Customer Behavior Patterns Research Articles

Marketing affordance of social media for product innovation: the role of organizational structures

PurposeDespite substantial research attention on the business use of social media in innovation literature, the action-based mechanisms through which social media affect firms' product innovation remain unclear. We address this gap by drawing on the affordance theory and examining the effects of social media applications on product innovations.Design/methodology/approachThe study was based on analyzing data collected through a questionnaire survey of Chinese firms. Partial least squares structural equation modeling was applied to test the hypotheses.FindingsThe results show that social media applications have a positive effect on marketing affordances (including customer behavior pattern discovery, real-time market response and marketing ambidexterity), in turn positively influencing product innovation performance. Organizational structures shape the actualization of the marketing affordance of social media; while organizational formalization positively moderates the relationships between social media application and marketing affordances, organizational centrality weakens these relationships.Practical implicationsManagers will benefit from understanding how social media can be applied to help their firms achieve product innovation. When manufacturing firms engage in social media for product innovation, they may find it worthwhile to focus on marketing actions such as customer behavior pattern discovery, real-time market response and marketing ambidexterity.Originality/valueThis study elucidates the action-based mechanism of marketing affordance by which social media usage improves product innovation performance. This study also highlights the design of organizational structure as an important approach to realizing the potential benefits of social media in product innovation.

Penerapan Algoritma Clustering untuk Segmentasi Pelanggan E-commerce berdasarkan Data Pembelian dan Aktivitas

In the current digital era, e-commerce has become one of the main pillars of global trade. With the ever-increasing amount of transaction and user activity data, e-commerce companies are faced with the challenge of understanding and managing diverse customer segments more effectively. This paper discusses the application of clustering algorithms for e-commerce customer segmentation based on purchasing data and user activity. The aim of this research is to identify homogeneous customer groups to support more targeted marketing strategies and increase customer retention. The problem faced is how to process big data originating from user transactions and activities on e-commerce platforms, as well as how to identify patterns that are useful for customer segmentation. The data used in this research includes purchase history, frequency of visits, length of time spent on the site, and interactions with certain products. The solution method applied in this research is the clustering algorithm, especially K-Means and DBSCAN. K-Means is used to group data into a predetermined number of clusters based on the Euclidean distance between data points. Meanwhile, DBSCAN is used to identify clusters with high density and separate data that is considered noise or outliers. Data preprocessing is carried out to clean and normalize the data before being applied to the clustering algorithm. Validation of clustering results is carried out using metrics such as Silhouette Score and Davies-Bouldin Index. The research results show that by applying the clustering algorithm, customers can be grouped into several segments that have similar characteristics. For example, we found groups of customers with high purchase frequency but low transaction value, as well as other groups with high transaction value but low purchase frequency. This information is very useful for companies to design more effective marketing strategies, such as special offers for customers with high transaction values ​​or loyalty programs for customers with high purchasing frequency. The conclusion of this research is that clustering algorithms can be a very effective tool in e-commerce customer segmentation, allowing companies to understand customer behavior patterns and develop more targeted and effective marketing strategies. Thus, implementing this method is expected to improve business performance and overall customer satisfaction.

Behavioural Economics in Marketing: Understanding consumer Decisison Making

Consumer decision-making, which is susceptible to emotional and social effects in addition to cognitive flaws, is the focus of behavioural economics, which integrates findings from economics and psychology. Examining the impact of behavioural economic principles such as limited rationality, prospect theory, and heuristics on customer behaviour, this abstract outlines important ideas and new developments in the field of applied behavioural economics to marketing. To determine which techniques are most successful in influencing customer decisions, we examine framing effects, anchoring, and nudging. Furthermore, the significance of data analytics and digital marketing in comprehending and capitalising on customer behaviour patterns is addressed. Businesses may boost engagement, happiness, and revenue by integrating behavioural data into marketing campaigns. In order to better understand consumer decision-making and its practical implications for marketers, the article also proposes topics for further research, such as the influence of new technology and ethical issues in consumer manipulation.

