Official government website of the Government of Kingdom of Saudi Arabia
Link to official Saudi websites end with edu.sa

All links to official educational websites in the Kingdom of Saudi Arabia end with sch.sa or edu.sa

Government websites use the HTTPS protocol for encryption and security.

Secure websites in the Kingdom of Saudi Arabia use the HTTPS protocol for encryption.

Registered with the Digital Government Authority under number:

20250417892
Main
UQU Programs
Data Science

Graduation Project 1

DS4801
3 hours English

Graduation Project 1

Capstone Project 2
1 Advanced Project Introduction and Objectives / Overview of Capstone 2 objectives and expectations / Introduction to advanced tools, techniques, and methodologies / Review of Project 1 projects (if applicable) and lessons learned / Team reformation or project continuation
2 Industry Problem Identification and Proposal / Engage with industry or research partners to identify real-world problems / Develop a detailed project proposal, including scope, objectives, and timeline / Advanced stakeholder communication techniques
3 Advanced Data Engineering / Implement robust data pipelines for large-scale processing / Use tools like Apache Spark, Hadoop, or Airflow for scalable data handling / Develop reusable and efficient data transformation workflows
4 Exploratory Data Analysis with Advanced Tools / Use advanced visualization libraries (e.g., Plotly, D3.js) / Perform detailed statistical and geospatial analyses (if applicable) / Discover hidden patterns and trends in the data
5 Model Selection for Complex Problems / Implement advanced algorithms (e.g., XGBoost, Random Forests, Deep Learning) / Handle multi-class, multi-output, or hierarchical predictions / Explore domain-specific models (e.g., NLP, computer vision, time-series)
6 Custom Model Development and Optimization / Build custom architectures or frameworks (e.g., TensorFlow, PyTorch) / Use AutoML tools for model selection and optimization / Integrate domain knowledge into model features
7 Evaluation of Advanced Models / Implement advanced evaluation metrics (e.g., AUC-ROC, BLEU, mAP) / Use SHAP or LIME for interpretability in complex models / Compare results with benchmarks or industry standards
8 Model Deployment and Operationalization / Deploy models in production using MLOps principles / Set up CI/CD pipelines for machine learning projects / Optimize models for real-time or edge deployment
9 Scalability and Performance Tuning / Optimize computational performance and reduce latency / Handle large-scale data and model deployment using cloud infrastructure / Apply caching and load-balancing strategies
10 Final Testing and Documentation / Perform extensive testing for edge cases and scalability / Prepare comprehensive documentation for all phases of the project / Review and refine the final solution
11 Final Presentations and Stakeholder Review / Present the completed project to industry partners, faculty, or peers / Focus on business value, technical depth, and societal impact / Incorporate feedback from reviewers
12 Course Reflection and Future Outlook / Reflect on advanced learning and career readiness / Discuss how to publish, patent, or productize the project (if applicable) / Guidance on using Capstone 2 for resumes, interviews, or further research
1.1 Mapped to: K1

Demonstrate a deep understanding of data science principles and their applications in real-world scenarios.

Teaching Strategy Use case studies, industry partner collaboration, and project-based learning to apply principles.
Assessment Methods Discussion
1.2 Mapped to: K2

Analyze datasets to derive meaningful insights and solutions.

Teaching Strategy Hands-on workshops, real-world data challenges, collaborative problem-solving.
Assessment Methods Discussion
2.1 Mapped to: S1

Implement end-to-end data science applications using advanced data analytics techniques.

Teaching Strategy Group projects, industry-specific projects, and interactive coding sessions
Assessment Methods Discussion
2.2 Mapped to: S2

Formulate data-driven solutions for complex, interdisciplinary problems.

Teaching Strategy Problem-based learning, interdisciplinary collaboration, and solution-oriented tasks.
Assessment Methods Discussion
2.3 Mapped to: S3

Evaluate and select appropriate tools, algorithms, and techniques for specific problems.

Teaching Strategy Tool selection workshops, algorithm comparison exercises, guest lectures from industry experts.
Assessment Methods Discussion
3.1 Mapped to: V1

Propose innovative data solutions that align with organizational objectives

Teaching Strategy Simulations, business challenge scenarios, collaboration with industry partners for project work.
Assessment Methods Final Project Presentation, Innovation Proposals
3.2 Mapped to: V2

Address ethical issues such as bias, fairness, and accountability in data science.

Teaching Strategy Ethical case studies, discussions, debates, and collaborative workshops on data ethics.
Assessment Methods Discussion
Assessment
Weight
Weekly Lab Assessments
25%
Project Presentation and Report
75%
Total
100%