Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

Exploring the impact of country-of-origin image and purchase intention in cross-border e-commerce

Product country-of-origin (COO) is now playing a central role in consumers’ purchase behavior. Previous studies have investigated several factors that impact COO. However, little attention has been paid to the impact of COO on consumers’ product evaluation on Chinese products, especially in the cross-border e-commerce context. Using a multi-methods design, this study first unearthed the antecedents of COO image towards Chinese products from the qualitative data in Study 1 by drawing on the legitimacy theory and then develops a contextual model of consumers’ product evaluation and purchase intention, integrating the role of a product with a different level of involvement. Using quantitative survey data from 252 foreign consumers, the study tests the research model in Study 2. The findings provide empirical evidence to support the model and highlight the importance of COO cues on foreign consumers’ purchase intention towards Chinese products. The results also enhance our understanding of consumers’ purchase decision in cross-border e-commerce.

Exploring the Impact of Country-of-Origin Image and Purchase Intention in Cross-Border E-Commerce

Product country-of-origin (COO) is now playing a central role in consumers’ purchase behavior. Previous studies have investigated several factors that impact COO. However, little attention has been paid to the impact of COO on consumers’ product evaluation on Chinese products, especially in the cross-border e-commerce context. Using a multi-methods design, this study first unearthed the antecedents of COO image towards Chinese products from the qualitative data in Study 1 by drawing on the legitimacy theory and then develops a contextual model of consumers’ product evaluation and purchase intention, integrating the role of a product with a different level of involvement. Using quantitative survey data from 252 foreign consumers, the study tests the research model in Study 2. The findings provide empirical evidence to support the model and highlight the importance of COO cues on foreign consumers’ purchase intention towards Chinese products. The results also enhance our understanding of consumers’ purchase decision in cross-border e-commerce.

How COVID-19 Has Influenced the Purchase Patterns of Young Adults in Developed and Developing Economies: Factor Analysis of Shopping Behavior Roots

The paper presents survey results from shopping behavior transformation in developed and developing countries due to the COVID-19 pandemic outbreak in spring 2020. The survey includes the polling process that covered 515 and 117 young adults, respectively, for two economies and factor analysis to determine the latent intentions of purchase behavior. Shopping patterns were studied for food, medicine, goods of first priority, electronics, clothing, and shoes. According to factor analysis results, we determined nine factors that reveal some similarities in shopping behavior as pro-safe purchases and belt-tightening patterns for both economies. Along with that, we revealed that people from developed countries perceived the greater danger and fear due to the COVID-19 crisis than young adults from developing economy. Based on polling results, the post–COVID-19 shopping channel choice behavior was evaluated for developed and developing economies.

Analysis of Factors Affecting Consumer Purchase Behavior: Study in Muslim communities who shop online through the Shopee Application

This study aims to determine and analyze what factors influence consumer buying behavior in the era of citizen 4.0 and the most dominant influences on consumer buying behavior in citizen 4.0. This research uses descriptive and explanatory survey methods. Sampling was carried out using the Accidental Sampling sample technique. The data analysis technique used is factor analysis. The findings of this study are factors such as availability and price factors, promotion factors, comfort factors, varieties and comparison factors, after-sales service factors, and connectivity factors that influence consumer purchasing behavior in the era of citizen 4.0. Besides that, variety and comparison factors are the most dominant factors affecting consumer buying behavior in the age of citizen 4.0, followed by availability and price factors, comfort factors, promotion factors, after-sales service factors, and connectivity factors.

Food Purchase Behavior during The First Wave of COVID-19: The Case of Hungary

Coronavirus disease (SARSCoV-2) appeared in 2019 was confirmed as pandemic by the WHO on 11 March 2020. Stay-at-home order had an impact on consumers’ food purchase habits, as people around the world were able to leave their homes solely in extremely severe or urgent cases. In our research, we delve into the impact of COVID-19 pandemic on consumers’ food purchase habits. The research involved 3000 consumers during the first wave of coronavirus. The sample represents the Hungarian population by gender and age. To achieve the research goals, we applied multivariate statistical tools. The findings suggest that the pandemic could not change consumer attitude significantly, but the order of factors influencing purchases changed. Consumer motivation factors were organized into four well-distinguished factors: Healthy, domestic, and environmentally friendly choice; Usual taste and quality; Reasonable price; Shelf life. Due to the lack of outstanding data during segmentation, we developed four segments by hierarchical cluster analysis: Health- and environment-conscious women; Price sensitive young people; Taste-oriented men; Quality-oriented intellectuals. The results confirm that food manufacturers and traders need to be prepared for further restrictions in the future.

