Data Analytics Projects Research Articles

The dark side of data ecosystems: A longitudinal study of the DAMD project

ABSTRACT Data are often vividly depicted as strategic assets that organisations can (re)use to create value for myriad purposes. However, the same qualities that make data so appreciated – that is, their volume, their value for a plurality of stakeholders and their indefinite reuse capacity – also have a dark side: data reuse can lead to deviant data use that undermines the legitimacy of data analytics initiatives. To investigate this dynamic, we build on the notion of data ecosystems and provide empirical evidence from a longitudinal, 15-year case study of the emergence, expansion and eventual collapse of a large-scale data analytics project – called DAMD – in the Danish health care sector. We demonstrate that data reuse in the evolving data ecosystem elicited a data reuse dark side that was so dominant that it eventually resulted in the project’s demise. We conceptualise the reuse dark side’s three major mechanisms as function creep, stakeholder creep and data creep. Based on these insights, we develop an empirically grounded Data Analytics Ecosystem Model that extends the current understanding of data ecosystems and provides a view of these ecosystems as having both a bright and a dark side.

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

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.

Comprehensive Data Analytics Project Using Excel and Tableau for the Sales and Purchases Cycles

ABSTRACTUsing materials from PwC's data analytics case study using a fictitious company, Pixystems Toy Company, Inc. (PwC 2017), the authors developed a comprehensive, multi-part data analytics project that is applicable for a variety of accounting courses. The project follows the common data analytics framework (ask the right questions, extract, transform, and load [ETL] the data, perform appropriate analyses, and present the results). Students apply this framework to the sales and purchases cycles. For each, students develop relevant questions, build a data model, and perform other ETL procedures, perform analytics, and prepare a presentation to convey insights and recommendations. For the sales cycle, Microsoft Excel is the analytics tool; for the purchases cycle, Tableau is used. This project provides an opportunity for students to gain experience with two analytics tools, understand the process of building a data model, and wrestle with how to convey the results of their analysis.

Can an understanding of data use in academic libraries assist in public service efforts?

More research is needed on data analytics projects in smaller academic libraries. Every academic library generates its own data, gathers that data, manages the storage of that data, and even may contribute it to a larger body of institutional data. This data could include digital data, reference data, circulation data, and instruction data. As data use becomes more prevalent at the higher educational level, academic libraries must navigate between using their library generated data to assist in meeting larger institutional goals and the library’s foundational values of privacy and confidentiality. The more academic libraries are able to partner with their host institutions, the more accountability will be had in future data analytics projects. The more libraries are attuned to their own data use, the more they are able to better serve their faculty, students, and host institutions.

Data Analytics in Investment Banks

Capital Markets are one of the most important pillars of worldwide economy. They gather skilled finance and IT professionals as well as economists in order to take the best investment decisions and choose the most suitable funding solutions every time. Data analytics projects in Capital Markets can definitely be very beneficial as all optimizations and innovations would have a financial impact, but can also be very challenging as the field itself has always incorporated a research component, thus finding out what could really be of an added value might be a tricky task. Based on a comprehensive literature review, this paper aims to structure the thoughts around data analytics in investment banks, and puts forward a classification of relevant data analytics use cases. Lastly, it also discusses how transforming to a data-driven enterprise is the real change investment banks should aim to achieve, and discusses some of the challenges that they might encounter when engaging in this transformation process.

Towards Identifying Data Analytics Use Cases in Product Planning

Cyber-physical systems (CPS) generate huge amounts of data during the usage phase. By analyzing these data, CPS providers can systematically uncover hidden product improvement potentials for future product generations. But many companies face difficulties starting industrial data analytics projects as they cannot rely on experience and miss orientation. Following the canonical action research methodology, this study aims to investigate the definition and specification of data analytics use cases. The results show a clear need for supporting methods and tools for defining and specifying use cases in usage data-driven product planning.

Data Acquisition and Preparation – Enabling Data Analytics Projects within Production

The increasing amount of available data in production systems is associated with great potential for process optimization. Due to lack of a data analytics methodology and low data quality within production these potentials often remain unused. Therefore, in this paper we present a model for data acquisition and data preparation including feature engineering for characteristic sensor signals of production machines. The model allows the extraction of relevant process information from the signal, which can be used for monitoring, KPI tracking, trend analysis and anomaly detection. The approach is evaluated on an industrial turning process.

