Supporting Small Businesses and Local Economies Through Virtual

Reality Shopping and Artiﬁcial Intelligence: A Position Paper

Rub

en Grande

, Santiago S

anchez-Sobrino

, David Vallejo

, Jos

e Jes

us Castro-Schez

and Javier A. Albusac

School of Computer Science, Department of Technologies and Information Systems, University of Castilla-La Mancha,

Paseo de la Universidad 4, 13071 Ciudad Real, Spain

Keywords:

Virtual Reality, Artiﬁcial Intelligence, e-Commerce, Recommender Systems, Sustainability.

Abstract:

The rise of e-commerce and online sales has had a detrimental effect on small businesses that lacked an online

presence in recent years, with negative consequences for local services and economies. Despite attempts to

digitize businesses, large corporations continue to hold a privileged position that allows them to capture the

majority of sales. Small businesses may regain a competitive edge against large platforms by anticipating

and adapting to the next phases of commercial evolution, which are likely to be heavily reliant on Virtual

Reality shopping and Artiﬁcial Intelligence. In this article, we propose a platform that combines these two

technologies and enables local businesses to join forces and overcome physical barriers, thereby providing

a virtual world of unrestricted retail spaces. The system also proposes retail collection points and develops

attractive leisure plans around these points through the outcomes of a recommender system, thereby promoting

city activity and bolstering local economies.

1 INTRODUCTION

Small businesses have been declining in recent years

due to the increase in online shopping. The popu-

larity and increasing access to the Internet and mo-

bile devices (By 2020, 59% of the world’s population

owned a mobile phone) have driven the growth of e-

commerce, leading to a decrease in demand for prod-

ucts and services in physical stores, particularly in the

small enterprise sector (Saha, 2015).

In addition to this fact, the COVID-19 pandemic

consolidated the digitization process and increased

online purchases due to the restrictions and safety

measures implemented to prevent the spread of the

virus (Paraschiv et al., 2022). This allowed many peo-

ple to conduct basic transactions and run processes

from their homes, contributing to the digitization of

society.

However, this trend has had a negative impact on

a signiﬁcant part of small businesses, as many stores

https://orcid.org/0000-0002-0583-6865

https://orcid.org/0000-0001-6620-1719

https://orcid.org/0000-0002-6001-7192

https://orcid.org/0000-0002-0201-7653

https://orcid.org/0000-0003-1889-3065

and local businesses have had to close due to lack

of customers and income. This has caused a loss of

jobs and economic opportunities in the communities

where these businesses were located, and has con-

tributed to the disappearance of the local identity and

character of some areas. While the amount of online

purchases in 2020 increased by 41%, the attendance

of shopping centers decreased between a 20% and

45%, depending on the country, in comparison with

the same period in 2019 (Paraschiv et al., 2022). In

addition, retailers with online presence, such as Ama-

zon or the Alibaba Group, registered an increment

in unique visitors, revenue and many other indica-

tors compared to before pandemic (Dumanska et al.,

2021).

All the signs are that the pandemic’s effect on con-

sumption is liable to persist, such as the sales volume

in e-commerce growing ﬁve times faster that ofﬂine

retail sales in U.S. or over 65% of the people between

Baby Boomers and Generation Z shopping mainly on-

line since the pandemic breakout (Kim, 2022). More-

over, elderly people, who were the majority of small

enterprises’ customer base, use more frequently In-

ternet to ﬁnd information about goods and services

and shopping/buying them, according to recent stud-

ies (Rybaczewska and Sparks, 2022).

312

Grande, R., Sánchez-Sobrino, S., Vallejo, D., Castro-Schez, J. and Albusac, J.

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artiﬁcial Intelligence: A Position Paper.

DOI: 10.5220/0011964600003467

In Proceedings of the 25th International Conference on Enterprise Information Systems (ICEIS 2023) - Volume 2, pages 312-319

ISBN: 978-989-758-648-4; ISSN: 2184-4992

 2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

Despite these challenges, small businesses remain

an important part of the economy and society in many

places around the world (Ayandibu and Houghton,

2017). Many people still value and appreciate the

added value that local businesses bring, such as per-

sonalized service, product quality, and community

involvement. By recognizing and appreciating the

added value that local businesses bring, residents of

small cities can support these businesses and help en-

sure their continued success. This, in turn, can help to

maintain a vibrant and thriving local economy, as well

as a strong sense of community. Therefore, it is im-

portant to ﬁnd ways to support and strengthen small

businesses to ensure their survival and contribute to

balanced economic and social development.

