Data Analytics

SIT717 Enterprise Business Intelligence 2018 T2

Assignment 1 : Survey on Data Mining and/or Machine Learning

This assignment is designed to provide students a good opportunity to read some materials to understand the theory, methods and recent development in the area of business intelligence, especially the modern technologies that are normally used in business intelligence. The typical technologies that are frequently applied in business intelligence come from the data mining and machine learning areas.

In this assignment, you are required to choose one ( Supervised Data Mining

) of the following areas, and write a survey on a topic you have chosen in that area:

1. Time Series or Stream Data Analysis

2. Unsupervised Data Mining

3. Supervised Data Mining

4. Outlier/Anomaly detection

5. Text or Short Text Mining

6. Image or Video Analytics

7. Recommendation or Prediction

8. Others (discussed with unit chair)

[Tasks and Requirements]:

Your survey should meet the following requirements:

(1) Should include the following components:

A. A meaningful title (5-20 words) followed by your name and student ID

The title should comprise at least two aspects: the technique and the purpose, and data type is also required sometime. An example title is "Using Classification Method to Discover Events from Twitter Data".

B. An abstract (100-200 words)

C. An introduction (300-500 words)

D. Body of the Survey (1500 -2000 words)

In this section, you need to cite formal publications/papers that you use, which can include conference proceedings, journal articles, books/book chapters, technical reports, Masters/PhD thesis or any other publications.

You need to clearly state:

 what the paper is about (this could be a theory, an idea, a hypothesis, an assumption, a proposal; it could also be a method, an approach, a technique, an algorithm etc.).

 how it works (technical details).

 how it can be used in business intelligence.

 what is the difference among several methods (this part is most important to differentiate your survey report from average levels and help you write an excellent report). You can provide comparisons of different methods. Identify their different techniques. Identify the advantages and disadvantages of each method. You could state your idea, your opinion, your view, and/or the other people’s view or opinion about the work/method in the paper.

E. Conclusion/Summary (200-300 words)

F. List of Reference ( Harvard are preferred ).

(2) Should be around 3000 words (2500-3500 words) (including references)

(3) You are required to read at least 5 references including lecture notes of this unit.