Benchmarking PySyft Federated Learning Framework on MIMIC-III Dataset

The adoption of the advanced data analytics methods has been limited in industries governed by strict data reuse regulations, such as healthcare. Barriers to data access and sharing have affected numerous research and development initiatives in healthcare resulting in major delays, extensive use of resources for data access and findings originating from datasets that are too small to be generalizable. Federated machine learning presents a solution to the problems health data analytics projects are facing by providing a way of complying with strict regulatory requirements without sacrificing privacy. Computing frameworks supporting federated machine learning are still in their infancy and their performance in realistic settings has been studied only to a limited extent. To expand the existing knowledge on federated learning in realistic deployment settings three groups of experiments comparing the performance of a neural network-based model trained in federated manner to that of an equivalent baseline model trained on centralized data storage were designed. Experiments were conducted on the MIMIC-III dataset and modelled a binary classification problem predicting in-hospital mortality. The effect that varying amounts of data, number of computational nodes, and data distribution in the federated network had on model performance and on training and inference durations were studied. Experiments demonstrated predictive performance comparable to that of the baseline for models trained in federated settings in terms of area under the ROC and F1 scores. Data distribution across computing nodes showed minimal to no effect on model performance or on training and inference durations. However, federated model training and inference took approximately 9 and 40 times longer, respectively, than the equivalent tasks executed in centralized settings. These results indicate that federated learning is a viable solution for enabling advanced data analytics in environments regulated by strict privacy requirements.

Sowing the seeds of value? Persuasive practices and the embedding of big data analytics

This paper draws on data from three organisational case studies and expert interviews to propose that persuasive practices are the precursors and enablers of analytical capability development. A bundle of seven practices was identified and observed to bridge multiple gaps between technical and non-technical colleagues on big data analytics (BDA) projects. The deployment of these practices varied according to the level of BDA maturity and featured a host of socio-material elements. This paper complements existing technical case studies with a fine-grained qualitative account of the managerial and human elements of BDA implementation. Effective deployment of persuasive practices potentially both embeds the benefits and mitigates the risks of BDA, sowing the seeds of many different forms of value.

Identifying the value of data analytics in the context of government supervision: Insights from the customs domain

eCommerce, Brexit, new safety and security concerns are only a few examples of the challenges that government organisations, in particular customs administrations, face today when controlling goods crossing borders. To deal with the enormous volumes of trade customs administrations rely more and more on information technology (IT) and risk assessment, and are starting to explore the possibilities that data analytics (DA) can offer to support their supervision tasks. Driven by customs as our empirical domain, we explore the use of DA to support the supervision role of government. Although data analytics is considered to be a technological breakthrough, there is so far only a limited understanding of how governments can translate this potential into actual value and what are barriers and trade-offs that need to be overcome to lead to value realisation. The main question that we explore in this paper is: How to identify the value of DA in a government supervision context, and what are barriers and trade-offs to be considered and overcome in order to realise this value? Building on leading models from the information system (IS) literature, and by using case studies from the customs domain, we developed the Value of Data Analytics in Government Supervision (VDAGS) framework. The framework can help managers and policy-makers to gain a better understanding of the benefits and trade-offs of using DA when developing DA strategies or when embarking on new DA projects. Future research can examine the applicability of the VDAGS framework in other domains of government supervision.

Intelligent User Assistance for Automated Data Mining Method Selection

In any data science and analytics project, the task of mapping a domain-specific problem to an adequate set of data mining methods by experts of the field is a crucial step. However, these experts are not always available and data mining novices may be required to perform the task. While there are several research efforts for automated method selection as a means of support, only a few approaches consider the particularities of problems expressed in the natural and domain-specific language of the novice. The study proposes the design of an intelligent assistance system that takes problem descriptions articulated in natural language as an input and offers advice regarding the most suitable class of data mining methods. Following a design science research approach, the paper (i) outlines the problem setting with an exemplary scenario from industrial practice, (ii) derives design requirements, (iii) develops design principles and proposes design features, (iv) develops and implements the IT artifact using several methods such as embeddings, keyword extractions, topic models, and text classifiers, (v) demonstrates and evaluates the implemented prototype based on different classification pipelines, and (vi) discusses the results’ practical and theoretical contributions. The best performing classification pipelines show high accuracies when applied to validation data and are capable of creating a suitable mapping that exceeds the performance of joint novice assessments and simpler means of text mining. The research provides a promising foundation for further enhancements, either as a stand-alone intelligent assistance system or as an add-on to already existing data science and analytics platforms.