In these circumstances, public national and inter-

national organisms are supporting the digitization of

small enterprises with funding initiatives. These are

oriented towards the creation of their online shops.

The motivation behind this approach lies in increas-

ing the competitive capacity of small businesses,

whose economic and human resources are very lim-

ited. However, the leading organizations in the sector

have already explored how to enhance the shopping

experience of its customers to promote new ways for

online shopping. In this context, technologies such as

Virtual Reality (VR), Augmented Reality (AR) and

Artiﬁcial Intelligence (AI), like recommendation sys-

tems, play an important role. Applications like Ama-

zon’s VR kiosks or IKEA’s Place AR are examples of

the application of some of these technologies. This

means that, despite the investment in digitizing small

businesses, they might be soon be unable to compete

when large corporations make further progress. In

this light, it may be sensible for the digitization ef-

forts of small retailers to be directed towards a state

of evolution that is rapidly approaching in the coming

years.

Thus, we ﬁnd it essential to identify solutions that

permit small shops to band together, overcome the

physical limitations of their small spaces, and offer

competitive prices, thereby concurrently stimulating

the activity of the city. VR and AI-based solutions can

meet these requirements. The true potential of using

VR is to improve online shopping customer’s experi-

ence, bringing it closer to a physical store experience,

while solving limitations of space and how much time

it is available (Xi and Hamari, 2021). AI will allow

us to improve business efﬁciency by increasing online

sales as well as boosting local businesses in a cooper-

ative way.

The aforementioned challenges represent the main

motivation to elaborate our proposal. In order to im-

prove local economies and increase their competitive

capacity, we propose an AI and VR-based platform

where small businesses unite to present themselves

to buyers. This increase in competitiveness is partly

driven by the use of disruptive technologies, the abil-

ity to offer lower prices, and the elimination of phys-

ical space limitations. The platform, in addition to

offering the ability to examine and evaluate products

in a way similar to in-person shopping through VR,

also includes the possibility of picking up purchased

products at local pick-up points. Additionally, asso-

ciated with the pick-ups, the platform will automati-

cally make recommendations for visiting local shops

where users can see the products that have caught

their interest and leisure plans based on various fac-

tors such as user proﬁle, purchased product, and the

time of pick-up, among others. These plans represent

an additional attraction for the buyer that could lead

to purchasing products from local businesses and en-

joying services, thereby strengthening the city’s econ-

omy.

The platform aims to be an innovative e-

commerce solution that allows small businesses (less

than 10 employees) with limited resources to develop

their commercial activities online, relying on VR and

AI, while also promoting the city’s economic life.

The proposal would allow small businesses to com-

pete with the big giants of e-commerce. Keep in mind

that more than 9 out of 10 (93.5%) enterprises in the

European Union are micro enterprises

The remainder of the paper is structured as fol-

lows. In Section 2, related works regarding VR shop-

ping proposals and prototypes are presented. In Sec-

tion 3, the proposed platform and the underlying ar-

chitecture are discussed. Challenges regarding the de-

velopment of this platform are shown in Section 4,

meanwhile the conclusions and future work are pre-

sented in Section 5.

2 RELATED WORK

2.1 Virtual Reality Shopping

In (Speicher et al., 2017) a prototype of Virtual Real-

ity Online Shopping Environment was developed and

evaluated by the authors in terms of inﬂuence of user

input (head pointing and speech) and output (desktop

and Head Mounted Display (HMD)) on task perfor-

mance and user’s preference and behavior. After car-

rying a survey where participants identiﬁed positive

and negative aspects of online shopping, the authors

https://ec.europa.eu/eurostat/statistics-explained/

index.php?title=Structural business statistics overview

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artiﬁcial Intelligence: A Position Paper

313

developed a prototype for desktop and smartphone

VR cases, where user input was limited to voice and

head pointing. Following the analysis of a case study

carried, design guidelines for virtual reality shopping

environments are proposed.

