Smart Retail Research Articles

Exploring smart retailing: anthropomorphism in voice shopping of smart speaker

PurposeThe purpose of this paper is to investigate the effects of anthropomorphism and identify factors related to adopting voice shopping on smart speakers.Design/methodology/approachProgress in partial least squares structural equation modeling (PLS-SEM) approach is used to test the proposed research framework regarding anthropomorphism and user perceptions on voice shopping via smart speakers. Individuals' responses to questions about attitude and intention to use voice shopping via smart speakers were collected and analyzed.FindingsThe results showed that anthropomorphism had a positive influence on satisfaction, which, in turn, had a positive impact on intention to adopt voice shopping, and customers had positive opinions regarding smart speakers.Research limitations/implicationsThis study only reflects a younger perspective on smart speaker voice shopping. This study identified the characteristics of smart speakers that increase customers' intention to purchase, which can be used to formulate sales strategies and management guidelines.Practical implicationsThis research provided a new perspective to enable practitioners to promote smart speakers for voice shopping. Smart speaker manufacturers can utilize the findings of this research to improve the system design of smart speakers to further facilitate voice shopping.Originality/valueUnlike previous studies, which focused on product attributes of smart speakers or voice shopping experiences, this study provided a clear picture of how the anthropomorphic feature of smart speakers affects customers' intention to adopt voice shopping.

Data Ecosystem Business Models

Purpose: Organizations evolve from using and governing data internally towards the exchange of data in multi-organizational data ecosystems. The purpose of this research is to determine a business model framework for actors operating in and/or entering a data ecosystem. Methodology: To determine a business model framework in data ecosystems. an analysis was made based on how the research fields of “business models”, “data governance”, “data ecosystems”, “data sharing”, “business ecosystem” complement each other. A business model framework was created, which was applied to three use case studies in the field of Smart Cities and Urban Digital Twins: The Helsinki Digital Twin, the Rotterdam Digital Twin, and the Smart Retail Dashboard in Flanders. Findings: The business model of actors in a data ecosystem is determined by value and control factors. Value is determined by the capability to create value through the exchange of data in the ecosystem, and to capture value through revenue (sharing) models and cost (sharing) models. Control is determined by ecosystem control. Governance models on the ecosystem level are required to enable the collaboration and to ensure trust to allow for the willingness to share data. Additionally, data governance on an ecosystem level is required, enabling the data exchange between the actors. Research Limitations: The model was applied to three use cases in Smart Cities and Urban Digital Twins. Consequently, the data ecosystems concern a high presence of public actors, yet also includes private companies. The applicability needs to be identified in other sectors in further research. Additionally, as the scope of the study was on business models, data governance, data-sharing and data ecosystems, abstraction was made of fields of study beyond these topics. Value and practical implications: The Data Ecosystem Business Model framework can serve as a guideline for organizations entering a data ecosystem, as well as for actors aiming to establish novel data ecosystems. Additionally, the framework can serve as a high-level overview for further research into the field of business models in data ecosystems.

IoT-based Automatic Dust Monitoring and Suppression System for Coal Warehouses and Processing Areas with a Reduction in Water Consumption

Dust is a serious problem at coal warehouses and processing areas of coal mines in Vietnam. At present, almost coal mines use high pressure mist machines to suppress dust. Several coal mines build fixed mist spray systems for dust suppression. These systems are manually controlled. This could lead to use too much water for suppressing dust and affect negatively coal quality. IoT is a new technology and applied to various fields such as smart home, smart city, smart agriculture, smart retail, smart health as well as in industry etc. This article presents a new IoT model for automatically monitoring and suppressing dust with a reduction in water consumption. Specially, the proposed model not only automatically monitoring dust density and warning when it is greater than the limit value but also automatically adjust open angle of water valve to save water according to the measured dust density.The simulation results demonstrate that the proposed model stably operates and uses less water for suppressing dust. In addition, the system allows to automatically/manually turn on/off the water pump as well as water valve according to the dust density. This will save more water and even energy. Furthermore, in order to protect sensor data when transmitted over wifi network, we use WPA wifi security protocol, and to reduce effects of noise, Kalman filter is applied to the proposed system.