Advancing manufacturing systems with big-data analytics: A conceptual framework

ABSTRACT With the intensive development and implementation of information and communication technologies in manufacturing, large amounts of heterogeneous data are now being generated, gathered and stored. Handling large amounts of complex data – often referred to as big data – represents a challenge as there are many new approaches, methods, techniques, and tools for data analytics that open up new possibilities for exploiting data by converting them into useful information and/or knowledge. However, the application of advanced data analytics in manufacturing lags behind in terms of penetration and diversity in comparison with other domains such as marketing, healthcare and business, meaning that the available data often remain unexploited. This paper proposes a new conceptual framework for systematically introducing big-data analytics into manufacturing systems. To this end, the paper defines a new stepwise procedure that identifies what knowledge and skills, and which reference models, software and hardware tools, are needed for the development, implementation and operation of data-analytics solutions in manufacturing systems. The feasibility of the proposed conceptual framework is demonstrated in a case study from an engineer-to-order company and by mapping the framework to several previous data-analytics projects.

“We called that a behavior”: The making of institutional data

Predictive uses of data are becoming widespread in institutional settings as actors seek to anticipate people and their activities. Predictive modeling is increasingly the subject of scholarly and public criticism. Less common, however, is scrutiny directed at the data that inform predictive models beyond concerns about homogenous training data or general epistemological critiques of data. In this paper, I draw from a qualitative case study set in higher education in the United States to investigate the making of data. Data analytics projects at universities have become more pervasive and intensive to better understand and anticipate undergraduate student bodies. Drawing from 12 months of ethnographic research at a large public university, I analyze the ways data personnel at the institution—data scientists, administrators, and programmers—sort student data into “attributes” and “behaviors,” where “attributes” are demographic data that students “can’t change.” “Behaviors,” in contrast, are data defined as reflective of what students can choose: attending and paying attention in class, studying on campus, among other data which personnel categorize as what students have control over. This discursive split enables the institution nudge students to make responsible choices according to behavior data that correlate with success in the predictive model. In discussing how personnel type, sort, stabilize, and nudge on behavior data, this paper examines the contingencies of data making processes and implications for the application of student data.

Precise and Fast Cryptanalysis for Bloom Filter Based Privacy-Preserving Record Linkage

Being able to identify records that correspond to the same entity across diverse databases is an increasingly important step in many data analytics projects. Research into privacy-preserving record linkage (PPRL) aims to develop techniques that can link records across databases such that besides the record pairs classified as matches no sensitive information about the entities in these databases is revealed. A popular technique used in PPRL is to encode sensitive values into Bloom filters (bit vectors), which has the advantage of allowing approximate matching using character q-grams. PPRL based on Bloom filter encoding has been shown to be accurate and scalable to large databases, and is thus now being used in real-world PPRL systems in Australia, Canada, and the UK. However, recent studies have shown that Bloom filters used for PPRL are vulnerable to cryptanalysis attacks that can re-identify some of the sensitive values encoded in these Bloom filters. While previous such attack methods were slow and required knowledge of various encoding parameters, we present a novel efficient attack which exploits how attribute values are encoded into Bloom filters. Our attack method does not require knowledge of the encoding function or its parameter settings used. It is able to correctly re-identify with high precision q-grams that could not have been hashed to certain Bloom filter bit positions, and using these re-identified q-grams it can then re-identify attribute values with high precision. Our method is significantly faster than earlier PPRL cryptanalysis attacks, and in our experimental evaluation, it is able to successfully re-identify attribute values from large real-world databases in a few minutes.

Enriching analytics models with domain knowledge for smart manufacturing data analysis

Today, data analytics plays an important role in Smart Manufacturing decision making. Domain knowledge is very important to support the development of analytics models. However, in today's data analytics projects, domain knowledge is only documented, but not properly captured and integrated with analytics models. This raises problems in interoperability and traceability of the relevant domain knowledge that is used to develop analytics models. To address these problems, this paper proposes a methodology to enrich analytics models with domain knowledge. To illustrate the proposed methodology, a case study is introduced to demonstrate the utilisation of the enriched analytics model to support the development of a Bayesian Network model. The case study shows that the utilisation of an enriched analytics model improves the efficiency in developing the Bayesian Network model.

