Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques

Requirement elicitation represents one of the most vital phases in information system (IS) and software development projects. Selecting suitable techniques is critical for eliciting correct specification various Recent studies have revealed that improper novice practices this phase increased failure rate both IS Previous research has primarily relied on creating procedural systems based contextual properties. In contrast, paper introduces a deep learning model selecting requirement elicitation. An experiment was conducted wherein collected dataset 1684 technique selection attributes were investigate with respect to 14 techniques. The study adopted seven criteria evaluate predictive performance using confusion matrix accuracy, precision, recall, F1 Score, area under ROC curve (AUC) loss curve. scored prediction accuracy 82%, precision score 0.83, recall 0.82, cross-validation 0.82 (± 0.10), One-vs-One AUC 0.74, One-vs-Rest 0.75 each label. Our results indicate model’s high ability. provides robust decision-making process delivering lowering risk project failure. implications can be used promote automatization process, thereby enhancing current required industry practices.