Clusters Of Consumers Research Articles

Bridging gaps in the demand and supply for circular economy: Empirical insights into the symbiotic roles of consumers and manufacturing companies

Given the systemic nature of the circular economy (CE), its successful implementation necessitates a holistic approach involving all the relevant stakeholders across the production and consumption processes. This study focuses on the gap between the demand and supply of circularity by investigating transitioning profiles of consumers and manufacturing companies and examining their symbiotic roles in shaping a systemic circular transition. Using two extensive surveys involving 1000 consumers and 1443 manufacturing companies in Italy, and employing a cluster analysis methodology, we examined pro-environmental purchasing profiles among consumers and varying levels of circular practice integration among companies. The cluster analysis reveals four different consumer cluster based on their attitudes towards CE during the purchasing and post-purchasing phases. While the majority focused only on a single purchasing aspect, approximately one-third consistently optimized, preserved, and enhanced product value throughout the purchase phase and post-purchase use. Conversely, companies were grouped into five clusters according to their varying levels of circularity integration across the product life cycle. Only a small subset of companies fully embraced circularity throughout their entire product life cycle, with most concentrating their efforts on specific phases of the value chain. The findings highlight a significant gap between circular demand and supply: while the biggest cluster of companies comprises linear manufacturers, linear consumers represent the smallest segments. This underscores the need for comprehensive engagement from both manufacturers and consumers in shaping circular production and consumption. Based on a stakeholder perspective, the study opens up a discussion on how to bridge this gap, emphasizing the role of consumers with pro-circular behaviors in pushing companies to integrate circularity principles more thoroughly, and the role of companies in raising the awareness of linear consumers about the impact of their purchasing choices. By profiling circular companies and consumers and unveiling their behavioral tendencies, this research provides actionable insights for policymakers and managers navigating the circular transition.

Adaptation and resilience in retail: Exploring consumer clusters in the new normal

PurposeThis research delves into the diverse responses of individuals to the challenges of the COVID-19 pandemic and subsequent shopping behaviour. DesignBased on the K-means clustering algorithm, a comprehensive analysis of survey data identifies distinct consumer clusters based on their adaptive capacities, resilience, and shopping preferences. The study encompasses a broad demographic spectrum, examining various aspects such as age, urban or rural residence, education, household size, and income. FindingsThe findings identify several clusters of consumers showing specific behaviour during the COVID-19 pandemic and their subsequent shopping behaviours, unveiling distinct profiles of adaptation, resilience, and shopping preferences. The K-means clustering algorithm allows the identification of four distinct consumer clusters. ImplicationsThe results have significant implications for understanding consumer behaviour, tailoring marketing strategies, and shaping the future of retail under the New Normal. Each cluster's characteristics provide valuable insights for businesses to align strategies with evolving consumer needs, considering both demographic factors and shopping preferences. OriginalityThe research contributes to the understanding of consumer behaviour during times of crisis, providing relevant insights from a theoretical perspective based on the K-means clustering algorithm.

Environmental Awareness and Social Sustainability: Insights from an Agent-Based Model with Social Learning and Individual Heterogeneity

Social sustainability requires both technological innovations and societal changes within energy systems, with decentralization playing a critical role. This shift emphasizes the increasing importance of individual user decision-making, posing significant management challenges. An individual’s environmental awareness has a key influence on their energy decisions. However, the relationship between individual environmental awareness and social sustainability, particularly from a systemic perspective, remains underexplored. Our study uses agent-based modeling to examine this relationship within Japan’s electricity market, focusing on social learning and consumer heterogeneity. We find that social learning leads to the formation of consumer clusters with specific electricity preferences, affecting environmental awareness differently across high- and low-carbon groups. This process reveals the nuanced role of social learning in promoting low-carbon technology adoption, which varies according to the market share of low-carbon energy. Additionally, our results suggest that initial heterogeneity in environmental awareness among consumers has a limited and varied effect on sustainable transition pathways. However, the diversity resulting from social learning significantly shapes these trajectories. These insights highlight the complex interplay between individual behaviors, societal dynamics, and technological advancements in steering the sustainable transition, providing valuable considerations for future energy system management.

