Identifying the factors influencing truancy and using data mining for prediction

Truancy from school is a problem in most societies, including developed societies. This research presents the process of discovering the underlying patterns behind truancy through the use of informed discussions and data mining techniques. The main objective of the study is to identify pupils at risk of truancy, before it occurs. Several models were built using different; classification algorithms. K=1-nearest neighbour showed the highest accuracy across all algorithms. The research also showed the importance of the new factor, security situation in identifying pupils at risk of truancy.