Later on, the same authors developed another VR

shop prototype using the Apartment metaphor (Spe-

icher et al., 2018) in order to study different selection

and manipulation techniques of products (grab and

beam) and different types of shopping carts (basket

and sphere). The authors carried a study with a proto-

type they developed. They concluded that immersion

and user experience were the most important aspects

for volunteers, as well as they introduce suggestions

to reduce motion sickness and types of products suit-

able for VR shops.

In (Veneruso et al., 2020) a VR application that

runs on Oculus Rift device is developed with the

aim to create a Virtual Dressing Room (VDR) based

on VR rather than on Augmented Reality (AR). The

main idea behind such application is to represent how

clothes ﬁts in an avatar made by the customer based

on body shape and size of the clothes selected.

In (Shravani et al., 2021) a VR online shopping

platform named VR Supermarket is presented. Such

system consists on a VR application developed in

Unity and deployed in the HTC Vive VR System,

and a dynamic recommendation system based on pur-

chase history hosted in a web server. While the VR

application handles the user input through controllers

and headset, it also interacts with the web server, that

is supported by an SQL database to make recommen-

dations. At the same time, the VR application re-

quires a NoSQL database for supporting data storage

and retrieval of products, supplementary information

or user information, among others.

The virtual environment that we aim to develop

is expected to change dynamically the products pre-

sented based on the recommendations made. How-

ever, the user will be allowed to visit the available

stores at any time.

2.2 Recommendation Systems

Recommendation systems have played a signiﬁcant

role in the success of e-commerce systems by pro-

viding personalized product and content suggestions

to customers based on their past behavior and prefer-

ences. These systems use various algorithms, such as

collaborative ﬁltering, content-based ﬁltering, hybrid

algorithms, and matrix factorization (Hussien et al.,

2021), to analyze customer data and generate recom-

mendations that are tailored to each individual user.

Collaborative ﬁltering algorithms, for example, use

data on customer preferences and past behavior to

make recommendations based on similar users, while

content-based ﬁltering algorithms use data on the

characteristics of individual products to make recom-

mendations based on customer preferences (Hwangbo

et al., 2018). Hybrid algorithms, on the other hand,

combine different types of algorithms to provide more

accurate and personalized recommendations.

Other kind of algorithms are Graph-based algo-

rithms, which use data on the relationships between

different products and customers to make recom-

mendations (Shaikh et al., 2017), Context-aware al-

gorithms, which use data on the context in which

recommendations are made (e.g. location, time,

device) to provide more relevant recommendations,

and Learning-to-rank algorithms, which use machine

learning techniques to learn the relative importance

of different factors in making recommendations (e.g.

customer preferences, product characteristics, past

behavior) (Karmaker Santu et al., 2017).

This has helped e-commerce businesses to im-

prove customer engagement and increase sales by

providing relevant and personalized recommenda-

tions to customers. In addition, recommendation sys-

tems can help to reduce the need for customers to

search for products, thereby making the shopping ex-

perience more convenient and efﬁcient.

In the context of VR shopping, recommendation

systems can play a similarly important role by pro-

viding personalized product suggestions and recom-

mendations to customers as they navigate virtual re-

tail spaces (Shravani et al., 2021). By analyzing cus-

tomer data and generating tailored recommendations,

VR shopping platforms can improve the customer

experience and drive business growth by providing

customers with relevant and personalized suggestions

(Huang et al., 2022). Furthermore, recommendation

systems can help VR shopping platforms to overcome

the physical limitations of traditional retail spaces by

providing customers with a virtual environment that

is tailored to their individual preferences and interests

(Elboudali et al., 2020).

These solutions are aimed to make recommenda-

tions of products in order to increase sales. How-

ever, our recommender system have to deal with these

recommendations and the generation of leisure plans

based on the user’s proﬁle, the date and time of col-

lection and the collection point.

ICEIS 2023 - 25th International Conference on Enterprise Information Systems

314

3 SMART VR-shopping

PLATFORM TO SUPPORT

SMALL BUSINESSES AND

LOCAL ECONOMIES

In our proposal, we consider the perspectives of both

the buyer and the seller in the context of a platform for

facilitating economic transactions. From the perspec-

tive of the buyer (see Figure 1), the platform aims to

provide high-quality services and customization ac-

cording to individual preferences and needs. Mean-

while, from the perspective of the seller and nearby

businesses, the platform seeks to enhance sales and

support the growth of local economies by generating

plans that include limited time sales and leisure activ-

ities (see Figure 2).

