Abstract—E-learning platforms, such as Blackboard have two major shortcomings: limited data capture as a result of the limitations of SCORM (Shareable Content Object Reference Model), and lack of incorporation of Artificial Intelligence (AI) and machine learning algorithms which could lead to better course adaptations. With the recent development of Experience Application Programming Interface (xAPI), a large amount of additional types of data can be captured and that opens a window of possibilities from which online education can benefit. In a corporate setting, where companies invest billions on the learning and development of their employees, some learner behaviours can be troublesome for they can hinder the knowledge development of a learner. Behaviours that hinder the knowledge development also raise ambiguity about learner’s knowledge mastery, specifically those related to gaming the system. Furthermore, a company receives little benefit from their investment if employees are passing courses without possessing the required knowledge and potential compliance risks may arise. Using xAPI and rules derived from a state-of-the-art review, we identified three learner behaviours, primarily related to guessing, in a corporate compliance course. The identified behaviours are: trying each option for a question, specifically for multiple-choice questions; selecting a single option for all the questions on the test; and continuously repeating tests upon failing as opposed to going over the learning material. These behaviours were detected on learners who repeated the test at least 4 times before passing the course. These findings suggest that gauging the mastery of a learner from multiple-choice questions test scores alone is a naive approach. Thus, next steps will consider the incorporation of additional data points, knowledge estimation models to model knowledge mastery of a learner more accurately, and analysis of the data for correlations between knowledge development and identified learner behaviours. Additional work could explore how learner behaviours could be utilised to make changes to a course. For example, course content may require modifications (certain sections of learning material may be shown to not be helpful to many learners to master the learning outcomes aimed at) or course design (such as the type and duration of feedback). Keywords—Compliance Course, Corporate Training, Learner Behaviours, xAPI. I. INTRODUCTION -LEARNING platforms, often referred to as Learning Management Systems (LMSs) such as Blackboard, Moodle, and Canvas have been widely adopted by schools and universities around the globe. However, the types of data that can be collected by these systems are very limited due to the L. Zachoval, D. O’Broin, and O. Cawley are with the Institute of Technology Carlow, Co. Carlow, Ireland (e-mail: Libor.Zachoval@ itcarlow.ie, Daire.OBroin@itcarlow.ie, oisin.cawley@itcarlow.ie). limitations of SCORM [1]. This data limitation constraints the use and applicability of many AI and machine learning algorithms that could be used to refine and further adapt online courses [2], [3], often these algorithms require a huge amount of data and appropriate features which often could not be captured. However, the xAPI tares down these barriers. The xAPI can capture a vast number of additional data types across multiple devices whether the user is online or offline [4]. Many innovative opportunities arise from this development but also uncertainties, such as, what data are worth capturing. The corporate world is highly competitive and in order for companies to stay competitive they invest into the training and development of their employees [5], [6]. Training and development may involve mandatory compliance courses which employees are required to pass. The emphasis on passing may divert focus away from learning towards passing the test. At present, scores achieved in multiple-choice questions gauge the mastery of a learner. However, this is a naive approach since a course may be passed without possessing the required knowledge. Learners can attempt to “game-the-system” by exploiting specific features of the system or the course to obtain correct answers [7], [8]. The identification of behaviours around gaming the system is quite a popular topic in the Intelligent Tutoring Community as gaming behaviours lead to poorer learning [7], [8]. In a corporate setting, such behaviours are troublesome, because the company receives only a little benefit from their investment if employees are passing courses without possessing the required knowledge and potential compliance risks may arise. Therefore, it is important to be aware of behaviours that hinder the development of learner’s knowledge and consider them while gauging one’s knowledge mastery. II. TERMINOLOGY A. SCORM SCORM carries two meanings in its name [9]-[12]. The first meaning lies in the Shareable Content Object (SCO), a simple learning object that together with a combination of other SCOs may form a course (an indication of object creation which can be shared across systems). The second meaning lies in the Reference Model (RM), a description of how existing technical specifications may be properly used by the developers, in this case it defines a way to construct an e- learning platform such as Learning Management System Libor Zachoval, Daire O Broin, Oisin Cawley Leveraging xAPI in a Corporate e-Learning Environment to Facilitate the Tracking, Modelling, and Predictive Analysis of Learner Behaviour E World Academy of Science, Engineering and Technology International Journal of Educational and Pedagogical Sciences Vol:13, No:11, 2019 1441 International Scholarly and Scientific Research & Innovation 13(11) 2019 ISNI:0000000091950263 Open Science Index, Educational and Pedagogical Sciences Vol:13, No:11, 2019 waset.org/Publication/10010902