Smart retail at Algramo: Addressing environmental issues competitively

The retail sector constantly works hard to enhance consumer experience and maximize profit margins by improving operational effectiveness. The approach of smart technology in-store management, known as “smart retailing” works on this issue and helps increase positive customer experience. This case narrates the use of smart technology in Algramo—a start-up based in Chile, by getting information from secondary sources. It discusses the execution of the mission of Algramo to help everyone drastically alter their consumption patterns to ensure a prosperous future for both the current and following generations. This case portrays how Algramo is using this technology-led innovation to combat tax for the poor, revolutionize the way consumers spend, and mitigate climate change.

Smart Fruit Basket

This paper discusses smart retailing solutions, self-checkout stores in particular. Since RFID tag-based product identification accounts for various limitations, the authors propose a smart basket to facilitate self-checkout mechanism for fruits and vegetables, based on multi-view image recognition and weight sensor. The system works on a multi-view model and recognizes and counts the fruit/vegetables from four camera views to handle the occlusions. The user places fruits inside the basket. Multiple cameras installed provide different views inside the basket and captures this fruit placing activity. Different views are then processed for image recognition using CNN (convolutional neural network). The authors also present a multi-view fruit recognition (MVFR) dataset to evaluate the system performance. The base of smart basket includes a weight sensor to account for weight information, the weight, and count information of fruit assist in bill generation at self-checkout station.

A Customer Behavior Recognition Method for Flexibly Adapting to Target Changes in Retail Stores.

To provide analytic materials for business management for smart retail solutions, it is essential to recognize various customer behaviors (CB) from video footage acquired by in-store cameras. Along with frequent changes in needs and environments, such as promotion plans, product categories, in-store layouts, etc., the targets of customer behavior recognition (CBR) also change frequently. Therefore, one of the requirements of the CBR method is the flexibility to adapt to changes in recognition targets. However, existing approaches, mostly based on machine learning, usually take a great deal of time to re-collect training data and train new models when faced with changing target CBs, reflecting their lack of flexibility. In this paper, we propose a CBR method to achieve flexibility by considering CB in combination with primitives. A primitive is a unit that describes an object’s motion or multiple objects’ relationships. The combination of different primitives can characterize a particular CB. Since primitives can be reused to define a wide range of different CBs, our proposed method is capable of flexibly adapting to target CB changes in retail stores. In experiments undertaken, we utilized both our collected laboratory dataset and the public MERL dataset. We changed the combination of primitives to cope with the changes in target CBs between different datasets. As a result, our proposed method achieved good flexibility with acceptable recognition accuracy.

Preliminary Study of Supermarket’s Mobile Application Needs For Indonesian Shopper

The increasing interest in smart city development provides an opportunity for retail to enter into what is known as the smart retail concept. Smart retail is a smart shopping concept with the help of technology. One of the technologies that can be used in the implementation of smart retail is smartphones. In Indonesia, large supermarkets such as Yogya and Super Indo have implementing smartphone technology, into their mobile applications. However, based on the results of user reviews in the App store/Playstore media, the application is still considered not very effective. This is what makes researchers interested in evaluating mobile applications for supermarkets. The method used in this research is mixed method by conducting Focus Group Discussions and Questionnaires. The results of the data were analyzed with the aim of finding problems commonly experienced by visitors. There were 6 FGD participants and 137 questionnaire respondents included in this study. Based on the results, it is found that the current applications do not meet consumer needs, this is because consumers prefer to shop directly at the supermarket. However, in the process of in-store shopping activity, problems are still often found, such as difficulty in finding the location of the product, the product is unavailable, there is no information on the price of the product on display, and so on. Thus, the type of application that has the potential as a solution to this problem is an application to help visitors in doing in-store shopping activities at the supermarket.

Evaluating Residual LSTM approach for predicting missing sensor data for IoMT


 
 
 Currently we are living in a digital age due to advancements in the fields like Internet of Things, Artificial Intelligence and Big Data. Especially IoT applications like Smart Home, Smart Watch, Smart Farming, Smart Retail and Smart Parking are seen everywhere around us. These applications are termed Smart due to their ability of self-decision making and monitoring surrounding environment. Data is the most precious assets that requires to make IoT application smart. But multiple times sensor data is found missing or noisy. Due to various reasons like sensor malfunction, sensor maintenance and poor internet communication between devices leads to rise of missing values. In majority cases Missing Completely at Random (MCAR) type missing data are found. Hence, we propose a Residual LSTM model approach for more accurate prediction of missing sensor data on TILES dataset consisting features like Breathing Depth, Breathing Rate and Heart Rate. Compared to approaches like Mean, Median, K-Nearest Neighbours’ and Bidirectional Recurrent Neural Network the Residual Long Short-Term Memory model yields better accuracy which is of huge importance in IoMT application.
 