The architecture consists of three distinct layers.

The ﬁrst layer acts as an input interface between the

user and the system, either through virtual worlds or

through the web (if the user prefers). This layer is

responsible for capturing the user’s interactions with

the digital ecosystem.

The middle layer, responsible for automatic rea-

soning, is further divided into three sub-modules: (a)

a module that progressively deﬁnes the user’s proﬁle

and preferences, (b) a recommendation module that

aims to offer the user the best alternatives based on the

information proﬁled by the previous module, and (c)

a module responsible for generating leisure/cultural

plans associated with the product collection points.

Finally, the top layer is responsible for display-

ing the information generated for the user, including

changes in the virtual environment based on previous

interactions, recommendations, and plans generated,

as well as mechanisms for formalizing purchases.

The following subsections describe in more detail

each of the three main layers of the proposed archi-

tecture.

3.1 Input Interface Layer: Interaction

Between the User and the Virtual

World

Companies that compete in the retail sector are us-

ing AR and VR to create more immersive experiences

for its customers. In literature, many theories that

were applied to online and traditional shopping en-

vironments have been applied to VR shopping envi-

ronments, as well as case studies. It has been stated

that the interactivity of VR allows customers to un-

derstand better how to use a product and the ﬁt of

it, making customers feeling more reliable with their

purchase decisions (Xi and Hamari, 2021). In addi-

tion, brands could enhance purchase behavior, satis-

faction and brand loyalty thanks to the involvement

that VR technologies provide.

Regarding devices and technologies used, HMDs

are the most prominent devices in VR shopping stud-

ies. These provides a great range of input devices

and tracking technologies such as VR controllers,

head, hands and eye tracking, among others (Xi and

Hamari, 2021). It is interesting to note that currently

there are challenges being addressed to provide a high

immersive experience that could simulate the inspec-

tion of a product in a physical store. For instance,

an accurate hand tracking to manipulate products pre-

cisely is needed, as well as the responses of objects

to such manipulations. We believe that interaction

with virtual hands provide more immersion and better

feedback to the customer than those made with con-

trollers.

In order to build a customized experience for the

consumer, the virtual environment should be able to

adapt the products showed according to the user’s

preferences. Online shopping portals have made a

large progress in this ﬁeld with the aim to increas-

ing the consuming intention of its visitors. In a VR

shopping environment, the interactions performed in

this that the devices allow us to register play a critical

role to achieve it. Some variables that could be used

to build a robust user proﬁle are: time that an object

is being watched (eye tracking) (Pfeiffer et al., 2020),

time that an object is being inspected (hand tracking),

number of times that a product is inspected or added

to its wish-list, or the parameters changed to a given

product such as color or size.

3.2 AI-Based Reasoning Layer

The products exhibited in the virtual environment will

be supplied by the underlying AI layer, which takes

the user proﬁle as input in order to determine what

products are the best to be recommended to such user.

The ﬁrst time a new customer uses the system, it does

not hold any information regarding its preferences.

Therefore, the system will have a set of generic pro-

ﬁles that contains common shopping preferences of a

large number of consumers (Radu and Maican, 2015).

These proﬁles will allow the system make the ﬁrst rec-

ommendations before having knowledge of the user.

Later, the interactions that the user makes with the

products presented in the portal, will trigger the AI-

based recommendation system to update user’s pro-

ﬁle. Hence, the next time that the consumer gets into

the VR environment, the changes in such proﬁle will

be reﬂected in the products showed to him/her, if the

changes were signiﬁcant enough.

