A total data quality management for credit risk: new insights and challenges

Moges, Helen Tadesse; Dejaeger, Karel; Lemahieu, Wilfried; Baesens, Bart

doi:10.1504/ijiq.2012.050036

Cited by 5 publications

(9 citation statements)

References 39 publications

(124 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another operational advantage of this type of data concerns data quality (Moges et al 2012): typically this is a major challenge when working with structured data. With payment data, however, no such issues arose: a simple "dump" from the transaction log is all that is needed for the BeSim method to be applied.…”

Section: Expert Feedbackmentioning

confidence: 99%

Mining Massive Fine-Grained Behavior Data to Improve Predictive Analytics

Martens

Provost

Clark

et al. 2016

MISQ

104

View full text Add to dashboard Cite

Organizations increasingly have access to massive, fine-grained data on consumer behavior. Despite the hype over "big data," and the success of predictive analytics, only a few organizations have incorporated such finegrained data in a non-aggregated manner into their predictive analytics. This paper examines the use of massive, fine-grained data on consumer behavior-specifically payments to a very large set of particular merchants-to improve predictive models for targeted marketing. The paper details how using this different sort of data can substantially improve predictive performance, even in an application for which predictive analytics has been applied for years. One of the most striking results has important implications for managers considering the value of big data. Using a real-life data set of 21 million transactions by 1.2 million customers, as well as 289 other variables describing these customers, the results show that there is no appreciable improvement from moving to big data when using traditional structured data. However, in contrast, when using fine-grained behavior data, there continues to be substantial value to increasing the data size across the entire range of the analyses. This suggests that larger firms may have substantially more valuable data assets than smaller firms, when using their transaction data for targeted marketing.

show abstract

Section: Expert Feedbackmentioning

confidence: 99%

Mining Massive Fine-Grained Behavior Data to Improve Predictive Analytics

Martens

Provost

Clark

et al. 2016

MISQ

104

View full text Add to dashboard Cite

show abstract

“…In this article, we validate our work analyzing a large case study from a financial institution, focusing on evaluating the probability of default, which is one of the main components of risk analysis. In the literature, the challenges of data quality in credit risk evaluation processes have been discussed in Moges et al (2012). In particular, the paper illustrates the main quality dimensions considered relevant by stakeholders and identifies accuracy as the main issue in this context.…”

Section: Related Workmentioning

confidence: 99%

“…We define it as a process that, on the basis of given inputs, provides as output an assessment (denoted as Process Outcome, y) that is a ranking or a rating for an object under investigation on a given scale of values. As discussed in the related work, this type of assessment is typical of decision-making processes, such as in financial institutions (Moges et al 2012). For instance, objects of investigation in a financial institution are the customers asking for credit to whom a rating is associated, which is used as a basis for decision making.…”

Section: Scenario: Scoring Processesmentioning

confidence: 99%

Validating Data Quality Actions in Scoring Processes

Cappiello

Cerletti

Fratto

et al. 2017

J. Data and Information Quality

View full text Add to dashboard Cite

Data quality has gained momentum among organizations upon the realization that poor data quality might cause failures and/or inefficiencies, thus compromising business processes and application results. However, enterprises often adopt data quality assessment and improvement methods based on practical and empirical approaches without conducting a rigorous analysis of the data quality issues and outcome of the enacted data quality improvement practices. In particular, data quality management, especially the identification of the data quality dimensions to be monitored and improved, is performed by knowledge workers on the basis of their skills and experience. Control methods are therefore designed on the basis of expected and evident quality problems; thus, these methods may not be effective in dealing with unknown and/or unexpected problems. This article aims to provide a methodology, based on fault injection, for validating the data quality actions used by organizations. We show how it is possible to check whether the adopted techniques properly monitor the real issues that may damage business processes. At this stage, we focus on scoring processes, i.e., those in which the output represents the evaluation or ranking of a specific object. We show the effectiveness of our proposal by means of a case study in the financial risk management area.

show abstract

“…Shankaranarayanan et al [38] used a percentage DQM representation where the quality level of the data represented with an 80% accuracy or completeness level is better than the quality of data represented by a 70% level. Moges et al [24] conducted a pilot study to evaluate DQM representations by using two different types of DQM formats. These are DQM with lower and upper value limits (range representation) and probability representation.…”

Section: Graphicalmentioning

confidence: 99%

“…Moreover, the impact of DQM on decision outcomes can be negative. In response, prior DQM research investigated the use of DQM for decision making processes, although there is no full consensus on the results [4,9,23]. Some researchers have found that DQM is used in certain situations [9], and others didn't find any statistical evidence that DQM is actually used, even when it is available [34].…”

Section: Introductionmentioning

confidence: 99%

Determining the use of data quality metadata (DQM) for decision making purposes and its impact on decision outcomes — An exploratory study

Moges

Vlasselaer

Lemahieu

et al. 2016

Decision Support Systems

Self Cite

View full text Add to dashboard Cite

Decision making processes and their outcomes can be affected by a number of factors. Among them, the quality of the data is critical. Poor quality data causes poor decisions. Although this fact is widely known, data quality (DQ) is still a critical issue in organizations because of the huge data volumes available in their systems. Therefore, literature suggests that communicating the DQ level of a specific data set to decision makers in the form of DQ metadata (DQM) is essential. However, the presence of DQM may overload or demand cognitive resources beyond decision makers' capacities, which can adversely impact the decision outcomes. To address this issue, we have conducted an experiment to explore the impact of DQM on decision outcomes, to identify different groups of decision makers who benefit from DQM and to explore different factors which enhance or otherwise hinder the use of DQM. Findings of a statistical analysis suggest that the use of DQM can be enhanced by data quality training or education. Decision makers with a certain level of data quality awareness used DQM more to solve a decision task than those with no data quality awareness. Moreover, those with data quality awareness reached a higher decision accuracy. However, the efficiency of decision makers suffers when DQM is used. Our suggestion would be that DQM can have a positive impact on decision outcomes if it is associated with some characteristics of decision makers, such as a high data quality knowledge. However, the results do not confirm that DQM should be included in datawarehouses as a general business practice, instead organizations should first investigate the use and impact of DQM in their setting before maintaining DQM in datawarehouses.

show abstract

A total data quality management for credit risk: new insights and challenges

Cited by 5 publications

References 39 publications

Mining Massive Fine-Grained Behavior Data to Improve Predictive Analytics

Mining Massive Fine-Grained Behavior Data to Improve Predictive Analytics

Validating Data Quality Actions in Scoring Processes

Determining the use of data quality metadata (DQM) for decision making purposes and its impact on decision outcomes — An exploratory study

Contact Info

Product

Resources

About