The Impact of Covid-19 on the Change of Customer Buying Behaviour

Background: The retail sector is rapidly developing over the past years. Retailers are investing more efforts and resources to provide a seamless experience through multiple channels. These developments led to significant changes in customer behaviour. Customers buying activities and way of selecting the products and retailers faced different changes and developments. The online retailing sector is entitled to continuous development. The latest development was due to the Covid-19 global pandemic that came without any previous notice. The customer behaviour starts adopting the digital online channels in most of their needs and wants. The appearance of new customer behaviour patterns due to Covid-19 lead to the emergence of new customer behaviour. Purpose: This study is of an exploratory and constructive nature. It is concerned with deepening the knowledge about the change in customer buying behaviour brought by Covid-19 on the retailing sector. The aim of the study is to identify and test new behavioural patterns that would influence the Swedish millennials’ in selecting between online and offline stores for shopping and buying fashion products. Method: An abductive approach was followed in this paper. Mixed methods of both qualitative and quantitative were used to fulfil the purpose of this exploratory research. The research followed a sequential exploratory design of two data collection phases. The ii empirical data was conducted from focus groups sessions with a total number of interviewee, and relevant responses from a web-based survey. Conclusion: The study has revealed two significant findings and contributed to propose a conceptual model. The fruitful results of this study are: (1) there is a vast customers’ migration towards online stores. (2) there are new behavioural patterns related to Covid 19 that are influencing the customer buying behaviour. (3) A proposed conceptual model which is concerned with the factors influencing the customer buying behaviour in selecting between online and offline fashion stores.

IP PBX를 이용한 소형 CRM 설계 및 구현

Today, many companies are using CRM as a means to secure sales opportunities, improve sales pipelines, and increase customer satisfaction. CRM like this improves the quality of corporate management by understanding customer behavior patterns and utilizes the process of change in the organization's work procedures and technology for marketing, sales, and customer service. In this study, we designed and implemented a small CRM using IP PBX to enable small and medium-sized businesses to introduce CRM without economic burden and measured its performance. As a result, we found a small customer management system (SOHO CRM) has proven its performance.

Customer Segmentation in User Behavior Analysis: A Comparative Study of Clustering Algorithms

A thorough understanding of customer behavior patterns is still essential for corporate success in today's digital environment. To segment clients in-depth, this study used three distinct clustering algorithms: k-means, hierarchical clustering, and dbscan. By carefully examining the age, yearly income, and consumption score This study goes beyond conventional views and creates a comprehensive and distinct perspective when disclosing numerous consumer attributes using data derived from the mall consumer Segmentation Data set. It offers insightful information that can be used to adjust a company's marketing plan. The strategic application of customer insights is redefined in this study, empowering stakeholders to decide wisely and improve market performance. The road to greater competitiveness and relevance in a developing market segment is mapped using real-world data and powerful clustering techniques. Based on research of this dataset, it was discovered that Dbscan performed best on this dataset with unequal density. It highlights the usefulness of these algorithms in today's complicated business world.

Studying Customer Behavior in the Libyan Telecoms Market using Data Visualization

In general, the main benefit of data visualization is that it provides a better understanding of complex data and enables faster decision-making.This study on call detail records (CDRs) and SMS activity data visualization was conducted to fully understand the customer behavior patterns and culture in the Libyan telecom market.A big telecom data (261 GB) was collected for CDRs between 28 March and 22 April 2020. This includes 19 working days, three Fridays and four Saturdays. The data visualization results show that the weekend SMS and call activity pattern shows a completely different behavior compared to other days of the week. Call behavior between 12:00 and 7:00 is generally almost the same. The peak times for calls on weekdays are between 11:30 and 13:00 and for SMS between 19:30 and 22:00. Furthermore, the analysis of SMS activities does not reflect customer behavior, but much of the SMS activity is the result of electronic payment services during shopping. However, Libyan culture is more about making phone calls than sending SMS messages. since the number of calls at dawn is minimal, the number of SMS increased slightly at this time. In order to retain customers, decision makers should consider these results and develop appropriate plans and strategies. However, in order to reduce call congestion and increase efficiency, decision makers should set appropriate pricing during peak or pre-peak and post-peak hours to convert many customers before or after peak hours.Also, they should somehow encourage customers to use SMS instead of calls.

What can transactional data reveal about the prevalence of menstrual pain in England?