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artiﬁcial Intelligence: A Position Paper

315

INPUT

VR & WEB

User Input Interface

Hand Tracking

User location

in virtual

environment

Eye Tracking

Exploration of

virtual objects

VR Information Collector

Web Information

Collector

Activity monitoring

Mouse Keyboard

ACTIVITY

LOG

AI-Based

Reasoning

Layer

User Profile &

Preferences

User profile

configurator

Preference

setter

Processing and

Storage

User Profile &

Taxonomy

Environment

(companies,

products,

collection places)

Recommender

Customizer

based on user

profile

Product

Recommender

Processing and

Storage

Planner

Offer

customizer

Plan/offer

generator

around

product pick-

up points

Processing and

Storage

OUTPUT

Presentation of VR

information

Recommendations

Plans and

offers

Proposal tailored to the user

Secure purchasing

management

Figure 1: General architecture of an AI-based VR-shopping platform.

Additionally, this knowledge can also be used to

encourage the buyer to visit physical stores where

these products are located when they go to pick up

a purchase at a pick-up point

Every time a customer wants to purchase a prod-

uct, the portal will show the different buying options

they can select (see Figure 4). These options include

the price of the product itself and a generated plan that

includes offers and activities from businesses that are

near the product’s collection point. Based on the col-

lection point, the user’s proﬁle, and the pick-up time,

the plan will include different offers and activities, en-

hancing the economic activity of the businesses in-

cluded in the plan. Under this approach, we expect

local economies to be strengthened.

One of the key aspects of ensuring the proper and

long-term operation of the proposed platform is the

association of small businesses in the area. The mem-

bers of this association will be the companies pub-

lishing their products in the VR environment and the

businesses that will be considered for generating the

plans. In this context, it is important that the platform

promotes the plans in a fair way, distributing sales and

potential beneﬁts evenly.

This strategy begins by displaying the buy options

in a ranking-like style. The variables to be considered

are the user’s preferences, their geographical location,

the geographical location of the collection point, and

the sales and beneﬁts recorded historically in the sys-

tem. Therefore, the system will prioritize an option

that is convenient for the consumer but also better dis-

tributes the beneﬁts among the businesses in the asso-

ciation.

Once a purchase is made, the system will adjust

the weights given to the different businesses, modify-

ing the order in which future buy options and plans

ICEIS 2023 - 25th International Conference on Enterprise Information Systems

316

Figure 2: Elaboration of plan after sale. It includes offers and activities around the product collection point.

will be suggested. For example, a store that has had

many recent sales should be shown in a lower position

for future potential purchases, even though its offer

may be the best for the potential customer.

3.3 Output Layer

As mentioned earlier, the output layer is responsible

for presenting all changes in the virtual world and the

generated information (recommendations and plans)

to the user.

Therefore, we developed a prototype using the

Unity game engine for the Oculus Quest 2 VR headset

as a ﬁrst approach for this layer. The main idea is to

represent a shopping center with various stores, each

one focused on products based on their nature, such as

clothes, lifestyle products, toys, etc. Hence, the user

will be able to select a store of their preference to visit

and interact with the objects there.

Additionally, when the user opens the application,

the ﬁrst room they will see contains products sug-

gested based on the outcomes of the recommenda-

tion system, after the system creates the user’s proﬁle

based on their preferences.

To simulate a shopping experience closer to a

physical store, the user will use their hands to inter-

act with the virtual environment (see Figure 3). Once

the customer shows an intention to buy a product, it

will click a panel with a shopping cart icon. After

that, the buying options will be shown, indicating the

Figure 3: A sample of product interaction with hands in a

VR store.

collection point and the points of interest with which

the plan will be elaborated (see Figure 4).

In order to recreate a physical store as much accu-

rate as possible, factors such as lighting, shadows and

product size, among others, must be considered. Fig-

ure 5 shows some shelves with clothes. These prod-

ucts should look lifelike so that the user wants to in-

teract with it. Digital assets like textures and materi-

als should be used wisely to make the user feel that

he/she is inside a real shopping center or store.

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artiﬁcial Intelligence: A Position Paper

317

Figure 4: Prototype of panel with buying options for a cer-

tain product.

Figure 5: Shelves with clothes in one of the virtual stores.

4 DISCUSSION AND

CHALLENGES

The implementation of the proposed virtual reality

(VR) platform could bring signiﬁcant beneﬁts to so-

ciety, small businesses, and local economies. By pro-

viding a convenient and customized VR platform for

facilitating economic transactions, the platform has

the potential to promote economic growth and sup-

port the development of local economies.