Contributing Factors on the Effectiveness of Delivering Business Technology Courses: On-Ground Versus Online

Enrollment in online college courses in the United States has grown by about 5% from 2012 to 2016. This paper examines course design and student performance data to research whether instructors can delivery on-ground and online sections of a business technology course with the same effectiveness. Authors address this paper’s research question by analyzing five pairs of on-ground and online sections of business technology courses. Each of the five pairs of business technology course, has data analytics projects as part of the course content, is taught by the same instructor with the same details of course contents in the same quarter. Overall results of this paper suggest that, with proper training and support of technology, an instructor can deliver both the on-ground and online sections of a business technology course with the same effectiveness as measured by students’ grade points. Further analysis shows that this result applies to female and male students, respectively. Female (male) students learn equally well in on-ground and online. This paper contributes to the literature by discussing some contributing factors on the effectiveness of delivering online business technology courses. Authors suggest that other than technology such as LockDown Browser or Respondus Monitor, continuous placement of the same instructor with Quality Matters training to teach both the on-ground and online sections of a course is crucial to success. Results of this paper consequently provide practical implications to instructors, academic advisers, and administrators of universities.

Accounting students’ learning processes in analytics: A sensemaking perspective

This paper takes a sensemaking perspective for purposes of better understanding the learning processes of students engaged in data analytics tasks and thus provide an enriched approach to teaching the subject. A sensemaking perspective addresses a gap in the accounting education literature by describing the learning processes associated with conducting data analytics tasks. A case study methodology was used by conducting an exploratory study of students’ sensemaking activities while engaging in an experiential data analytics project. Findings from the study suggest students engaged in data analytics tasks experience states of uncertainty and ambiguity. They also experience behaviors of wrestling to develop findings and insights, experimenting followed by failure, creating solutions, and regularly evaluating their work progress. The variety of these behaviors, which resemble deep-learning processes can pose challenges to teaching data analytics to accounting students.

Case Article—Baseball Analytics: Advancing to Prescriptive Analytics in the Major League Baseball Front Office

This case uses player evaluation and personnel decision making in Major League Baseball (MLB) to introduce many of the key steps of data analytics projects. The data analytics process is a unique combination of art and science, and teaching the art of data analytics is challenging to do in a standard classroom setting with small data sets. The goal of this case is to move beyond the simple “cookie cutter” data sets and introduce students to the challenges of dealing with real data to answer important questions, as well as introduce or reinforce multiple data-mining/machine-learning methods. The case builds on a very rich data set collected by the authors, which allows for students or groups of students to arrive at different answers to the same question. An extensive teaching note with sample questions and the associated R code and output are at https://doi.org/10.1287/ited.2018.0201ca .

Case—Baseball Analytics: Advancing to Prescriptive Analytics in the Major League Baseball Front Office

This case uses player evaluation and personnel decision making in Major League Baseball (MLB) to introduce many of the key steps of data analytics projects. The data analytics process is a unique c...

Bringing big data analytics closer to practice: A methodological explanation and demonstration of classification algorithms

BackgroundBig data analytics are becoming more prevalent due to the recent availability of health data. Yet in spite of evidence supporting the potential contribution of big data analytics to health policy makers and care providers, these tools are still too complex to be routinely used. Further, access to comprehensive datasets required for more accurate results is complex and costly. Consequently, big data analytics are mostly used by researchers and experts who are far removed from actual clinical practice. Hence, policy makers should allocate resources to encourage studies that clarify and simplify big data analytics so it can be used by non-experts (e.g., clinicians, practitioners and decision-makers who may not have advanced computer skills). It is also important to fund data collection and integration from various health IT, a pre-condition for any big data analytics project. ObjectivesTo methodologically clarify the rationale and logic behind several analytics algorithms to help non-expert users employ big data analytics by understanding how to implement relatively easy to use platforms as Azure ML. MethodsWe demonstrate the predictive power of four known algorithms and compare their accuracy in predicting early mortality of Congestive Heart Failure (CHF) patients. ResultsThe results of our models outperform those reported in the literature, attesting to the strength of some of the models, and the utility of comprehensive data. ConclusionsThe results support our call to policy makers to allocate resources to establishing comprehensive, integrated health IT systems, and to projects aimed at simplifying ML analytics.