Plant-based fish analogues vs. fish: Assessment of consumer perception, acceptance, and attitudes

Plant-based fish is developed to mimic the taste, texture, and appearance of fish. Despite being the fastest-growing segment in plant-based analogues sales, it remains a niche product due to several hindrances, including sensory and nutritional issues. This study assessed consumer perception, attitudes and acceptance drivers of plant-based canned tuna involving 165 consumers who evaluated for liking and described through the Check-All-That-Apply method five plant-based and three animal-based samples. Consumers’ food neophobia level, food related lifestyles and food frequency consumption of a series of plant-based and animal-based products were investigated as potential explanatory variables in drivers of acceptance. Generalised linear models showed that plant-based samples scored very low (<40 VAS score), while animal-based products were well accepted (63.6 – 75.2). Principal Coordinate Analysis revealed that pink colour, tuna/fish flavour, and dryness characterised tuna samples and contributed positively to liking, while unappealing appearance, off-flavour, legume/vegetable flavour, bitterness, gelatinous and gumminess, characterised plant-based samples and contributed negatively to liking. Agglomerative hierarchical analysis identified two consumer clusters differing in liking for plant-based fish analogues. One cluster (27 % of consumers) showed significantly higher liking scores for all plant-based samples, a higher consumption of plant-based analogues and seemed more careful when buying food, both regarding its nutritional composition and its naturalness than the other cluster. This study suggests that the exploitation of plant-based ingredients (textured soy, pea and wheat proteins) affect all sensory dimensions of plant-based canned tuna and highlights the importance of sensory optimisation in the development of plant-based alternatives to meet consumer preferences.

Customer personality analysis and clustering for targeted marketing

A customer’s personality has been stated to be a key determinant in his or her purchasing behavior. Therefore, in today's highly competitive market, understanding customer behavior and preferences is very important for businesses aiming to stay ahead. This research presents a customer personality analysis and clustering of consumers using machine learning into different consumer groups, this kind of clustering is key for targeted marketing strategies. The machine learning technique used in this work is the k-means machine learning clustering algorithm which divides a set of n observations into k clusters with the aim of designating each observation as a representative of a cluster. The model revealed insightful patterns and correlations between customer characteristics and their purchasing behavior. Through comprehensive data analysis and feature engineering, the model identifies key personality traits such as extroversion, openness, conscientiousness, agreeableness, and neuroticism, based on customer interactions, demographics, and psychographic data. The dataset that was used for this work was obtained from kaggle, it originated from different sources such as customer relationship management (CRM) systems, e-commerce platforms, social media platforms, surveys. The dataset comprises information on "people," "products," and "promotion," aiming to understand customer behavior, preferences, and responses to various marketing efforts. The output of this work provides businesses with actionable insights to tailor marketing campaigns and product offerings to individual customer preferences, thereby enhancing customer satisfaction and maximizing profitability.

Analysing Purchase Preference Towards Geographical Indications (GIs) Using Consumer Segmentation Approach

Consumers of local food products often face a dilemma regarding their purchase decisions due to the non-availability of information that is required to assess the quality of the product. To reduce this information asymmetry, the Geographical Indication Registry in India issues a Geographical Indication tag (GI tag) as a community right to the growers of local special products originating from a region, town or country. The GI tag symbolises uniqueness, curtails counterfeit products' spread, and reduces information asymmetry. This study has taken a select case of Udupi Mattu Gulla Brinjal, a GI horticulture produce grown by a community-based enterprise (CBE) in the Udupi District of South India. This research work aims to study and analyse consumer preference towards Udupi Mattu Gulla Brinjal (GI) using a consumer segmentation approach. The Principal Component Analysis technique has been used to identify statements with discriminatory power. Subsequently, the statements of research importance have been used to identify consumer segments using a two-step clustering approach. The study results have identified three important consumer clusters based on the analysis of consumer preference characteristics. Thereafter, marketing strategies have been proposed after analysing the profile of each segment. The study is undertaken as a response to an initiative from the Sustainable Development Goals (SDGs) Coordinating Centre, Government of India, to partner the development of agriculture in the local area of Udupi District. The objectives of the study are consistent with SDG goal 11 (sustainable communities) and SDG goal 12 (responsible consumption).