For small businesses, the VR platform offers a

valuable opportunity to expand their customer base

and increase sales. By providing easy access to a wide

range of potential customers through immersive VR

experiences, the platform can help small businesses

to grow and thrive in a competitive market. Fur-

thermore, the platform’s ability to customize VR ser-

vices and offers according to individual preferences

and needs can help small businesses to better meet

the needs of their customers and build long-term rela-

tionships.

For local economies, the VR platform has the po-

tential to support economic development by promot-

ing local commerce and fostering strong connections

between businesses and consumers. By facilitating

economic transactions and supporting the growth of

small businesses through the use of VR technology,

the platform can help to create jobs, stimulate eco-

nomic activity, and strengthen the local economy.

In addition to the beneﬁts discussed in the previ-

ous paragraphs, the proposed VR platform also has

the potential to support eco-friendly solutions. By in-

cluding pickup points as part of the platform, the need

for packages to be shipped long distances can be re-

duced, which can help to reduce emissions from trans-

portation. Additionally, the use of pickup points can

reduce the amount of packaging and materials used

for shipping, which can help to reduce waste and min-

imize the environmental impact of the platform.

Despite the possible beneﬁts of the platform, we

have identiﬁed challenges that will be faced during

the development of the project. First, the underlying

recommendation system algorithm must be deﬁned to

distribute potential sales and beneﬁts evenly. The ex-

isting approaches and algorithms to build recommen-

dation systems will be inspected to have a consistent

background to deﬁne such algorithm. Such algorithm

also involves the plan generator, which also should

be fair. Moreover, we must explore the different VR

devices and its services in order to ﬁnd the one that

provides the best hand and eye tracking, among oth-

ers.

Another challenge regarding available VR head-

sets is its hardware limitations. The 3D models to be

used like products and assets to build the stores must

have quality enough to look realistic. However, they

should be optimized to avoid overheating the headset,

since it could make the user sick.

5 CONCLUSIONS AND FUTURE

WORK

In this article, we have discussed the need for small

businesses to digitize in order to improve their com-

petitiveness and prevent their disappearance in the

face of online retail giants. We have argued that re-

sources and aid for digitization should be directed to-

wards achieving a future state in which virtual real-

ity (VR) and artiﬁcial intelligence (AI) will play a

prominent role in the commercial landscape. Based

on this idea, we have proposed a VR platform that al-

lows small businesses to offer their products in an at-

tractive and immersive way from the comfort of their

ICEIS 2023 - 25th International Conference on Enterprise Information Systems

318

own homes. The platform also allows retailers to

join forces to offer more competitive prices and in-

corporates pickup points to support local economies.

In addition to the economic beneﬁts of the pro-

posal, we have also highlighted its potential to sup-

port eco-friendly solutions by reducing the need for

long-distance shipping and packaging waste. Overall,

the VR platform offers a comprehensive solution for

promoting the growth of small businesses and local

economies in a sustainable, digitally-advanced future.

The working lines on which we will strive include

the precise scanning and integration of real products,

including accessibility options to interact in the vir-

tual space, modeling of user proﬁles through interac-

tions with products or the dynamic generation of vir-

tual exhibitors.

ACKNOWLEDGEMENTS

This work has been founded by the Span-

ish Ministry of Science and Innovation

MICIN/AEI/10.13039/501100000033, and the

European Union (NextGenerationEU/PRTR), under

the Research Project: Design and development of

a platform based on VR-Shopping and AI for the

digitalization and strengthening of local businesses

and economies, TED2021-131082B-I00.

REFERENCES

Ayandibu, A. and Houghton, J. (2017). The role of Small

and Medium Scale Enterprise in Local Economic De-

velopment (LED). 11:133–139.

Dumanska, I., Hrytsyna, L., Kharun, O., and Matviiets,

O. (2021). E-commerce and M-commerce as Global

Trends of International Trade Caused by the Covid-19

Pandemic. WSEAS TRANSACTIONS ON ENVIRON-

MENT AND DEVELOPMENT, 17:386–397.

Elboudali, A., Aoussat, A., Mantelet, F., Bethomier, J., and

Leray, F. (2020). A customised virtual reality shop-

ping experience framework based on consumer be-

haviour: 3DR3CO. International Journal on Interac-

tive Design and Manufacturing (IJIDeM), 14(2):551–

563.