 
 
 
 
 
 
 

RecIoT: A Deep Insight into IoT-Based Smart Recommender Systems

Typically, Internet of Things (IoT) is perceived as the technology for connecting people, devices, vehicles, home appliances, etc., and 212 billion heterogenous devices are presumed to be connected by 2020 under its umbrella. This domain is gaining popularity worldwide because of the wave it has brought in both research and industrial sector. Smart applications of this scenario provide assistance and services to the users in smart homes, smart cities, smart retail, agriculture, healthcare, etc. However, researchers are now exploring the potential of IoT systems in other domains, one of them being recommender systems. In recent years, the focus of researchers has drifted towards utilizing recommender systems to improve offered selections to IoT users. Therefore, the aim of this paper is to study the present practices, approaches, and challenges in the aforementioned domain along with possible solutions. Briefly, the contributions of this paper are as follows: (1) providing an overview of the prevailing scenario in a range of application domains associated with IoT based recommender systems, (2) providing a framework of some real-world applications, (3) outlining key areas for the improvement towards context-aware personalized services in the future research, and (4) providing a bibliometric trend analysis prevalent in the concerned domain.

Expert Opinions on Smart Retailing Technologies and Their Impacts

The share of e-commerce has been rising uninterrupted for many years, but the largest share of sales is still achieved in stationary retail. Nevertheless, many retailers are forced to address the benefits that consumers have gotten used to through digital shopping experiences. Smart Retailing (SR) is seen as a possible solution for brick-and-mortar stores to answer the challenges created by the rise of e-commerce. This study aims to present the current state of research in SR and evaluate its potential to confront the challenges that have arisen in the industry. To do so, we built upon insights from previous works, in which we derived specific areas of impact that need to be considered when implementing those technologies. In this work, we substantiate our developed assessment with empirical data generated through the analysis of exploratory expert interviews. The \textit{gain of valuable data} and the \textit{personalization of the shopping experience} are confirmed among the positive impact factors. At the same time, \textit{privacy concerns} and \textit{customer acceptance risk} were the most discussed negative impact factors in the interviews. Finally, the interview findings were used to adapt the Technology Acceptance Model (TAM) to the specific context of SR. Overall, this work provides more profound insight into the essential factors that need to be considered by brick-and-mortar retailers to face the increasing pressure imposed by online competition.

Smart Meters and Retail Competition: Trends and Challenges

Retail electricity competition has been introduced for over a decade in many markets, but challenges in having an active retail market remain. Universal smart meters have also emerged as a trend. What is the interaction between competition and smart meters? What role can information via smart meters play in these markets? Has it enabled enhanced competition? Or has it further increased the incumbent's advantage? We present an overview and preliminary exploration using an aggregate data set from the Spanish electricity market. The evidence suggests that competition challenges remain large, although some modest evidence of increased pricing innovation exists.

Performance improvement of Routing Protocol for Low‐Power and Lossy Networks protocol in an Internet of Things‐based smart retail system

SummaryThe Internet of Things (IoT) technology improvement has led to concepts such as smart retail and supply chain management systems. The main problem with IoT‐based smart retail and supply chain management systems is the need for a high‐speed network for responding quickly to many transactions within the network. If the network is not able to respond to all transactions quickly, it will not be possible to handle all requests in time. Also, the network must be stable and reliable to ensure that all requests are received and answered. And finally, they must have a very low power consumption metric to reduce costs. This paper suggests a Multi‐Sink Routing Protocol for Low‐Power and Lossy Networks (RPL) topology for network node placement to achieve network performance improvement. The proposed topology is modeled in a simulated environment using an Instant Contiki operating system by Cooja simulator and is evaluated regarding the different performance metrics including packet delivery ratio (PDR), power consumption, node participation, and control traffic overhead. Also, the network behavior is analyzed by the Wireshark tool. The results show achieving better performance and improving the level of confidence.

