Data Mining and Machine Learning COMP 3027J
ASSIGNMENT 1
Weight: 40%
Submissions: A report (PDF), and a zip file (including code and datasets) on Brightspace.
The purpose of this assignment is to practice how to use data mining and machine learning to
solve real-world problems. You will need to identify the target problem yourself. You can
choose any project, but it must be a classification task and includes visual analytics in the
report. (Note: Do not related to or use the dataset in Assignment 2; Do not related to your
FYP project.) as long as it is legal. This assignment is a group project, and each group should
have four members. Each group only needs to submit one solution.
Your pdf report should clearly detail how you carried out the experiment to address your
targeted problem and show the results you got.
1. Your report should be written in Overleaf, and use the provided template:
https://www.overleaf.com/latex/templates/acm-journals-primary-articletemplate/cpkjqttwbshg.
2. It should be a human-readable document (e.g. do not include code)
3. The final report is expected to be 4-6 pages including references.
4. You should provide your UCD student number instead of institution in the provided
template.
5. Use clear headings for each section.
6. Include tables and figures if needed appropriately, such as giving captions, describing
your figures or analysing the results provided in your tables in your text etc.
7. The final report filename should be “Comp3027J_GroupXX” (e.g.
Comp3027J_Group01)
In your report, it is recommended to discuss the following essential topics, but not limited to
these topics:
1. What is the real-world problem addressed and why it is important.
2. Dataset selection (collection) and Data pre-processing.
Where you find your data (or how do you collect the data and create your dataset)?
How do you analyze your data?
how to pre-process your data to fit your solution?
Any challenges with your dataset?
etc.
3. Methodology
Any machine learning algorithm can be used (not limited to the algorithm we have
learned).
Creativity is encouraged.
Be careful, a sophisticated approach with little description and explanation will
receive little credit.
4. Evaluation
Elaborate your experiment, such as splitting dataset, K-fold;
Compare your solution with benchmarks in literature;
Evaluation metrics for your task;
Analysing your results etc.
You should submit a pdf file and a zip file. In your zip file, you should include your code and
dataset. Please make sure to clean up your code to make the results reproducible. If its size
exceeds the Brightspace limit, it needs to be submitted via a USB key. Note your pdf report
must be submitted as an individual file, which should not be compressed into the zip file.
There will be an interview at the end of the term, and you will be asked about the methodology
adopted.
2
• Grading
Problem Literature Methodolgy Evaluation Code+Reproducibility
5% 5% 15% 10% 5%
請加QQ：99515681 郵箱：
[email protected] WX：codinghelp