Introduction & BackgroundIt has been reported that up to 91% of those who menstruate experience associated pain. Despite its ubiquity, the prevalence of menstrual pain has been under researched due to stigma, disregard from medical professionals and a lack of data. It has also been reported that different demographics experience menstrual pain differently yet the impact of socio-demographic factors on menstrual pain remains to be explored on a national scale due to data scarcity.
 Objectives & ApproachIn this study, we propose one way to overcome this data barrier, using a novel measure of menstrual pain extracted from supermarket shopping data. We use these national datasets to identify individual customer behaviour patterns. Specifically, we use transactions involving both a pain and menstrual item as a proxy measure for menstrual pain. We investigate national menstrual pain sales and whether there are significant differences between deprived and less deprived areas of England.
 Relevance to Digital FootprintsThis paper brings together data from multiple sources, to provide a population level analysis of the prevalence of menstrual pain England. We use transactional data from a pharmaceutical retailer to develop a novel proxy measure for menstrual pain. We use various machine learning algorithms to explore the relationship between transactional data and various data sources pertaining to social deprivation.
 ResultsOur findings indicate that there is a high prevalence of menstrual pain with at least 26.7% of customers who purchase menstrual items also purchasing pain relief simultaneously. These customers are nearly four times more likely to purchase pain relief with a menstrual item than they are without. In addition, our results indicate a significant geographical disparity between menstrual pain transactions. We examine the relationship between a variety of deprivation factors and regional menstrual pain transactions and find average regional income has the highest predictive impact on menstrual pain sales. Contrary to what would expected from previous research, customers from the region with the lowest regional income were a third less likely (32%) to make a menstrual pain transaction than those from the highest income region.
 Conclusions & ImplicationsThis work motivates further research into the national prevalence of menstrual pain to understand why this regional disparity exists and whether it is a consequence of "period poverty". A better understanding of the sociodemographic factors associated with menstrual pain will help healthcare professionals stratify patients by risk, and could inform strategies to predict and prevent menstrual pain and its adverse impacts.

Embracing Innovative Approaches in Data Science: Investigating Contemporary Trends in Data Collection, Analysis, and Visualization Methods

Today businesses are becoming more productive and their return on investment (ROI) is increasing with the development of new technologies like data science, artificial intelligence and data analytics. In today's trend organizations are dealing with big data and these data can drive the whole organization in many ways. The process of doing data analysis and extracting meaningful insight is known as data science. Most business organizations are taking data driven models to ease their work and for making intelligent business decisions. The life cycle of a data science involves so many steps like understanding the business, data collection, analysis and data modelling etc., and to achieve these steps various new technologies and methods are available. Firstly, the process of data collection has been significantly augmented by artificial intelligence, allowing businesses to gather vast amounts of structured and unstructured data efficiently. This rich pool of data serves as the foundation upon which strategic decisions are made. By leveraging advanced data collection methods, organizations gain invaluable insights into market trends, customer behaviour, and operational patterns, empowering them to make informed, data-driven decisions. Secondly, data analysis, a core element of data science, plays a pivotal role in extracting meaningful insights from the collected data. Through sophisticated analytical techniques, businesses can uncover hidden patterns, correlations, and trends within the data. This deep understanding of the data not only facilitates efficient problem-solving but also enables the identification of opportunities for innovation and growth. Informed by data analysis, businesses can optimize processes, identify cost-saving measures, and enhance overall operational efficiency. Lastly, data visualization techniques such as real-time visualization and augmented analytics empower organizations to transform complex data sets into easily understandable visual representations. Real-time visualization provides businesses with up-to-the-minute insights, enabling them to respond promptly to market changes and emerging trends. Augmented analytics, on the other hand, leverages machine learning algorithms to automate data analysis and present actionable insights in an intuitive manner, further accelerating the decision-making process. In this study the recent trends in data science like artificial intelligence for data collection, augmented analytics and predictive analysis for data analysis and data democratization & real time visualization techniques for data visualization are discussed in detail. This study also presents the tools, key challenges and applications of these recent methods in brief.

Big data affordances and market performance: The moderating role of servitization

Many service-oriented manufacturers (SOMers) aggressively engage with big data to stay ahead of the competition, but not all have achieved the anticipated market returns. To unravel this puzzle, we draw on affordance theory and the resource-based view to investigate the combined effects of two big data affordances (i.e., customer behavior pattern spotting and real-time market responsiveness) and two service categorizations (i.e., basic and advanced services) on market performance. Analyzing data from 223 SOMers in China, we reveal that while customer behavior pattern spotting is positively associated with market performance, real-time market responsiveness has a U-shaped association with market performance. More interestingly, basic services enhance the positive association between customer behavior pattern spotting and market performance, whereas SOMers with a high (vs. low) level of advanced services better use real-time market responsiveness to enhance market performance. We contribute to the big data literature by offering a new theoretical explanation for the inconsistent big data–performance relationship. Our findings also have managerial implications by guiding SOMers on how to reorient their big data usage.

Big Data Analysis for Strategic Decision Making in Business Information Systems

The use of big data in the context of strategic decision making in business information systems has become the main focus of research in the current digital era. This research aims to analyze the role of big data in facilitating effective strategic decision making in a rapidly changing business environment. The research methods used include a thorough literature survey and comprehensive analysis of case studies of several leading companies that have adopted big data technology in their business information systems. The research results show that big data has a crucial role in improving strategic decision-making capabilities by providing fast access and in-depth analysis of complex and varied data. This allows organizations to identify market trends, customer behavior patterns and new business opportunities in a more timely and accurate manner. In conclusion, the integration of big data in business information systems is an inevitable strategy for organizations that want to remain competitive in this digital era.