Mask R-CNN with New Data Augmentation Features for Smart Detection of Retail Products

Human–computer interactions (HCIs) use computer technology to manage the interfaces between users and computers. Object detection systems that use convolutional neural networks (CNNs) have been repeatedly improved. Computer vision is also widely applied to multiple specialties. However, self-checkouts operating with a faster region-based convolutional neural network (faster R-CNN) image detection system still feature overlapping and cannot distinguish between the color of objects, so detection is inhibited. This study uses a mask R-CNN with data augmentation (DA) and a discrete wavelet transform (DWT) in lieu of a faster R-CNN to prevent trivial details in images from hindering feature extraction and detection for deep learning (DL). The experiment results show that the proposed algorithm allows more accurate and efficient detection of overlapping and similarly colored objects than a faster R-CNN with ResNet 101, but allows excellent resolution and real-time processing for smart retail stores.

An Approach to Assessing Shopper Acceptance of Beacon Triggered Promotions in Smart Retail

This paper studies shopper acceptance for using beacons in the purchase process. The main goal is to examine shopper response to beacon-triggered promotions and propose a model that would help retail practitioners plan the implementation of beacons in stores. The model was evaluated via an in-market test to examine the effects of beacon-triggered promotion on shopper attention, technology acceptance, and the decision to purchase. The test was conducted in Belgrade, Serbia in 10 representative stores where beacons were implemented with 10 twin control stores. The SimplyTastly mobile application was used for sending notifications. Furthermore, two more in-market beacon activations were analysed in Croatia and Bulgaria. The results showed that shoppers accepted beacon technology and that beacon-triggered promotion had a positive impact on shopper attention, purchase behaviour, and the decision to purchase. The results show that the proposed model could serve as a sound basis for the implementation of beacon technology in retail.

Drivers and challenges of internet of things diffusion in smart stores: A field exploration

The digitally disruptive environment has evolved rapidly due to the introduction of new advancements within the field of smart applications. Applications of one of the most prominent technologies, Internet of Things (IoT), often appear in the retail sector, where smart services have transformed the customer experience holistically. Presented in this paper are the findings from an exploratory field study in the retail service sector, which drew on the views of experienced practitioners about the smart store experience and the associated changes. The paper presents an overview of the drivers of smart retail service diffusion and the relevant challenges, such as the business expectations and the heterogeneity of devices. The arising themes indicate that IoT security is a major challenge for businesses installing IoT devices in their journey towards smart store transformation. The paper highlights the importance of a secure data-sharing IoT environment that respects customer privacy as the smart experience in-store offers data-driven insights and services. Implications for research and practice are discussed in terms of the customer experience relevant to the identified challenges.

Chatbots in retail: How do they affect the continued use and purchase intentions of Chinese consumers?

AbstractThe application of artificial intelligence in the retail industry has exposed many innovation opportunities and significantly impacts consumer behavior. Based on the social presence, retailer innovativeness, and self‐determination theories, this study constructs an integrated and original framework for elucidating the influence mechanism of the social characteristics of anthropomorphic intelligent services (chatbots) on consumer behavioral intentions. An empirical study of Chinese consumers (n = 442) reveals the following: first, the social presence of chatbots exerts a direct and positive impact on retailer experience innovativeness and intimacy; second, retailer experiential innovativeness, intimacy, and sense of empowerment mediate the influence of the social presence of chatbots on consumers' behavioral intentions; third, the cute communication styles in the low‐level social presence are very conducive for promoting the relationships between social presence and experiential innovativeness. By improving the level of social presence, formal communication styles can play a key role in promoting relationships. Theoretically, this study contributes to the social presence theory by extending it to the interaction with retailer experiential innovativeness and exploring the chain‐like mediating role of experiential innovativeness, as well as the self‐determined satisfaction between the social presence and consumer behavior intentions. Furthermore, this study also examines how different chatbot communication styles moderate the influence of social presence on consumers' behavioral intentions, thereby revealing the differential effects and boundary conditions of chatbot social presence on consumer behaviors. These findings will offer retailers insights into consumers' psychological activities to practically design chatbots and conduct smart retail innovation activities.