Investigating Electricity Usage Profile for Residential Consumers in India

Electricity has become one of the essential needs in modern society. The demand and necessity for electricity have increased with population, trade, and industry, which has resulted in increased stress on the grid. As the development of an electricity storage system is costly, utilities are working on customer segmentation to classify the consumers according to their usage patterns to understand their demand and further develop resources accordingly. In this work, the K-Means clustering algorithm has been applied to a two-year monthly consumption data set (January 2019 to December 2020) of 100 residential consumers from Kutheda village Hamirpur (Himachal Pradesh, India) to visualize the diverse consumption behaviour. It resulted in four different clusters of consumers. It also showed that there is a group having a large number of consumers whose consumption is low and consumption pattern is very less flexible in different seasons. Another group of consumers with high consumption also shows high flexibility in consumption patterns, but their number is less. Also, the winter season shows the highest consumption of electricity and the monsoon season shows the lowest consumption of electricity in this particular region. This analysis will certainly help the electricity provider to make production planning for a different group of consumers in a specific season based on electricity consumption patterns.

Live streaming economy and green consumer behavior of farming products: A psycholinguistic forecasting by using social computation

From the perspective of psycholinguistics, live-streaming programs not only facilitate the accessibility of farming products for online consumers but also exert a social influence on psychological behavior. This study delves into the green behavior of online consumers regarding farming products, specifically targeting those interested in participating in live-streaming programs. By leveraging demographic information and consumer preferences, this study sheds light on online consumers' green behavior through extensive surveys. Cluster analysis is also employed to distinguish the categories of online consumer behavior and identify the underlying motivations of consumers within social networks. The probability of consumer clusters engaging with various categories of online green consumption is further examined through a Bayesian model. Additionally, the externality effect of social networks on online consumers' green behavior based on the live streaming economy is further simulated by the SIR model. Drawing on insights from psycholinguistics within the domain of live-streaming big data, this research provides profound insights for global managers aiming to gain a deeper comprehension of online consumers' green behavior within live-streaming programs showcasing farming products. Moreover, it offers critical support for the digital marketing of these farming products in the era of digital transformation.

Sensory Attributes Driving Preference for Wild Rocket (Diplotaxis tenuifolia) Leaves Tasted as a Single Ingredient and as a Part of a Recipe.

Two cultivars of wild rocket (Diplotaxis tenuifolia), cv. Denver and Marte, were subjected to chemical determination of flavour-related constituents, sensory descriptive analysis, and measurement of liking by consumer test. Consumers evaluated rocket leaves both as a single ingredient and in a recipe formed by a roll of bresaola with also Grana Padano cheese. Sensory analyses showed that Marte was characterized by a more intense bitterness, hotness, and pungency, which corresponded to a higher total GSL content, mainly due to a higher level of dimeric 4-mercaptobutyl GSL. Five clusters of consumers were identified based on their liking scores. When tasting rocket leaves as a single ingredient, three clusters showed a higher liking for the milder cultivar, one cluster showed an opposite preference, while flavour attributes, such as bitterness and hotness, appeared as the main drivers of liking. Differences in liking were no longer found between the two cultivars when rocket leaves were evaluated in the recipe. Therefore, as rocket leaves are generally consumed as a part of a recipe with other ingredients instead of as a single ingredient, in the assessment of consumer preferences, it should not be neglected the influence of the way in which the product is consumed.

