an artificial market, this study uses multi-agent simulation (MAS) to exhibit the emergent decoy effect phenomenon, which is a market dynamic phenomenon originating from the individual behavior of heterogeneous consumers and their interactions in the real-world complex market. The combined use of the ABM and the MAS method in studying consumer behavior and markets gives one the potential to cope with the dynamic changes and complexities in the real-world business environment.

2021

Because of the dissemination of impulse buying behavior in consumers its academic studies have increased over the last decade. Because in large stores, sales have to be increased, the behavior of consumers in impulse buying to be taken into account by the researchers and managers of the stores. The purpose of this paper is to model agent-based the impulse buying behavior of consumers (customers), with regards to the factors of discount and swarm in the purchase. In terms of executive purpose and with agent-based modeling approach, the present paper examines the existing reality of consumer impulse buying behavior. This paper develops consumption models, examines and analyzes consumer behavior under the NetLogo software environment. In comparing the optimal points of discounts and sales volume in both discount and swarm-discount functions that lead the stores to maximize profits and sales volume simultaneously, it can be debated that with running this model (swarm-discount) stores wo...

Lecture Notes in Computer Science, 2014

We present an agent-based business simulation game where the marketplace is simulated as an evolving system of autonomous interacting deliberative agents acting as utility maximizers. Consumers are explicitly modelled as deliberative agents with concrete beliefs, intentions and desires who act to accomplish their purchase plans. Simple codification rules at the level of the utility functions of the agents allow the emergence of complex behaviour which illustrate fundamental concepts from economics such as the law of demand, diminishing returns, effects of price and income changes and substitution and complementary effects. The game was tested experimentally, with our results proving to be encouraging, with the majority of the participants considering they were able to understand the results of the simulation. The high levels of agreement on this subject were closely related to the high degree of information provided by the agent-based model of consumer behaviour which allowed the disclosure of information, both at the micro and macro levels of complexity, without however, hindering the strategic value of the game.

Economics Web Institute, 2004

Manufacturing Systems and Technologies for the New Frontier, 2008

This paper describes the multi-agent modeling of a service market which consists of a service provider and various types of consumers. The difficulty in determining, and thus reacting to, the needs of markets, lies in the fact that consumers have diverse value concepts, which can differ through interaction with others. This study conducts a questionnaire on consumer lifestyles, and constructs models for the several types of consumers, based on the survey results. It also clarifies characteristics of a service market. The multi-agent simulations of this service market are executed to verify the validity of the proposed model.

The volatility in a CPG market is modeled using a bottom-up simulation approach and validated against disaggregated supermarket transactions data. The simulation uses independent agents, each agent representing unique households in the data. A simple behavioral model incorporates household preferences for product attributes and prices. Our validation strategy tests the model predictions at both macro and micro levels and benchmarks the performance in each against a random choice model. The model significantly outperforms the benchmark at both levels. At the macro level, choices made by heterogeneous agents accurately captures the volatility in market shares over time. This accuracy at the macro level is driven by the accuracy of predictions at the micro household level SKU and attribute choice.

Complexity, 2010

Consumer markets have been studied in great depth, and many techniques have been used to represent them. These have included regression-based models, logit models, and theoretical market-level models, such as the NBD-Dirichlet approach. Although many important contributions and insights have resulted from studies that relied on these models, there is still a need for a model that could more holistically

2013

This paper presents a customer behavioral model for grounding the number of purchase items in Agent-Based In-Store Simulator (ABISS). ABISS is a decision support system for a retail management. Using ABISS, we are able to virtually investigate the shopping paths of the customers and analyze the effect of sales promotion. To grounding the number of purchase items, first we conduct a field study using Radio Frequency Identification (RFID) and analyze the collected RFID data and Point-of-Sales (POS) data. Then we develop a decision model, which determined customers’ “Shopping List”, “Possession Money Limit”, and “Staying time”. The experimental result has revealed that we ground the number of purchasing items of obtained by the POS data, if we concentrate on the tuning of ABISS parameters on “Shopping List” and “Possession Money Limit”.