Consumers’ Purchase Behavior Preference in E-Commerce Platform Based on Data Mining Algorithm

E-commerce platform can recommend products to users by analyzing consumers’ purchase behavior preference. In the clustering process, the existing methods of purchasing behavior preference analysis are easy to fall into the local optimal problem, which makes the results of preference analysis inaccurate. Therefore, this paper proposes a method of consumer purchasing behavior preference analysis on e-commerce platform based on data mining algorithm. Create e-commerce platform user portrait template with consumer data records, select attribute variables and set value range. This paper uses data mining algorithm to extract the purchase behavior characteristics of user portrait template, takes the characteristics as the clustering analysis object, designs the clustering algorithm of consumer purchase behavior, and grasps the common points of group behavior. On this basis, the model of consumer purchase behavior preference is established to predict and evaluate the behavior preference. The experimental results show that the accuracy rate of this method is 91.74%, the recall rate is 88.67%, and the F1 value is 90.17%, which are higher than the existing methods, and can provide consumers with more satisfactory product information push.

ReRec: A Divide-and-Conquer Approach to Recommendation Based on Repeat Purchase Behaviors of Users in Community E-Commerce

Existing studies have made a great endeavor in predicting users’ potential interests in items by modeling user preferences and item characteristics. As an important indicator of users’ satisfaction and loyalty, repeat purchase behavior is a promising perspective to extract insightful information for community e-commerce. However, the repeated purchase behaviors of users have not yet been thoroughly studied. To fill in this research gap from the perspective of repeated purchase behavior and improve the process of generation of candidate recommended items this research proposed a novel approach called ReRec (Repeat purchase Recommender) for real-life applications. Specifically, the proposed ReRec approach comprises two components: the first is to model the repeat purchase behaviors of different types of users and the second is to recommend items to users based on their repeat purchase behaviors of different types. The extensive experiments are conducted on a real dataset collected from a community e-commerce platform, and the performance of our model has improved at least about 13.6% compared with the state-of-the-art techniques in recommending online items (measured by F-measure). Specifically, for active users, with w = 1 and N(UA)∈[5,25], the results of ReRec show a significant improvement (at least 50%) in recommendation. With α and σ as 0.75 and 0.2284, respectively, the proposed ReRec for unactive users is also superior to (at least 13.6%) the evaluation indicators of traditional Item CF when N(UB)∈[6, 25]. To the best of our knowledge, this paper is the first to study recommendations in community e-commerce.

“Why Do We Buy Green Products?” An Extended Theory of the Planned Behavior Model for Green Product Purchase Behavior

Many consumers are concerned about environmental issues and have expressed interest in purchasing green products. However, actual sales of green products are still not as high as expected. Therefore, marketers of green products may need to investigate the factors driving green purchase behaviors. In this study, we proposed an extended theory of planned behavior (TPB) model that links consumers’ environmental concerns, perceived image of the company, consumer innovativeness, and environmental knowledge with green product purchase behavior. We applied a quantitative approach to collect the data via online questionnaires through Amazon MTurk. With 974 useable samples, the data were analyzed with structural equation modeling (SEM) using Smart PLS. The results showed that green purchase intention positively and significantly affects green purchase behavior. Moreover, the multigroup analysis revealed that the direct influence of green purchase intention on green purchase behavior is higher in developing countries than in developed countries. Regarding the direct effect on green purchase intention, attitude toward green products, perceived consumer effectiveness (PCE), environmental concern, and company’s perceived green image are significant antecedents of the intention to purchase, with attitude toward green products being the most robust antecedent among the three. However, subjective norms do not act as a direct antecedent of purchase intention. For the indirect effect on green purchase intention, four main antecedents (attitude toward green products, subjective norms, PCE, and environmental concerns) indirectly impact purchase intention via the mediating role of the perceived green image of the company. This study contributes to existing literatures via extending the TPB model. Regarding attitude-intention-behavior model, we found that environmental concern complements the model as an antecedent of green purchase intention. Moreover, a company’s perceived green image mediates the relationship between four antecedents and green purchase intention. Therefore, marketers of green products may also enhance future purchases by promoting the green image of the company. Particularly, we found that environmental knowledge positively moderates the relationship between environmental concern and a company’s perceived green image. We added on the empirical evidence that PCE plays a crucial role in stimulating green purchases as its direct positive influence on green purchase behavior is larger than that of green purchase intention. Moreover, consumer innovativeness positively moderates the relationship between PCE and green purchase intention.

Factors Influencing Consumer Brand Choice Service Tailoring Shop in Thailand, Focusing on Ermenegildo Zegna, Brioni and Local Brand

The study compares foreign and local brands, focusing on Ermenegildo Zegna, Brioni, and local brands, in order to uncover the elements that impact customers' brand choice decisions in Thailand. The study looked at the elements that influence a customer's decision to buy a custom-made suit, in order to figure out what the most important component is. Understanding how Marketing Mixed affects customer happiness and purchase decisions is especially important. The second goal is to investigate how brand equity affects sales, with a particular focus on customer brand preferences and market expansion. The author chose the survey approach for this study, which is a quantitative research. Data was collected at random online through 346 legitimate questionnaires, and data was analyzed using cross tabulation and multinomial logistic regression. The study's findings show that all of the investigated factors, including product, price, location, promotion, brand equity, and customer purchase behavior determinants, have a positive impact on tailoring's customer brand choice decision in Thailand, with some specifications of each factor being found to be significant. Finally, when comparing these three brands, certain results are noteworthy.