About the project
The examination task in this course is a machine learning project where you collect and process data, and use a suitable machine learning algorithm on that data.
Note that there will be no project presentations and the reports will not be published anywhere. It is only the course examiner that will read your report and look at your code. The reason for this is that some of you will most likely work with data that you don’t want to be shared with people outside the company.
Step 1: Collecting data
- Find some data, preferably from your work place, that you can use for some data mining task
- If you can’t find useful data, you can generate data by scraping websites or use datasets available online
- Discuss with your teacher if the data you have selected is suitable
Step 2: Data processing
- Transform your data into a suitable format, for example CVS or ARFF
- You might also need to pre-process your data for it to be suitable for machine learning algorithms
Step 3: Applying machine learning on the data
- Select and apply a suitable machine learning algorithm for classification or regression on your data
- Gather suitable performance metrics, for example accuracy and training time
Step 4: Write technical report
- Write a technical report where you:
- Describe your data and how it was gathered
- Describe the pre-processing if you used any
- Describe and motivate your choice of machine learning algorithm
- Present and discuss the results
- Discuss what your machine learning system can be used for
You shall submit a short (1-2 pages) description of your project. Describe the data you plan to work with and how you plan to approach the problem.
You shall submit the project files and a technical report describing the project, how you approached the problem and your findings.