Data driven TRL Transition Predictions for Early Technology Development in Defence

This paper proposes the framework of TRL (Technology Readiness Level) transition predictions for early technology development in defense. Though predicting future TRLs is an important planning tool, it has been studied less actively than other critical issues on TRL, and previous studies mostly have resorted to domain experts. The proposed data-driven utilises both explanatory predictive modelling techniques. As a case study, applied real data from DTiMS (Defense Technology InforMation Service) which identified as key resource. result shows that two predictor variables, before R&D project cost, are statistically significant TRLs. Also, popular models fitted compared with various performance indices using 10-fold cross validation. selected linear regression support vector machine lowest prediction errors.