Topical Collection "Utilizing Models for e-Business Decision-Making: From Data to Wisdom"

Editors

Prof. Dr. Mirjana Pejić-Bach
E-Mail Website
Collection Editor
Department of Informatics, Faculty of Economics and Business, University of Zagreb, 10020 Zagreb, Croatia
Interests: data science; artificial networks; simulation modeling; decision trees; cluster analysis; association rules; supervised learning; unsupervised learning; system dynamics
Special Issues, Collections and Topics in MDPI journals
Dr. María Teresa Ballestar
E-Mail Website
Collection Editor
Academic Department of Economy and Finance, ESIC Business and Marketing School, 28223 Pozuelo de Alarcón, Madrid, Spain
Interests: electronic commerce; big data; data analytics; machine learning; public policies; customer behavior; digitalization
Special Issues, Collections and Topics in MDPI journals

Topical Collection Information

Dear Colleagues,

Data has become omnipresent, as every aspect of personal and business activities is gradually being measured in numerous ways and turned into data, which is analyzed and used to form a value. In recent years, datafication has become a challenge, as processing all the data is nearly impossible due to its abundance, which is increasing exponentially year after year.

Nowadays, data is collected continuously both by humans and by machines, in both structured and non-structured manners. Relational databases, data warehouses, and data marts store the structured data that is often generated as the result of various interactions in e-businesses environments. Textual data is stored in the form of various business and other documents. Social media is also a rich source of textual data since our society has been transforming our communication platforms from analogic sources to digital, through online channels which are used both by persons and businesses for their communications. Moreover, human communication has been extended to the frequent online use of visual media, in the form of static pictures and video, which is also reflected in various e-business models. Soon, there will be more machines connected online than humans, and all of these machines, including mobile phones, the Internet-of-Things, and smart devices, among others, are collecting data.

What to do with all of these data? How to make the best use of it? Plenty of approaches have been adapted or invented to analyze these data, which are well known under various names such as data mining, knowledge discovery in databases, data science, data analytics, and others. All of them prescribe a certain process of data collection, data transformation, data analysis, model development and model deployment, combining machine learning, artificial intelligence and statistical analysis to understand it.

Because of the rich data sources and various methods that are nowadays easy to implement due to the availability of computed analytical tools, data analysis has become omnipresent. However, more data does not automatically lead to better decision making. On the contrary, plenty of data creates various problems that range from the issue of data selection to the misuse of data analysis that mixes correlation with causation. Besides, data analysis is often data-driven, and not decision-driven. In other words, decisions are often inspired by the available data, though data analysis should be driven by the decisions that are needed to improve performance. Finally, it is important to note that doing good analysis is not always a sign of improvement, as many organizations do not evolve to be real data-driven organizations and reject making decisions based on analysis, thus making them fail.

In the topic collection, we intend to focus on all of the stages in data analysis. First, we invite papers that discuss the availability, quality, and transformation of data used in e-business analysis. Second, the selection of existing, and invention of new data analysis approaches is a strong driver of improved e-business modes. Finally, the practical and theoretical implications of the data analysis in e-business are still not sufficiently explored. We invite you to participate in this topic collection with your case studies, original analysis, reviews, conceptual papers, and commentaries.

Prof. Dr. Mirjana Pejic-Bach
Dr. María Teresa Ballestar
Collection Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the collection website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Theoretical and Applied Electronic Commerce Research is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • decision-making
  • datafication
  • business performance
  • data analysis
  • data science
  • data mining
  • knowledge discovery in databases
  • big data
  • business intelligence
  • artificial intelligence
  • machine learning
  • security
  • privacy

Published Papers (3 papers)