Huang, J., Zhang, H., Lu, H., Yu, X., and Li, S. (2022). A

novel position-based vr online shopping recommenda-

tion system based on optimized collaborative ﬁltering

algorithm.

Hussien, F. T. A., Rahma, A. M. S., and Wahab, H. B. A.

(2021). Recommendation systems for e-commerce

systems an overview. Journal of Physics: Conference

Series, 1897(1):012024.

Hwangbo, H., Kim, Y. S., and Cha, K. J. (2018). Rec-

ommendation system development for fashion retail

e-commerce. Electronic Commerce Research and Ap-

plications, 28:94–101.

Karmaker Santu, S. K., Sondhi, P., and Zhai, C. (2017). On

application of learning to rank for e-commerce search.

In Proceedings of the 40th International ACM SIGIR

Conference on Research and Development in Informa-

tion Retrieval, SIGIR ’17, page 475–484, New York,

NY, USA. Association for Computing Machinery.

Kim, R. (2022). Retail After COVID-19: Use Virtual Real-

ity to Enhance Ecommerce. pages 118–123.

Paraschiv, D. M., T

an, E., Manea, D. I., Ionescu, C. D.,

Mihai, M., and S

erban, O. (2022). The change in

e-commerce in the context of the Coronavirus pan-

demic. Management & Marketing, 17(2):220–233.

Num Pages: 220-233 Place: Bucharest, Poland Pub-

lisher: De Gruyter Poland.

Pfeiffer, J., Pfeiffer, T., Meißner, M., and Weiß, E.

(2020). Eye-tracking-based classiﬁcation of infor-

mation search behavior using machine learning: Ev-

idence from experiments in physical shops and virtual

reality shopping environments. Information Systems

Research, 31(3):675–691.

Radu, L. and Maican, C. (2015). Personalization in e-

commerce using proﬁles similarity. Bulletin of the

Transilvania University of Brasov. Series V : Eco-

nomic Sciences, 8.

Rybaczewska, M. and Sparks, L. (2022). Ageing con-

sumers and e-commerce activities. Ageing & Society,

42(8):1879–1898. Publisher: Cambridge University

Press.

Saha, A. (2015). A Study on ”The impact of online shop-

ping upon retail trade business”. IOSR Journal of

Business and Management, 2:74–78.

Shaikh, S., Rathi, S., and Janrao, P. (2017). Recommenda-

tion system in e-commerce websites: A graph based

approached. In 2017 IEEE 7th International Advance

Computing Conference (IACC), pages 931–934.

Shravani, D., R, P. Y., Atreyas, P. V., and G, S. (2021). VR

Supermarket: a Virtual Reality Online Shopping Plat-

form with a Dynamic Recommendation System. In

2021 IEEE International Conference on Artiﬁcial In-

telligence and Virtual Reality (AIVR), pages 119–123.

Speicher, M., Cucerca, S., and Kr

uger, A. (2017). VR-

Shop: A Mobile Interactive Virtual Reality Shopping

Environment Combining the Beneﬁts of On- and Of-

ﬂine Shopping. Proceedings of the ACM on Interac-

tive, Mobile, Wearable and Ubiquitous Technologies,

1(3):102:1–102:31.

Speicher, M., Hell, P., Daiber, F., Simeone, A., and Kr

uger,

A. (2018). A virtual reality shopping experience using

the apartment metaphor. In Proceedings of the 2018

International Conference on Advanced Visual Inter-

faces, AVI ’18, pages 1–9, New York, NY, USA. As-

sociation for Computing Machinery.

Veneruso, S. V., Catarci, T., Ferro, L. S., Marrella, A., and

Mecella, M. (2020). V-door: A real-time virtual dress-

ing room application using oculus rift. In Proceedings

of the International Conference on Advanced Visual

Interfaces, AVI ’20, New York, NY, USA. Associa-

tion for Computing Machinery.

Xi, N. and Hamari, J. (2021). Shopping in virtual reality: A

literature review and future agenda. Journal of Busi-

ness Research, 134:37–58.

Supporting Small Businesses and Local Economies Through Virtual Reality Shopping and Artiﬁcial Intelligence: A Position Paper

319