Encapsulated Opuntia spp. fruit powder as a natural colorant in biscuit filling cream

AbstractThe aim of the present study was to assess the utilization of prickly pear (PP) powder obtained by spray drying of juice (Opuntia spp., purple cultivar), in a sandwich biscuit filling cream, incorporating different concentrations from 0.5 to 10% (w/w). Cream viscosity profiles did not differ according to PP concentration Color saturation was achieved at 6% PP. In the final recipe, 2% of the PP powder was added in the cream, as was determined by sensory evaluation. Commercial sandwich biscuit with cream containing strawberry powder (SP) was also evaluated as reference. Semi trained assessors concluded that SP and PP filling creams had similar sweetness but different dominant color attributes: light pink and purple, approximating strawberry, and passion fruit respectively. When a cluster analysis was performed, two clusters of consumers were revealed with clear color choice, in favor of PP. A clustering of all parameters measured revealed that objective color parameters, were clustered together only with some cream sensorial attributes detected by semi trained assessors. Hue angle was the only color attribute that was highly correlated to consumer acceptance. PP cream and sandwich biscuit were highly acceptable indicating the potential of using PP as natural colorant. Graphical abstract

Analyzing Strawberry Preferences: Best-Worst Scaling Methodology and Purchase Styles.

This research has investigated Italian consumers' preferences for and purchasing behaviors of strawberries utilizing the Best-Worst Scaling methodology (BWS). This approach enables the key factors that influence strawberry purchasing decisions to be identified and different choice groups to be characterized. To achieve this goal, a survey was conducted on a sample of 496 respondents living in the metropolitan area of Milan (North Italy). The declared preferences of the individuals for 12 strawberry characteristics, divided into intrinsic, extrinsic, and credence attributes, were first measured. A Latent Class Analysis (LCA) was then performed to identify different clusters of consumers according to the individuals' preferences. Subsequently, the heterogeneity of the clusters was tested, using the Chi-square test, and sociodemographic characteristics and purchasing habits were considered. The results suggest that the most important attribute in the choice of strawberries was appearance, highlighting the importance of preserving it throughout the supply chain, followed by one of the increasingly important aspects of diets, which is health benefits. The attribute considered the least important was the brand. This study demonstrates, from a holistic point of view, that sociodemographic characteristics, food habits, and perceptions of different strawberry attributes influence consumers' preferences and behaviors. Practical implications suggest a new prospective for communication marketing strategies for producers, creating a better brand identity and highlighting in their marketing all of the aspects that consumers would like to know about the fruits they choose as quality certifications.

Federated Constrastive Learning and Visual Transformers for Personal Recommendation

This paper introduces a novel solution for personal recommendation in consumer electronic applications. It addresses, on the one hand, the data confidentiality during the training, by exploring federated learning and trusted authority mechanisms. On the other hand, it deals with data quantity, and quality by exploring both transformers and consumer clustering. The process starts by clustering the consumers into similar clusters using contrastive learning and k-means algorithm. The local model of each consumer is trained on the local data. The local models of the consumers with the clustering information are then sent to the server, where integrity verification is performed by a trusted authority. Instead of traditional federated learning solutions, two kinds of aggregation are performed. The first one is the aggregation of all models of the consumers to derive the global model. The second one is the aggregation of the models of each cluster to derive a local model of similar consumers. Both models are sent to the consumers, where each consumer decides which appropriate model might be used for personal recommendation. Robust experiments have been carried out to demonstrate the applicability of the method using MovieLens-1M, and Amazon-book. The results reveal the superiority of the proposed method compared to the baseline methods, where it reaches an average accuracy of 0.27, against the other methods that do not exceed 0.25.

Targeted information intervention among consumer clusters for electric vehicle penetration – A case study of Punjab, India

Low success rates of existing EV adoption policies in India highlight the need for targeted policies to boost EV adoption. The current study employs a single-arm information intervention to analyse the impact of information provision on electric vehicle (EV) adoption among consumer clusters in a developing country context. Using Gaussian Mixed Modelling clustering, the sample was grouped into four segments based on three psychological latent variables. Clusters with greater pro-environmental values had higher pre-intervention positive purchase intention, signifying that policies aimed at promoting EVs among environmentally conscious consumers have higher chances of success. The intervention showed significant desirable changes in every cluster. Results indicate that such campaigns would achieve higher success in consumer clusters with low eco-friendliness. Appropriate measures for each cluster are suggested. The characteristics of consumer clusters with higher pre-intervention purchase intention could serve as guidelines for businesses and governments while formulating new and updating their existing EV policies.