2022

Article
Customer Response Model in Direct Marketing: Solving the Problem of Unbalanced Dataset with a Balanced Support Vector Machine
J. Theor. Appl. Electron. Commer. Res. 2022, 17(3), 1003-1018; https://doi.org/10.3390/jtaer17030051 - 21 Jul 2022
Viewed by 396
Abstract
Customer response models have gained popularity due to their ability to significantly improve the likelihood of targeting the customers most likely to buy a product or a service. These models are built using databases of previous customers’ buying decisions. However, a smaller number [...] Read more.
Customer response models have gained popularity due to their ability to significantly improve the likelihood of targeting the customers most likely to buy a product or a service. These models are built using databases of previous customers’ buying decisions. However, a smaller number of customers in these databases often bought the product or service than those who did not do so, resulting in unbalanced datasets. This problem is especially significant for online marketing campaigns when the class imbalance emerges due to many website sessions. Unbalanced datasets pose a specific challenge in data-mining modelling due to the inability of most of the algorithms to capture the characteristics of the classes that are unrepresented in the dataset. This paper proposes an approach based on a combination of random undersampling and Support Vector Machine (SVM) classification applied to the unbalanced dataset to create a Balanced SVM (B-SVM) data pre-processor resulting in a dataset that is analysed with several classifiers. The experiments indicate that using the B-SVM strategy combined with classification methods increases the base models’ predictive performance, indicating that the B-SVM approach efficiently pre-processes the data, correcting noise and class imbalance. Hence, companies may use the B-SVM approach to more efficiently select customers more likely to respond to a campaign. Full article
Show Figures

Figure 1

Article
B2C E-Commerce Customer Churn Prediction Based on K-Means and SVM
J. Theor. Appl. Electron. Commer. Res. 2022, 17(2), 458-475; https://doi.org/10.3390/jtaer17020024 - 06 Apr 2022
Cited by 3 | Viewed by 1359
Abstract
Customer churn prediction is very important for e-commerce enterprises to formulate effective customer retention measures and implement successful marketing strategies. According to the characteristics of longitudinal timelines and multidimensional data variables of B2C e-commerce customers’ shopping behaviors, this paper proposes a loss prediction [...] Read more.
Customer churn prediction is very important for e-commerce enterprises to formulate effective customer retention measures and implement successful marketing strategies. According to the characteristics of longitudinal timelines and multidimensional data variables of B2C e-commerce customers’ shopping behaviors, this paper proposes a loss prediction model based on the combination of k-means customer segmentation and support vector machine (SVM) prediction. The method divides customers into three categories and determines the core customer groups. The support vector machine and logistic regression were compared to predict customer churn. The results show that each prediction index after customer segmentation was significantly improved, which proves that k-means clustering segmentation is necessary. The accuracy of the SVM prediction was higher than that of the logistic regression prediction. These research results have significance for customer relationship management of B2C e-commerce enterprises. Full article
Show Figures

Figure 1

Article
Customer Churn in Retail E-Commerce Business: Spatial and Machine Learning Approach
J. Theor. Appl. Electron. Commer. Res. 2022, 17(1), 165-198; https://doi.org/10.3390/jtaer17010009 - 15 Jan 2022
Cited by 3 | Viewed by 2592
Abstract
This study is a comprehensive and modern approach to predict customer churn in the example of an e-commerce retail store operating in Brazil. Our approach consists of three stages in which we combine and use three different datasets: numerical data on orders, textual [...] Read more.
This study is a comprehensive and modern approach to predict customer churn in the example of an e-commerce retail store operating in Brazil. Our approach consists of three stages in which we combine and use three different datasets: numerical data on orders, textual after-purchase reviews and socio-geo-demographic data from the census. At the pre-processing stage, we find topics from text reviews using Latent Dirichlet Allocation, Dirichlet Multinomial Mixture and Gibbs sampling. In the spatial analysis, we apply DBSCAN to get rural/urban locations and analyse neighbourhoods of customers located with zip codes. At the modelling stage, we apply machine learning extreme gradient boosting and logistic regression. The quality of models is verified with area-under-curve and lift metrics. Explainable artificial intelligence represented with a permutation-based variable importance and a partial dependence profile help to discover the determinants of churn. We show that customers’ propensity to churn depends on: (i) payment value for the first order, number of items bought and shipping cost; (ii) categories of the products bought; (iii) demographic environment of the customer; and (iv) customer location. At the same time, customers’ propensity to churn is not influenced by: (i) population density in the customer’s area and division into rural and urban areas; (ii) quantitative review of the first purchase; and (iii) qualitative review summarised as a topic. Full article
Show Figures

Figure 1

Back to TopTop