Market-Based Analysis: Apriori approach to analyze purchase patterns

In this paper, a data mining approach has been developed to analyze customer behavioral patterns and to get a further idea of the scale of the products purchased. Using the approach we found the best and least performing products, the average number of the products that the customer is interested in buying, And using the apriori algorithm we can generate the frequent items which can be bought together which will help us in suggesting products for the customer to buy. Each pattern is supported by the support and confidence generated using the apriori algorithm.

The Influence of Digital Technology Adoption by Small and Medium Enterprises and Online Consumer Behavior on the Success of E-commerce Platforms in Bandung City

This study looks into the complex relationships that exist between the use of digital technology by Small and Medium Enterprises (SMEs) in Bandung City, online consumer behavior, and the performance of e-commerce platforms. Through the use of structured surveys and a quantitative approach, information about digital technology integration, online customer behavior patterns, and markers of e-commerce success was gathered from 121 SMEs. The results show that consumer behavior dynamics are diverse, there is a moderate level of acceptance of digital technology, and both characteristics have a considerable beneficial impact on the performance of e-commerce. The key component that emerges is trust, underscoring the significance of building customer confidence in the digital economy. The study adds to our knowledge of the complex interactions that occur between customer engagement and technology adoption, providing SMEs navigating the digital landscape with useful insights.

Review: Application of Machine Learning to Investment Portfolios

This review focuses on the use of three machine learning methods in portfolios using reinforcement learning, recurrent neural networks and random forests. Machine learning algorithms create a model from training or sample data, train themselves by continuously learning from the data, and then adjust their actions based on the insights found to gain the ability to make better predictions and decisions. As today's big data continues to expand and grow, the market demand for machine learning is expected to increase significantly. This is because companies can use it to understand trends in customer behavior and business operation patterns to support the development of new products. Thus, the use of machine learning methods to build an optimal portfolio can help investors minimize risk and maximize returns. Asset management firms enable investors to invest in the best investment opportunities by developing investment plans based on specific client requirements and return expectations.

Factors Affecting Customer Satisfaction in Purchasing Car

Globalization of the markets coupled with economic downturn had changes the pattern of customer behavior and consumption patterns. The customer buying behavior is a complex topic as many internal and external factors have impact on the level of satisfaction of the customer. From the past decade, previous researchers had attempted to understand how customers’ needs their responses and feedbacks. In 2017, the number of Honda Civic 2017 Model car owners has reached 109,511 units in Malaysia and the Malaysia’s southern region occupied 34% of Honda’s total sales compared to others car model (Honda, 2018; Lye, 2018). Seeing that the demand for this model is high, it is crucial to study the car owners’ satisfaction align with the automobile and organizational standards, especially through effective customer satisfaction measurement model. The objective of the research is to study the relevant factors that affecting customers’ satisfaction in purchasing Honda Civic car (model 2017). This research studied the factors (price, customers’ services, brand image and quality) in influencing the customers’ satisfaction. The results show that customers’ services and quality have significant relationship towards customers’ satisfaction. The findings would be useful for academicians to further study on factors related with this area or to find out whether similar to apply this to other industry as well.

A continuum perspective of customer choice rules for competitive facility location problems

Customer patronage behavior plays a critical role in estimating market share in the context of locating competitive facilities. Three common rules used to describe customer patronage behaviors are: the binary rule, the proportional rule, and the partially binary rule. Recently, we propose another customer choice rule, the partially proportional rule, to describe the behavior of customers when choosing a chain of facilities that offer exclusive services. Although these four rules describe very different customer patronage behaviors, this paper finds that they actually correspond to optimal solutions for four special cases of a class of optimization problems. For the general cases of this class of optimization problems, we also give the corresponding optimal solutions. This work provides a continuum perspective for understanding customer choice rules, while providing possible theoretical guidance for studying unexplored customer behavior patterns.

An effective strategy for churn prediction and customer profiling

Customer churn prediction and profiling are two major economic concerns for many companies. Different learning approaches have been proposed, however the a priori choice of the most suitable model to perform both tasks remains non-trivial as it is highly dependent on the intrinsic characteristics of the churn data. Our study compares eight supervised machine learning methods combined with seven sampling approaches on thirteen public churn data sets. Our evaluations, reported in terms of area under the curve (AUC), explore the influence of rebalancing strategies and data properties on the performance of learning methods. We rely on the Nemenyi test and Correspondence Analysis as means of visualizing the association between models, rebalancing and data. This work identifies the most appropriate methods in an attrition context and proposes an effective pipeline based on an ensemble approach and deep autoencoders segmentation. Our strategy can enlighten marketing or human resources services on the behavioral patterns of customers and their attrition probability. The described experiments are fully reproducible and our proposal can be successfully applied to a wide range of churn-like datasets.

