ACIT4520 Applied Data Science Project Course description

A team of students will carry out a real-world data science project. A practical data-driven application will be targeted using state-of-the-art methods, frameworks, and tools. The students will construct a working system from scratch, covering the entire data science pipeline — from data collection and preprocessing, exploratory analysis, and feature engineering to building predictive models, evaluating them, and deploying solutions.

Students will participate in all phases a data science project, including early design decisions, data handling, model selection, and system implementation. Example application domains may include healthcare analytics, financial forecasting, recommender systems, natural language processing, image-based data analysis, sustainability, business, engineering, or social sciences, and climate-related data projects.

Through this course, students will gain an in-depth understanding of "data science in practice," as opposed to "data science in theory" or working with toy/articifical datasets.

Language of Intruction: English

It is highly recommended that the student has taken courses in Statistical Learning, Data Mining at Scale: Algorithms and Systems, Advanced Machine Learning, and/or Evolutionary AI and Robotics.

Good programming skills, for example 20 ECTS of programming-focused subjects, are also recommended.

No formal requirements over and above the admission requirements.

After completing this course, the student will have achieved the following learning outcomes, outlined in terms of knowledge, skills, and overall competence.

Knowledge

The student:

• has advanced knowledge of the key stages of a data science project, including data collection, preprocessing, analysis, modelling, and evaluation.
• understands different approaches tohandling real-world datasets, including challenges such as missing data, bias, scalability, and ethical considerations.

Skills

The student can:

• analyze the strengths and weaknesses of various machine learning and statistical modelling techniques for applied data science tasks.
• apply state-of-the-art data science tools and methods to solve complex, real-world data-driven problems.
• develop, validate, and evaluate predictive models using appropriate performance metrics.
• design and implement scalable workflows for managing and processing large datasets.
• effectively visualize, communicate, and interpret the results of data analysis for both technical and non-technical audiences.

General competence

The student:

• can work collaboratively in a project team to design, implement, and deliver a data-driven solution.
• knows how to reflect on ethical, legal, and societal implications of applied data science projects.
• can communicate project outcomes and methodological choices clearly in both written, visual and oral formats.
• can contribute to interdisciplinary projects by applying data science knowledge to domains such as health, business, industry, finance, engineering, or social sciences.

The project will be carried out in groups of 3 to 5 students.

Teaching and supervision will consist of resource lectures, seminars, workshops, and guidance meetings. Students are expected to participate in self-study and group collaboration throughout the course.

The following required coursework must be approved before the student can submit the final Group/Project work and participate in the final oral presentation:

• minimum 80% attendance of workshops
• minimum 80% participation in group supervision
• milestone project deliverables (project plan, dataset description, preliminary analysis).
• mid-term group oral presentation (30 minutes, including presentation and Q&A. All group members must be present at the group presentation and participate in questions and answers.)

The assessment consists of two parts:

1. A final group project report (3 to 5 students) of 10000 to 25000 words + code (50% of the final grade). Both the code/program and the report will be evaluated.
2. A group oral presentation (30 minutes). All group members must be present for this final presentation and participate in delivering the presentation and answering questions. (50% of the final grade)

Both the project report and oral presentation must receive a pass (E grade or above) in order to pass the course.

The oral exam grade cannot be appealed.

The written report grade can be appealed.

New/postponed exam

In case of a failed exam or legal absence, the student may apply for a new or postponed exam. New or postponed exams are offered within a reasonable time span following the regular exam. The student is responsible for registering for a new/postponed exam within the time limits set by OsloMet. The Regulations for new or postponed examinations are available in Regulations relating to studies and examinations at OsloMet.

All aids are permitted, provided the rules for plagiarism and source referencing are complied with.

Grade scale A-F.

Exam part 1 (project report): one internal examiner.

Exam part 2 (oral presentation): two internal examiners.

External examiners are used periodically.