Abstract: Predicting risks in software projects is essential to reducing cost overruns, avoiding delays, and improving project success rates. Traditional estimation techniques often fail because risk ...

The growth of machine learning (ML) has revealed model vulnerabilities to adversarial attacks, where small data perturbations degrade performance. Classical defenses often struggle, especially with ...

Using the GBM algorithm to predict the subsequent 3-month OUD risk, the top decile subgroup had a positive predictive value of 3.26%, a negative predictive value of 99.8%, and a number needed to ...