Name the chosen data set(s) (from e.g. module resources, UCI ML Repository or other open data sources) and describe the data (e.g. attribute types and values, source of data) and context.

COS7045-B Advanced Machine Learning

Assessment 001: Coursework

Length: Approximately 5,000 words (plus accompanying software/models/scripts)

The aim of this coursework is to critically analyse data sources and data sets, critically evaluate possible data analytics, mining and modelling challenges and solutions, conduct research into relevant academic literature in the subject area, choose, design and implement machine learning and data mining algorithms to the chosen data, and apply the chosen techniques to a specific case study with a defined research question. The coursework is worth 100 marks, and the distribution of marks is detailed in the marking scheme.

The coursework requires electronic submission of a report documenting solutions to the tasks below in .pdf or Microsoft Word format, and all software files generated to solve the tasks, with informative file names preferably linked to the tasks they are related to, should be submitted using Canvas following instructions made available on the VLE.

You are expected to select a data set (or several for data integration applications) of your choice from open machine learning/data mining (re)sources, to develop a case study and apply relevant analysis, mining and learning techniques on the data set(s) for supervised and/or unsupervised learning, as motivated and decided by which is suitable depending on the data set characteristics and chosen research questions. The tasks below indicate expected outputs and relative marks per task:

Task A. [20 marks] Data choice, relevant literature and research question

Name the chosen data set(s) (from e.g. module resources, UCI ML Repository or other open data sources) and describe the data (e.g. attribute types and values, source of data) and context.

[5 marks]

Present a brief but focussed review of relevant academic literature in topics relevant to the chosen dataset (previous work on the dataset, or papers presenting results on similar or related data) and present key findings and recommendations extracted from the research.

[10 marks]

Introduce the specific research question(s) related to the problem, with specific reference to the dataset(s) and the expected or proposed outcome of the work upon completion.

[5 marks]

Task B. [20 marks] Data Analysis

Apply descriptive statistical techniques suitable for the chosen task. Details of contextual programming and usage of graphical representation and analysis of data are expected. For example, sort the data by class, line or bar plot each of the features individually if applicable; for each feature compute characteristics like its minimum, maximum, mean, mode and standard deviation, and study the correlation between features for each class or the distance matrix.

 [10 marks]

Analyse and discuss results of statistical analysis and other contextual analysis of the data. Identify key outcomes and actions from the analysis task that will support the practical work towards the identified research question for the chosen dataset.

 [10 marks]

Task C. [40 marks] Practical work and results

Describe and justify choices for practical application of algorithms, tools and processes for the chosen supervised/unsupervised challenge identified through the research question and research into literature conducted.

[10 marks]

Develop and document practical solutions, with reference to supporting files/scripts/models as appropriate. Describe the (pre-)processing steps, classification/regression/clustering/mining steps and evaluation techniques (e.g. training and testing set choices, clustering evaluation methods, rule assessment metrics or others) used to produce results for answering the research question. Parameter choices and testing described.

[20 marks]

Present and discuss results from the practical work, including appropriate visualisations of models, clusters, rules etc. as necessary. Discuss and evaluate the results including any comparisons to benchmark datasets and research literature.

[10 marks]

Task D. [20 marks] Critical Review

Describe difficulties using the tools/techniques as above. Provide reflections focused on technical, interpretational and functional issues, and the steps/approach you took to overcome these challenges.

[5 marks]

Document your observations on the case study, practical work and results. Present conclusions deduced/induced from each result. Describe and explain which techniques were most helpful to evaluate, explore and analyse the dataset. Describe how techniques were compared. Document techniques/activities that you could/should perform in the future to continue this work.

[10 marks]

Discuss the results of the case study you developed and any interesting observations by comparing them with published academic sources.

[5 marks]

COS7045-B Advanced Machine Learning