Predicting Order Cancellations for E-Commerce Domain: A Proposed Model Based on Retailing Experience

E-Commerce technologies enable contact between businesses and their suppliers for the aim of exchanging information such as purchase orders, invoices, and payments thank to the rapid development in information technologies. E-Commerce has become a particularly important concept and has revolutionized the retail space. Understanding customer behavior patterns is key to gaining competitive advantage and achieving business goals. Predicting the probability of order cancellations has become a very urgent need as it causes loss of revenue for the retailer. When dealing with day-to-day operations such as order processing, tracking and order cancellations, finding enough time to grow the business is difficult. Cancellations are an important aspect of retail industry revenue management. In fact, little is known about the factors that cause customers to cancel or how to avoid them. The aim of this study is to propose a model that predicts the tendency to cancel an order and the parameters that affect the cancellation of the order. This solution can identify key factors that cause orders to be canceled by analyzing historical transaction data. A custom modeling application has been created that helps automate the process of tracking order cancellations in real time and predict the probability of an order being cancelled. For this purpose, machine learning techniques (ML) such as Artificial Neural Network, Support Vector Machine, Linear and Logistic Regression, XGBoost, Random Forest are applied to provide a tool for predicting order cancellations. The Random Forest algorithm achieves the best performance with 86% accuracy and 88% F1-Score compared to the other algorithm. This work will help firms manage their inventories well and strengthen their actions regarding customer behavior.

Intelligent e-commerce Framework for Consumer Behavior Analysis Using Big Data Analytics

Internet shopping gradually surpassed conventional retail shopping; it has been taken up internationally by many customers. However, e-commerce in emerging markets remains at an early stage, and thus, the factors that lead to its acceptance must be discovered. The main objective is to combine the expected theory of behavior, rational activity, and the technology model’s acceptability using big data analysis (BDA) to evaluate the main predictors of internet buying plans. The growth in online shopping raises rivalry in the area of e-commerce between various organizations. The existing enterprise planning methods became obsolete with the advent of technology. Enterprises must adapt market intelligence through big data analysis to improve the business process in e-commerce. In the e-commerce market world, the influence of BDA plays a crucial part. The proposed model addresses different methodologies and methods for data analysis e-commerce. Users are proposing several new ways of enhancing market intelligence using BDA in the e-commerce sector. The findings show the relevance of the reasonable action theory and technology acceptance model, for explaining online shopping intentions, confirmation that e-commerce behavior often determines intentional purchases online, which in turn can be explained in terms of perceived utility, how easy it is to use, and how subjective the online shopping rule is perceived. This perspective of online shopping intention has contributed to a paradigm change in the e-commerce industry, as data is no longer viewed as the outcome of their market practices but as their greatest asset: a vital insight into the needs of consumers, a prediction of customer behavior patterns, the democracy of publicity to match consumer preferences, and success assessment to determine efficiency in meeting customers. The experimental outcomes of suggested BDA enhance the order delivery ratio (95.2%), customer behavior analysis ratio (92.6%), product quality ratio (97.6%), customer satisfaction ratio (95.9%), and demand prediction ratio (96.3%).

Mining Willing-to-Pay Behavior Patterns from Payment Datasets

The customer base is the most valuable resource to E-commerce companies. A comprehensive understanding of customers’ preferences and behavior is crucial to developing good marketing strategies, in order to achieve optimal customer lifetime values (CLVs). For example, by exploring customer behavior patterns, given a marketing plan with a limited budget, a set of potential customers is able to be identified to maximize profit. In other words, personalized campaigns at the right time and in the right place can be treated as the last stage of consumption. Moreover, effective future purchase estimation and recommendation help guide the customer to the up-selling stage. The proposed willing-to-pay prediction model (W2P) exploits the transaction data to predict customer payment behavior based on a probabilistic graphical model, which provides semantic explanation of the estimated results and deals with the sparsity of payment data from each customer. Existing work in this domain ranks the customers by their probabilities of purchase in different conditions. However, the customer with the highest purchase probability does not necessarily spend the most. Therefore, we propose a CLV maximization algorithm based on the prediction results. In addition, we improve the model by behavioral segmentation wherein we group the customers by payment behaviors to reduce the size of the offline models and enhance the accuracy for low-frequency customers. The experiment results show that our model outperforms the state-of-the-art methods in purchase behavior prediction.