(1) To develop a rigorous and repeatable method for building effective Bayesian network (BN) models for medical decision support from complex, unstructured and incomplete patient questionnaires and interviews that inevitably contain examples of repetitive, redundant and contradictory responses; (2) To exploit expert knowledge in the BN development since further data acquisition is usually not possible; (3) To ensure the BN model can be used for interventional analysis; (4) To demonstrate why using data alone to learn the model structure and parameters is often unsatisfactory even when extensive data is available. The method is based on applying a range of recent BN developments targeted at helping experts build BNs given limited data. While most of the components of the method are based on established work, its novelty is that it provides a rigorous consolidated and generalised framework that addresses the whole life-cycle of BN model development. The method is based on two original and recent validated BN models in forensic psychiatry, known as DSVM-MSS and DSVM-P. When employed with the same datasets, the DSVM-MSS demonstrated competitive to superior predictive performance (AUC scores 0.708 and 0.797) against the state-of-the-art (AUC scores ranging from 0.527 to 0.705), and the DSVM-P demonstrated superior predictive performance (cross-validated AUC score of 0.78) against the state-of-the-art (AUC scores ranging from 0.665 to 0.717). More importantly, the resulting models go beyond improving predictive accuracy and into usefulness for risk management purposes through intervention, and enhanced decision support in terms of answering complex clinical questions that are based on unobserved evidence. This development process is applicable to any application domain which involves large-scale decision analysis based on such complex information, rather than based on data with hard facts, and in conjunction with the incorporation of expert knowledge for decision support via intervention. The novelty extends to challenging the decision scientists to reason about building models based on what information is really required for inference, rather than based on what data is available and hence, forces decision scientists to use available data in a much smarter way.

To make accurate predictions of attributes like defects found in complex software projects we need a rich set of process factors. We have developed a causal model that includes such process factors, both quantitative and qualitative. The factors in the model were identified as part of a major collaborative project. A challenge for such a model is getting the data needed to validate it. We present a dataset, elicited from 31 completed software projects in the consumer electronics industry, which we used for validation. The data were gathered using a questionnaire distributed to managers of recent projects. The dataset will be of interest to other researchers evaluating models with similar aims. We make both the dataset and causal model available for research use.

Background: This paper investigates the impact of data quality on the performance of models predicting effort on software testing. Data quality was reflected by training data filtering strategies (data variants) covering combinations of Data Quality Rating, UFP Rating, and a threshold of valid cases. Methods: The experiment used the ISBSG dataset and 16 machine learning models. A process of three-fold cross-validation repeated 20 times was used to train and evaluate each model with each data variant. Model performance was assessed using absolute errors of prediction. A ‘win–tie–loss’ procedure, based on the Wilcoxon signed-rank test, was applied to identify the best models and data variants. Results: Most models, especially the most accurate, performed the best on a complete dataset, even though it contained cases with low data ratings. The detailed results include the rankings of the following: (1) models for particular data variants, (2) data variants for particular models, and (3) the best-performing combinations of models and data variants. Conclusions: Arbitrary and restrictive data selection to only projects with Data Quality Rating and UFP Rating of ‘A’ or ‘B’, commonly used in the literature, does not seem justified. It is recommended not to exclude cases with low data ratings to achieve better accuracy of most predictive models for testing effort prediction.

Accurate estimation of software project characteristics during the early stages of development remains a constant challenge in software projects. Recent research suggests that large language models (LLMs) offer new opportunities to support such estimation tasks through their ability to interpret natural language specifications and extract contextual information from project descriptions. This paper presents a mapping study providing an overview of research on the applications of LLMs in early software project estimation. Thirty primary studies were systematically identified and categorised to examine estimation targets, used models, reference and supportive techniques, as well as applied evaluation measures. The obtained results provide insights into the methodological considerations, limitations, and challenges associated with LLM-based estimation approaches. The obtained findings inform both researchers and practitioners about the current state and potential of LLMs for supporting early-stage software project estimation.