Synthesizing CRISP-DM and Quality Management: A Data Mining Approach for Production Processes

Schäfer, Franziska; Zeiselmair, Christian; Becker, Jonas; Otten, Heiner

doi:10.1109/itmc.2018.8691266

Cited by 46 publications

(31 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the more recent years, variations of CRISP-DM tailored for the healthcare (Catley et al, 2009 ) and medical domain, such as CRISP-MED-DM (Niaksu, 2015 ), have been suggested. The majority of organisations that apply a data analysis methodology prefers extensions of CRISP-DM (Schäfer et al, 2018 ). Such extensions are fragmented and either propose additional elements into the data analysis process, or focus on organisational aspects without the necessary integration of domain-related factors (Plotnikova, 2018 ).…”

Section: Challenges and Opportunities In Creating Methodologies Which Consistently Embed Interpretabilitymentioning

confidence: 99%

Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach

Kolyshkina¹,

Simoff

2021

Front. Big Data

View full text Add to dashboard Cite

Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. The rapid growth of data collection and linking capabilities combined with the increasing diversity of the data-driven AI techniques, including machine learning (ML), has brought both ubiquitous opportunities for data analytics projects and increased demands for the regulation and accountability of the outcomes of these projects. As a result, the area of interpretability and explainability of ML is gaining significant research momentum. While there has been some progress in the development of ML methods, the methodological side has shown limited progress. This limits the practicality of using ML in the health domain: the issues with explaining the outcomes of ML algorithms to medical practitioners and policy makers in public health has been a recognized obstacle to the broader adoption of data science approaches in this domain. This study builds on the earlier work which introduced CRISP-ML, a methodology that determines the interpretability level required by stakeholders for a successful real-world solution and then helps in achieving it. CRISP-ML was built on the strengths of CRISP-DM, addressing the gaps in handling interpretability. Its application in the Public Healthcare sector follows its successful deployment in a number of recent real-world projects across several industries and fields, including credit risk, insurance, utilities, and sport. This study elaborates on the CRISP-ML methodology on the determination, measurement, and achievement of the necessary level of interpretability of ML solutions in the Public Healthcare sector. It demonstrates how CRISP-ML addressed the problems with data diversity, the unstructured nature of data, and relatively low linkage between diverse data sets in the healthcare domain. The characteristics of the case study, used in the study, are typical for healthcare data, and CRISP-ML managed to deliver on these issues, ensuring the required level of interpretability of the ML solutions discussed in the project. The approach used ensured that interpretability requirements were met, taking into account public healthcare specifics, regulatory requirements, project stakeholders, project objectives, and data characteristics. The study concludes with the three main directions for the development of the presented cross-industry standard process.

show abstract

Section: Challenges and Opportunities In Creating Methodologies Which Consistently Embed Interpretabilitymentioning

confidence: 99%

Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach

Kolyshkina¹,

Simoff

2021

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…Therefore, re-evaluation should be made when similar situations are encountered. In other words, the CRISP-DM method; It can be considered as a supportive tool for improvement, error analysis and quality management, data analysis and mining projects (Schäfer et al, 2018, Weimer et al, 2019. (Huber et al, 2019) (Fahmy et al,2017) In the CRISP-DM process used; After evaluating possible problems at the first stage, a literature review was conducted and which software libraries to use were determined (Table 1).…”

Section: Methodsmentioning

confidence: 99%

Do Machine Learning and Business Analytics Approaches Answer the Question of ‘Will Your Kickstarter Project be Successful?

Kılınç¹,

Aydın²,

Tarhan³

2021

ibr

View full text Add to dashboard Cite

Kickstarter is one of the popular crowdfunding platforms used to implement business ideas on the web. The success of crowdfunding projects such as Kickstarter is realized with future financial support. However, there is no platform where users can get decision support before presenting their projects to supporters. To solve this problem, a platform where users can test their projects is required. Within this scope, a business intelligence model that works on the web has been developed by combining business analytics and machine learning methods. The data used for business analytics has been brought to a state that can provide inferences through visualization, reporting and query processes. Within the scope of machine learning, various algorithms were applied for success classification and the best results were given by 91% Random Forest, 85% Decision Tree, 84% K-Nearest Neighbors (KNN) algorithms. F1-Score, Recall, Precision, Mean Squared Error (MSE), Kappa and AUC values were analyzed to determine the most successful models. Thus, Kickstarter users will be able to see their shortcomings and have a prediction about success before presenting their projects to their backers.

show abstract

“…To corroborate this view from data science experts, we also checked that CRISP-DM is still a very common methodology for data mining applications. For instance, just focussing on the past four years, we can find a large number of conventional studies applying or slightly adapting the CRISP-DM methodology to many different domains: healthcare [18], [19], [20], [21], signal processing [22], engineering [23], [24], education [25], [26], [27], [28], [29], logistics [30] production [31], [32], sensors and wearable applications [33], tourism [34], warfare [35], sports [36] and law [37]. However, things have evolved in the business application of data mining since CRISP-DM was published.…”

Section: Crisp-dm and Related Process Modelsmentioning

confidence: 99%

CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories

Martínez-Plumed

Contreras-Ochando

Ferri

et al. 2021

IEEE Trans. Knowl. Data Eng.

215

101

View full text Add to dashboard Cite

Synthesizing CRISP-DM and Quality Management: A Data Mining Approach for Production Processes

Cited by 46 publications

References 13 publications

Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach

Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach

Do Machine Learning and Business Analytics Approaches Answer the Question of ‘Will Your Kickstarter Project be Successful?

CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories

Contact Info

Product

Resources

About