Search results

Saudi universities have incorporated capstone projects in the final year of an undergraduate study. Although universities are following recommendations of the National Commission for National Commission for Academic Accreditation and Assessment (NCAAA) and Accreditation Board for Engineering and Technology (ABET), no detailed guidelines for management and assessment of capstone projects are provided by these accreditation bodies. Variation in the management and assessment practices of capstone project courses and analysis of the students' capabilities to align with industry demands, to realize Vision 2030, is challenging. This study investigates the current practices for structure definition, management and assessment criteria used for capstone project courses at undergraduate level for information technology (IT) programs at Saudi universities.

A web-based questionnaire is administered using a web service commonly used for questionnaires and polls to investigate the structure, management and assessment of capstone projects at the undergraduate level offering software engineering, computer science and information technology (SECSIT) programs. In total, 42 faculty members (with range of experience of managing/advising capstone projects from 1 to more than 10 years) from 22 Saudi universities (out of more than 30 universities offering SECSIT undergraduate programs) participated in the study.

The authors have identified that Saudi universities are facing challenges in the utilized process model, the distribution of work and marks, the knowledge sharing approach and the assessment scheme. To cope with these challenges, the authors recommend the use of an incremental development process, the utilization of a project-driven approach, the development of a national level digital archive and the implementation of homogeneous assessment scheme.

To contribute to the national growth and to fulfill the market demand, universities are recommended to align the capstone project courses with latest technology trends. Universities must collaborate with the industry and update the structure and requirements of capstone project courses accordingly. This will further facilitate to bridge the gap between industry and academia and will develop a win–win scenario for all the stakeholders.

Although universities are committed to increase innovative capacities of their students for enabling them to contribute to economic and social growth, it is still hard to know the knowledge creation and sharing at national level. Variations in the management and assessment practices for capstone projects further intensify this challenge. Hence, there is a need of smart assessment and management of software capstone projects being developed in Saudi universities. Incorporating latest technologies, such unified management can facilitate discovering the trends and patterns related to the domain and complexity.

This study proposes a machine learning framework to predict customer complaints from production line tests in an automotive company's lot-release process, enhancing Quality 4.0. It aims to design and implement the framework, compare different machine learning (ML) models and evaluate a non-sampling threshold-moving approach for adjusting prediction capabilities based on product requirements.

This study applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) and four ML models to predict customer complaints from automotive production tests. It employs cost-sensitive and threshold-moving techniques to address data imbalance, with the F1-Score and Matthews correlation coefficient assessing model performance.

The framework effectively predicts customer complaint-related tests. XGBoost outperformed the other models with an F1-Score of 72.4% and a Matthews correlation coefficient of 75%. It improves the lot-release process and cost efficiency over heuristic methods.

The framework has been tested on real-world data and shows promising results in improving lot-release decisions and reducing complaints and costs. It enables companies to adjust predictive models by changing only the threshold, eliminating the need for retraining.

To the best of our knowledge, there is limited literature on using ML to predict customer complaints for the lot-release process in an automotive company. Our proposed framework integrates ML with a non-sampling approach, demonstrating its effectiveness in predicting complaints and reducing costs, fostering Quality 4.0.