|
![]() | 2017/8 |
![]() | School of Management |
![]() | 6 [equivalent to 12 CATS credits] |
![]() | 120 |
![]() | Masters UG & PG (FHEQ level 7) |
![]() |
|
![]() | CW 40%, EX 60% |
![]() |
|
![]() |
|
![]() | |
![]() | Aims: This unit covers contemporary statistical and algorithmic methods for cleaning, processing and extracting hidden information and knowledge out of raw data. Learning Outcomes: At the end of this unit, students will be able to: * Choose appropriate algorithms to detect previously unknown rules and patterns within data and infer their business implications * Measure the accuracy and precision of the rules and patterns detected * Identify clusters within multi-dimensional data and classify the members of these classes and the outliers Skills: Intellectual skills: * Develop algorithmic thinking for rule extraction and exception detection (T, F, A) * Enhance perspective of knowledge discovery (T, F, A) Practical skills: * Simplify and convert data for analysis (T, F, A) * Use state-of-the-art data mining software (T, F) Transferable skills: * Improve assessment of the value of knowledge (F) Content: Topics covered include rule extraction, clustering methods, self-organizing maps, support vector machines, neural networks, and outlier detection. |
![]() |
MN50645 is Compulsory on the following programmes:School of Management
|
Notes:
|