Factors affecting acceptance of smart retail solutions in Hungary: an empirical study using UTAUT2 model

In today's digitalisation process, retail is also undergoing a transformation, with the emergence of new smart solutions. Integrating intelligent solutions into a business model means new strategic challenges for retailing companies. The aim of the research is to examine the factors influencing the behavioural intention and use behaviour of smart retail solutions (SRS). The proposed model was based on the extended Unified Theory of Acceptance and Use of Technology (UTAUT2). Data was collected by conducting a questionnaire of 302 Hungarian respondents. Confirmatory factor analysis (CFA) and partial least squares (PLS-SEM) estimation were implemented. The results showed that behavioural intention is significantly and positively influenced by effort expectancy and it is significantly and negatively influenced by facilitating conditions. Most of the respondents are not yet regular users of SRS, and the market penetration of front-end intelligent solutions in retail is considered as rather low. JEL code: M10, M31, O14

Wireless Communication Technologies for IoT in 5G: Vision, Applications, and Challenges

Communication technologies are developing very rapidly and achieving many breakthrough results. The advent of 5th generation mobile communication networks, the so-called 5G, has become one of the most exciting and challenging topics in the wireless study area. The power of 5G enables it to connect to hundreds of billions of devices with extreme-high throughput and extreme-low latency. The 5G realizing a true digital society where everything can be connected via the Internet, well known as the Internet of Things (IoT). IoT is a technology of technologies where humans, devices, software, solutions, and platforms can connect based on the Internet. The formation of IoT technology leads to the birth of a series of applications and solutions serving humanity, such as smart cities, smart agriculture, smart retail, intelligent transportation systems, and IoT ecosystems. Although IoT is considered a revolution in the evolution of the Internet, it still faces a series of challenges such as saving energy, security, performance, and QoS support. In this study, we provide a vision of the Internet of Things that will be the main force driving the comprehensive digital revolution in the future. The communication technologies in the IoT system are discussed comprehensively and in detail. Furthermore, we also indicated indepth challenges of existing common communication technologies in IoT systems and future research directions of IoT. We hope the results of this work can provide a vital guide for future studies on communication technologies for IoT in 5G.

Understanding consumer perceptions and attitudes toward smart retail services

PurposeThis study aims to identify the antecedent factors influencing consumer attitudes and patronage intentions toward an intelligent unmanned convenience store (IUCVS) in Taiwan. The IUCVS is a new smart service that offers customers a novel shopping experience, given that it avoids queues and physical contacts with cashiers. However, studies discussing IUCVS remain scant owing to its brief history.Design/methodology/approachThis research develops a synergistic model combining original unified theory of acceptance and use of technology (UTAUT) constructs with perceived risk and value to test differences between unexperienced and experienced customers’ attitudes and patronage intentions toward IUCVSs. Data collected from 268 experienced and 156 unexperienced consumers were tested against the proposed research model using partial least squares (PLS) structural equation modeling and multi-group analysis (PLS-MGA).FindingsIn line with expectations, three UTAUT variables (i.e. performance, effort expectancy and social influence) and perceived value significantly and positively influence consumer attitudes toward IUCVSs. This research confirms the significant and negative direct effect of perceived risk on consumers’ patronage intentions toward IUCVSs. Furthermore, the PLS-MGA results unveil that a significant difference exist in the effects of perceived convenience value on attitudes toward IUCVS between consumers who had experience of using self-service machines and those who have not.Originality/valueThis research successfully fills the research gap by offering a synergistic model for evaluating consumers’ attitudes and patronage intentions toward a new smart service. Several important theoretical and practical implications are provided to help retail managers develop service strategies.

Quantitative Analysis of Consumption Influencing Factors in Smart Retail Scenarios Based on Structural Equation Modeling

Taking Beijing as an example, we explore the paths and effects of several key factors on urban residents' consumption in smart retail scenarios. The study measured business identification (BI), marketing perception (MP), product experience (PE), environmental experience (EE) and purchase intention (PI). A structural equation model of the relationship between the five latent variables and their influences was constructed based on the measurement of the five influences of purchase intention (PI). In addition, the six observed variables of payment form, type, quality, logistics and delivery, shop environment and discount are very important in influencing purchase intention. Accordingly, the problems associated with smart retailing at this stage of development are identified and methodological recommendations are made. These include improving consumers' commercial acceptance of smart retail, optimising the product mix, strengthening the marketing management of smart retail and improving the quality of smart retail services.