A predictive model approach to forecast consumers’ cluster membership in the green fast moving consumer goods sector

Predictive models are increasingly crucial in navigating heterogeneous markets. This study develops a predictive model approach to forecast consumer cluster membership in the green fast-moving consumer goods sector, focusing on bio-based products like adhesives and plasters. Through two online surveys in Germany, we identified key factors acting as drivers and barriers, demonstrating their effectiveness in distinguishing similar consumer segments across both product categories. Utilizing multinomial logistic regression, we crafted a prediction model that accurately forecasts cluster membership, providing novel insights into consumer behavior towards non-food bio-based products. This facilitates the development of targeted business and marketing strategies, optimizing resource allocation in market research activities. Our findings offer significant contributions to understanding the dynamics influencing consumer choices in the bio-based product market.

A machine learning-based framework for clustering residential electricity load profiles to enhance demand response programs

Load shapes derived from smart meter data are frequently employed to analyze daily energy consumption patterns, particularly in the context of applications like Demand Response (DR). Nevertheless, one of the most important challenges to this endeavor lies in identifying the most suitable consumer clusters with similar consumption behaviors. In this paper, we present a novel machine learning based framework in order to achieve optimal load profiling through a real case study, utilizing data from almost 5000 households in London. Four widely used clustering algorithms are applied specifically K-means, K-medoids, Hierarchical Agglomerative Clustering and Density-based Spatial Clustering. An empirical analysis as well as multiple evaluation metrics are leveraged to assess those algorithms. Following that, we redefine the problem as a probabilistic classification one, with the classifier emulating the behavior of a clustering algorithm, leveraging Explainable AI (xAI) to enhance the interpretability of our solution. According to the clustering algorithm analysis the optimal number of clusters for this case is seven. Despite that, our methodology shows that two of the clusters, almost 10% of the dataset, exhibit significant internal dissimilarity. As a result, these clusters have been excluded from consideration for DR programs. The scalability and versatility of our solution makes it an ideal choice for power utility companies aiming to segment their users for creating more targeted DR programs.

Segmenting Chinese wine consumers on the basis of wine knowledge and consumption behavior

Purpose This study aims to provide insights into wine consumers in Hong Kong and Mainland China, and the diversity of their behavior, by investigating their motivations, consumption and purchasing behavior and segmenting the sample based on wine knowledge and frequency of consumption to identify three distinct clusters that are then profiled. Design/methodology/approach Data was collected through an online survey of wine consumers of ethnic Chinese origin residing in Mainland China and Hong Kong, using two methods of recruitment (a convenience sample from wine-related databases, a panel survey undertaken by an international market research firm). The final sample comprised 477 respondents, about equally divided among Mainland Chinese and Hong Kong wine consumers. Analysis of the data using the Statistical Package for Social Sciences for Windows (SPSS) 29 included a series of descriptive analyses, followed by a two-step cluster analysis using an Euclidean distance method. Findings Wine knowledge and frequency of wine consumption were relatively higher within the sample as a whole than previous studies, but three distinct consumer segments are evident. There is evidence of a democratization of wine consumption, and a greater focus on wine consumption for enjoyment in relaxed and informal settings. rather than consumption driven by health and status, occurring primarily in commercial or business settings. The dominance of red wine in this market is also declining, and intrinsic cues – specifically, prior experience of the wine – are becoming important in wine purchase decisions. Originality/value This study uses a broad sample of wine consumers to identify trends in wine consumption patterns and motivations, and purchase decision-making behavior, of Mainland Chinese and Hong Kong wine consumers. The identification of three clusters of wine consumers offers both points of comparison with previous segmentation research globally and within China, whilst also identifying scope for further research.

