Sustaining learners through an education cycle is a challenge for institutions at all levels. Forhigher education institutions, learners are presumed to be mature enough to complete theirstudy courses. However, the challenge of student dropouts is prevalent. This paper seeksto address the key question of why students continue to drop out of learning institutionsdespite interventions undertaken by stakeholders. The attrition rates are a major concernthat requires immediate attention if sustainable education is to be achieved. Dropping outof school is attributed to both individual factors and external factors. However, both requiremitigation to save the future of education. This paper presents an analysis of challengesleading to student dropouts sampled from five institutions within the central region ofUganda (532 respondents). In addition, we leveraged the power of artificial intelligence (AI)to design and present a machine learning model for early student dropout prediction so thatearly interventions can be undertaken.

The study adopted the design science methodology to scientifically support the design andvalidation of the machine learning student dropout prediction model. The early warningmodel presents key performance indicators to signal whether a student is predisposed todrop out or on course to completion. This way corrective intervention can be undertaken early enough for likely dropout. The validation experiment conducted on a sample of 523from the five institutions predicated a dropout of 10%. This proved the concept and thecapacity of the model to predict learner dropout from university.