This thesis describes a longitudinal study on factors which predict academic success in introductory programming at undergraduate level, including the development of these factors into a fully automated web based system (which predicts students who are at risk of not succeeding early in the introductory programming module) and interventions to address attrition rates on introductory programming courses (CS1). Numerous studies have developed models for predicting success in CS1, however there is little evidence on their ability to generalise or on their use beyond early investigations. In addition, they are seldom followed up with interventions, after struggling students have been identified. The approach overcomes this by providing a web-based real time system, with a prediction model at its core that has been longitudinally developed and revalidated, with recommendations for interventions which educators could implement to support struggling students that have been identified. This thesis makes five fundamental contributions. The first is a revalidation of a prediction model named PreSS. The second contribution is the development of a web-based, real time implementation of the PreSS model, named PreSS#. The third contribution is a large longitudinal, multi-variate, multi-institutional study identifying predictors of performance and analysing machine learning techniques (including deep learning and convolutional neural networks) to further develop the PreSS model. This resulted in a prediction model with approximately 71% accuracy, and over 80% sensitivity, using data from 11 institutions with a sample size of 692 students. The fourth contribution is a study on insights on gender differences in CS1; identifying psychological, background, and performance differences between male and female students to better inform the prediction model and the interventions. The final, fifth contribution, is the development of two interventions that can be implemented early in CS1, once identified by PreSS# to potentially improve student outcomes. The work described in this thesis builds substantially on earlier work, providing valid and reliable insights on gender differences, potential interventions to improve performance and an unsurpassed, generalizable prediction model, developed into a real time web-based system.