i-Synergy: An integrated predictive model of time pressure, personality types, gender, knowledge and task complexity to determine software developer’s performance

Human factors play a crucial role in software engineering (SE) as software is developed and utilized by people. One of the key reasons for software project failure is not assigning the right people to the right tasks during project planning. This issue becomes critical when developers work under time pressure (TP), often resulting in poor performance and delays. Each personality type approaches TP differently, and gender-based personality differences may further influence how developers handle TP, leading to varied outcomes. In addition, task complexity and developers’ knowledge interrelate with personality types and gender, potentially affecting project performance under TP. The main aim of this study is to propose the i-SYNERGY model by investigating the relationship between TP, personality types, gender, knowledge, and task complexity. To develop this model, empirical evidence was gathered from controlled experiments conducted with SE students, and generalised from industrial data through two case studies. The Myers-Briggs Type Indicator (MBTI) and NASA task load index (TLX) were used to measure personality types and TP, respectively. The data analysis was divided into two stages. The first stage involved examining factual figures of data to develop the model, while the second stage involved predictive experiments for developing the model under the knowledge discovery in databases (KDD) process. Five data mining techniques—artificial neural network (ANN), support vector machine (SVM), decision tree, K-nearest neighbor (KNN) and logistic regression were employed to identify the most suitable technique for model development. Logistic regression yielded the most significant results for developing the study model, confirming that personality types and gender differences influence software developers' ability to handle TP. This study offers empirical evidence regarding the impact of TP on humanistic aspects. Furthermore, the model developed can be leveraged to enhance the success rate of software projects in the field of SE.