Decision Support Systems

In most practical prediction problems, such as regression and classification, the different types of prediction errors are not equally costly in the decision-making process. Although there exist numerous real-world cost-sensitive regression ...

• A One-Step Boosting algorithm is proposed for post hoc cost-sensitivity in regression
• The boosting step uses a linear function as a secondary learner for cost-sensitivity
• The method consistently yields a significant reduction in ...

Motivated by prior inconclusive findings on the effectiveness of open innovation initiatives in generating business value and the complexity of open innovation, this study draws on the IT-enabled organizational capabilities perspective to propose ...

• IT impact on open innovation initiatives and open innovation performance.
• Large scale sample of >1100 large firms in Spain.
• Firms' IT resources enable the execution of open innovation initiatives.
• The business value of IT by ...

This paper explores the optimal regulation strategies of the government and platforms to provide guidelines for how to maintain the order of user-generated content platforms and prevent adverse social events. The platform decides the intensity of ...

• Two-tier regulation on user-generated content among platforms and the government is explored.
• Government regulation is classified into direct regulation and indirect regulation.
• Platforms with the same basic intrinsic values in the ...

Online reviews affect consumer purchase decisions and become prevalent in different sectors. Platforms elicit useful reviews by allowing consumers to vote for helpfulness. The link between review features and review helpfulness hence has been a ...

• Show significant contribution of review emotions using R-squared decomposition.
• The nonlinear effect of review arousal moderated by review valence on review helpfulness.
• Articulate latent mechanisms leading to the moderated ...

The facilitation of information technology has led to the rapid development of online-to-offline commerce, and this mode is attracting increasing businesses to enter the market. Its unique on-demand features affect consumers' shopping behaviors. ...

• The new entrant negatively affects consumers' ordering and spending from existing providers.
• The impact is altered by consumers' engagement level and distance from the new entrant.
• Platform's technological innovation and sellers' ...

Fraud detection is to identify, monitor, and prevent potentially fraudulent activities from complex data. The recent development and success in AI, especially machine learning, provides a new data-driven way to deal with fraud. From a ...

Display Omitted

• We propose deep boosting decision tree (DBDT), an effective fraud detection method.
• DBDT combines the advantages of both conventional methods and deep learning.
• DBDT embeds neural networks into boosting to improve the ...

A man-made machine-reading comprehension (MRC) dataset is necessary to train the answer extraction part of existing Question Answering (QA) systems. However, a high-quality and well-structured dataset with question-paragraph-answer pairs is not ...

• A resource-efficient approach for designing a QA system utilizing a large-scale CQA dataset
• A novel QA system comprising a classifier-retriever-summarizer structure
• System establishment with 3,081,834 QA pairs covering 140 topics ...

Understanding what information is important for consumers when making a purchase-related decision has been a key question for researchers and practitioners ever since the advent of empirical research in commerce. Nevertheless, our knowledge of ...

• Explores social commerce user patterns of information utilization in purchase-related decisions.
• Examines the dynamic characteristics of consumer information use interacting with information presented on social commerce.
• Identifies ...

Organizational innovation communities for new product development (NPD) have become an integral part of organizations' strategy to find innovative ideas for new products with the help of their consumers. The success of these communities largely ...

• Research highlights the difference between idea crowdsourcing platforms for improvement ideas vs new product ideas.
• Research finds idea quality has an inverted U-shape relationship with past performance and the number of submitted ...

E-commerce retailers (e-tailers) are increasingly competing in order fulfillment to win over customers. Delivery guarantee emerges as a key competitive factor. Prior studies have examined the relationship between delivery performance and ...

• Delivery guarantee is a decision support tool provided by e-tailers to facilitate consumers' decision-making for purchase and improved rating.
• Delivery guarantee is a double-edged sword that can backfire at a higher magnitude if it ...

Predictive process monitoring (PPM) allows companies to improve the efficiency of their business processes by predicting aspects such as the process outcome, the next event, or the time until the next event. So far, existing studies have mainly ...

• Propose integration of digital documents into predictive processing monitoring.
• Deep learning architecture using pretrained feature extraction methods.
• Evaluation based on real-world data from a German insurance company.
• ...

Data quality is an important topic for businesses and therefore requires appropriate analysis tools. Although several rule-based systems exist today for quality measurement, their results do not always reflect the real impact of quality issues on ...

• Impact of data quality is evaluated using a cost-based ‘fitness for use’ approach.
• Cost-based evaluation is performed by organizing an experiment with 218 volunteers.
• Cost-based evaluation allows for economic considerations ...

• Propose a fake review detection method based on the general mixed probability.
• Generate review data more effectively than several well-known sampling algorithms.
• Yield accurate detection using content, behavioral and ...

Online consumer reviews play an important role in helping consumers judge the quality and authenticity of products on e-commerce platforms. However, the constant presence of fake reviews on these platforms has significantly impacted the operation ...

This work proposes a holistic decision support tool to be used by diverse stakeholders and decision-makers, integrating experimental data. Considering the characteristics of each region, the tool aids in defining the most suitable testing ...

• Decision support tool to sustain strategic and tactical decisions.
• Portugal and France case studies explored in the real pandemic context.
• Aids in designing pool strategies per country and region.
• Experimental work for pool ...