Sustainable and healthy food consumption in Europe: an analysis of consumer purchase patterns, motivations and barriers towards foods from SFSCs

PurposeThe aim of this paper is to better understand European consumers' behaviour in relation to Short Food Supply Chains (SFSCs), so as to provide insights to support their development as part of a sustainable food system. Specifically, it aims to analyse consumer purchase patterns, motivations and perceived barriers and to identify patterns of behaviour amongst different consumer groups.Design/methodology/approachAn online consumer survey was conducted in 12 European countries (n = 2,419). Quantitative data analysis, including principal component analysis (PCA) and cluster analysis, was undertaken using SPSS.FindingsFour consumer clusters are named according to their behavioural stage in terms of SFSC engagement: Unaware Unengaged, Aware Unengaged, Motivationally Engaged and Executively Engaged. Unaware Unengaged and Aware Unengaged are in the non-engagement phase of behaviour. Motivationally Engaged are motivationally activated to engage in the behaviour but fail to do so consistently. Executively Engaged is the fully engaged cluster, being motivated to act and purchasing local food on a frequent basis. The results show an interesting interplay between motivations and barriers, i.e. higher scores for motivations and lower scores for barriers do not necessarily translate into higher purchase frequency.Originality/valueThe research gleans insights into the contextual factors that may inhibit SFSC purchases in different consumer segments. It offers practical implications for policymakers and others seeking to develop SFSCs as part of a sustainable food system.

The interplay of food-related lifestyle and eating behavior in Italian women.

Women play a crucial role in food shopping and preparation, and their food choices have significant implications for their health and that of their families. This study aims to provide a perspective on women's eating lifestyle, which has undergone significant changes. A factor analysis was conducted to assess the degree of involvement in food choices and the types of food items consumed among a sample of 399 Italian women. Through cluster analysis, four segments were identified: hedonic food consumers, sustainable- and balanced-diet consumers, food experimenters, and no food fondness consumers. The results reveal a correlation between the degree of food involvement and the type of food consumed. Furthermore, the food lifestyle of the sample is partially dependent on age. Individuals aged 25-28 years show more hedonic food consumption behavior, while the older age group (44-64 years) falls into the sustainable and balanced diet consumer cluster (the largest cluster) and the cluster of those who do not express definable food choices (no food fondness).

Bee pollen as a functional ingredient in bread: an exploratory study based on attitudes and expectations of Brazilian consumers

This study investigated consumers' perceptions of adding bee pollen to bread. An attitude questionnaire composed of 48 statements related to "general health," "light products," "natural products," "salty products," "food as a reward," "pleasure," and "food neophobia" was answered by the participants, who indicated their level of agreement with each statement according to a 5-point Likert scale, ranging from (1) "totally disagree" to (5) "totally agree." A check-all-that-apply (CATA) questionnaire was also employed to characterize 12 visual stimuli. The creation of stimuli was carried out using a factorial design, resulting in 12 images of bread. Three clusters of consumers were identified, each associating positive attributes with stimuli containing bee pollen, regardless of the health claim, while negative attributes were associated with stimuli without added pollen. The main positive drivers of liking were "I would buy," "attractive," "pleasant color," "healthy," "light," and "natural." On the other hand, the negative drivers of liking were "unattractive," "I don't like it," "I wouldn't buy," "hard," and "unpleasant color." This study provides valuable information for developing healthier bread using natural ingredients with bioactive compounds, such as bee pollen.

A Consumer Behavior Analysis Framework toward Improving Market Performance Indicators: Saudi’s Retail Sector as a Case Study

Studying customer behavior and anticipating future trends is a challenging task, as customer behavior is complex and constantly evolving. To effectively anticipate future trends, businesses need to analyze large amounts of data, use sophisticated analytical techniques, and stay up-to-date with the latest research and industry trends. In this paper, we propose a comprehensive framework to identify trends in consumer behavior using multiple layers of processing, including clustering, classification, and association rule learning. The aim is to help a major retailer in Saudi Arabia better understand customer behavior by utilizing the power of big data analysis. The proposed framework is presented as being generalized to gain insight into the generated big data and enable data-driven decision-making in other relevant domains. We developed this framework in collaboration with a large supermarket chain in Saudi Arabia, which provided us with over 1,000,000 sales transaction records belonging to around 30,000 of their loyal customers. In this study, we apply our proposed framework to those data as a case study and present our initial results of consumer clustering and association rules for each cluster. Moreover, we analyze our findings to figure out how we can further utilize intelligence to predict customer behavior in clustered groups.