Can language help in the characterization of user behaviour? Feature engineering experiments with Word2Vec

Among the many significant advances in the area of deep learning– use of deep neural networks –, the Natural Language Processing (NLP) space holds a special place. The availability of very large datasets, along with the existence of powerful computing environments have created a fascinating environment for researchers. One of the algorithms recently created is Word2Vec — it enables the creation of embeddings: low-dimensional, meaningful representation of language that can be used for machine learning tasks such as prediction or classification. In this study, we experiment with Word2Vec and apply it to a different domain: representation of user behavior in information systems. We demonstrate how many feature engineering tasks for user behavior characterization can be enriched by the use of NLP concepts.

Critical factors in the use of High-Performance Computing for user behaviour feature engineering


Towards a unified ontology for the design of Secure Enterprise Governance of Information Technology (SEGIT) systems

The design and implementation of a secure governance system for an Information Technology (IT) operation is a complex endeavor. An end-to-end implementation based on COBIT 2019 revolves around seeking the achievement of 40 objectives, each with 7 different types of components that need to be tailored to the specific context in which the organization operates. In particular, there are 40 different master processes that encompass more than 1,200 activities — each with suppliers providing inputs and customers receiving outputs. Moreover, the design of a Secure Enterprise Governance of IT (SEGIT) system needs to recognize the many sources that provide guidance for the organization. From government regulations to industry-specific mandates, the sheer amount of information processed can be a daunting exercise for the stakeholders involved. The design of a SEGIT system departs from a common understanding of the artifacts that need to be created — such as processes or controls — so all stakeholders have a shared conceptualization for the system. This study is about seeking this shared conceptualization: an ontology for the design of secure governance systems. Furthermore, we implement the posited ontology with the use of two technological environments: Protégé and Apache Fuseki.

Towards a substantive theory for DevSecOps adoption

DevSecOps is a set of people, process and technology practices in software development that dramatically transforms the way in which information system changes are planned and deployed. Notwithstanding its benefits, successful DevSecOps adoption requires careful planning, design and implementation. In this qualitative study we use Grounded Theory as the foundational research method to posit a theory for DevSecOps adoption, and analyze via a case study in a mid-size Canadian organization.