Learning Management Systems are integral technologies within higher education institutions. These tools automatically amass large amounts of log data relating to student activities. The field of learning analytics uses data from learning management systems (LMSs) and student information systems to track student progress and predict future performance in order to enhance learning environments (Siemens, 2011). The aim of this paper is to describe a project where we utilized a system developed in Dublin City University to use information about student engagement with our LMS, Moodle, to create a model predicting pass or failure in certain modules. The project is divided into three distinct phases. An initial investigation was completed analyzing Moodle activity for the last six years. The purpose of this exercise was to determine automatically if "trends" could be identified linking Moodle engagement with student attainment. This was done by training a machine learning classifier to map student online behaviour, against outcomes. Once the classifier was trained, several modules were identified as suitable for building a predictor of student exam success. Ten modules were identified for semester 1 with a further seven identified for semester 2. The second phase involved analyzing current students' engagement with these modules and sending students information about the predictions of their attainment for the module, based on their Moodle engagement. At this stage concerns were raised within the university that the data that we share with the students could actually have the opposite effect to what we are after, i.e. the student may look at the data and think that there is no point in putting in more effort as 'I'm too far behind already'. Dietz-Uhler and Hurn refer to this as "instead of being a constructive tool, feedback becomes a prophet of failure" (Dietz-Uhler, 2013). This contention was addressed by conducting an online survey with students in an effort to explore their experiences of being provided with feedback regarding their engagement with the LMS. The third and final phase of this project was the development of a dashboard for lecturers to enable monitoring of their students' engagement with their module on Moodle. This enables lecturers to have an overview of how students are engaging with their course on Moodle and quickly identify students who are not engaging with the LMS and who are potentially at risk of failure or non-completion. There are numerous examples of the use of learning analytics in higher education. This study focuses on the provision of data obtained through learning analytics to the student and qualitative analysis that was conducted in relation to this data. This research adds to the existing research into learning analytics being used for student retention.