Perception-Based Multi-Agent Geo-Simulation in the Service of Retail Location Decision-Making in a Shopping Mall *
Bibliographic record
Abstract
Abstract In the very competitive retail world, mall managers develop various strategies to differentiate their malls from their competitors in order to enhance customer loyalty. One possible strategy consists in changing the mall configuration and more specifically the stores' locations. Deciding on stores' locations is a very important decision which can be expensive in terms of money and time. In order to guarantee the success of such decisions, mall managers should be able to better understand customers' behaviours and the way they may react to changes in the mall's configuration. Traditional techniques such as surveys and the use of Ggeographic Information Systems may help to understand customers' behaviours in an existing mall, but they are not adequate for anticipating customers' reactions to a future layout of the mall. Thanks to recent progress in the areas of geo-simulation and multi-agent systems, simulating the behaviours of a large number of virtual agents in a geo-referenced virtual world is now possible. We propose to apply these techniques in the shopping mall domain. In this paper, we present a multi-agent geo-simulation approach and a software, MallMAGS, which are used to model and simulate customers' shopping behaviours in virtual malls. Using such a geo-simulation, a manager can reproduce his or her mall layout, create a population of virtual shopper agents which mimic the behaviours of mall customers, observe how virtual shopper agents interact with the virtual mall and how they react to changes in the mall configuration. We suggest that SOLAP techniques (Spatial On Line Analytical Processing) be used to systematically analyse the results of these multi-agent geo-simulations. Resumes Dans le monde tres competitif de la vente au detail, les gerants de centres d'achats developpent de nombreuses strategies afin de differencier leurs centres de leurs competiteurs dans le but d'augmenter la loyaute de leurs consommateurs. Une strategie possible consiste a changer la configuration du centre d'achat, plus precisement la localisation des boutiques. Decider de la localisation des boutiques est une decision tres importante qui peut couter cher en termes d'argent et de temps. Dans le but de garantir le succes de telles decisions, les gerants de centres d'achats devraient etre capables de mieux comprendre les comportements des consommateurs et les facons par lesquelles ils pourraient reagir aux changements dans la configuration du centre d'achat. Des techniques traditionnelles telles que les sondages et l'utilisation de systemes d'information geographique peuvent aider a comprendre les comportements des consommateurs dans un centre d'achat existant, mais elles ne sont pas adequates pour prevoir les reactions des consommateurs a de futures dispositions du centre d'achat. Grace aux progres recents dans les milieux de la geo-simulation et des systemes d'agents multiples, simuler les comportements d'un grand nombre d'agents virtuels dans un monde virtuel geo-referencie est maintenant possible. Nous proposons l'application de ces techniques au domaine des centres d'achats. Dans cet article, nous presentons une approche de geo-simulation a agents multiples et un logiciel, MallMAGS, qui sont utilises afin de modeliser et simuler les comportements d'achat des consommateurs dans des centres d'achats virtuels. Utilisant une telle geo-simulation, un(e) gerant(e) peut reproduire sa disposition du centre d'achat, creant une population de agents clients virtuels qui imitent les comportements des consommateurs du centre d'achat, observer comment les agents clients virtuels interagissent avec le centre d'achat virtuel et comment ils reagissent aux changements dans la configuration du centre d'achat. Nous suggerons que les techniques SOLAP (Spatial On Line Analytical Processing--Traitement analytique spatial en ligne)) soient utilisees afin d'analyser systematiquement les resultats de ces geo-simulations a agents multiples. …
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".