Genetic model-based success probability prediction of quantum software development projects

Context: Quantum computing (QC) holds the potential to revolutionize computing by solving complex problems exponentially faster than classical computers, transforming fields such as cryptography, optimization, and scientific simulations. To unlock the potential benefits of QC, quantum software development (QSD) enables harnessing its power, further driving innovation across diverse domains. To ensure successful QSD projects, it is crucial to concentrate on key variables. Objective: This study aims to identify key variables in QSD and develop a model for predicting the success probability of QSD projects. Methodology: We identified key QSD variables from existing literature to achieve these objectives and collected expert insights using a survey instrument. We then analyzed these variables using an optimization model, i.e., Genetic Algorithm (GA), with two different prediction methods the Naïve Bayes Classifier (NBC) and Logistic Regression (LR). Results: The results of success probability prediction models indicate that as the QSD process matures, project success probability significantly increases, and costs are notably reduced. Furthermore, the best fitness rankings for each QSD project variable determined using NBC and LR indicated a strong positive correlation (rs=0.945). The t-test results (t = 0.851, p = 0.402>0.05) show no significant differences between the rankings calculated by the two methods (NBC and LR). Conclusion: The results reveal that the developed success probability prediction model, based on 14 identified QSD project variables, highlights the areas where practitioners need to focus more in order to facilitate the cost-effective and successful implementation of QSD projects.