Prof Qiwei Yao Col.7.16

This course is available on the BSc in Accounting and Finance. This course is available as an outside option to students on other programmes where regulations permit. This course is available with permission to General Course students.

This course is available as an outside option to the students who are interested in data analytics and who have statistical background at least equivalent to ST107 or ST108. No prior knowledge in programming is required.

This course is capped at 60 for the 2018/19 session. 

Students must have completed a statistical course at least equivalent to Quantitative Methods (Statistics) (ST107) or Statistical Methods for the Social Sciences (ST108).

The primary focus of this course is to help students view various problems from business, economy/finance, and social domains from a data perspective and understand the principles of extracting useful information and knowledge from data. Students will also gain the hands-on experience using R -- a programming language and software environment for data analysis and visualisation. Learning basic data analytic methods and techniques is combined with real-life examples. 

The core contents of the course include data cleansing, data transformation, data visualisation, R-programming,  classification, regression, clustering, over-fitting avoidance and model evaluation. The course also covers a subset of the following topics: illustration of R-access of databases and big data platforms,  illustration of parallel computing in R, similarity matching, market-basket analysis, link prediction, text mining, network analysis, causal modelling. 

This is not a course on algorithms and IT technologies required for handling massive data, which deserve separate courses. The focus is on the fundamental principles and concepts of data analytics or data science. It becomes ever-increasingly important in this information age to gain adequate understanding of data science even if one never intends to apply it oneself.

20 hours of lectures, 5 hours of seminars and 5 hours of computer workshops in the MT.

Students are encouraged to install R in their own laptops, and to use their own laptops in the workshops.

Students will be expected to produce 5 exercises and 5 other pieces of coursework in the MT.

Five sets of work on data analysis using R are for Weeks 1, 3, 5, 8 and 10. Five sets of exercise are for Weeks 2, 4, 7, 9 and 11.

Wickham, H, and Grolemund, G. (2017). R for Data Science. O'Reilly. Available online at http://r4ds.had.co.nz

James, G., Witten, D., Hastie, T. and Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R. Springer. Available online at http://www-bcf.usc.edu/~gareth/ISL

Provost, F. and Fawcett, T. (2013). Data Science for Business. O'Reilly. 

Zuur, A., Ieno, E. and Meesters, E. (2009). A Beginner’s Guide to R. Springer. Available online from LSE Library.

Hastie, T., Tibshirani, R and Friedman, R. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd Edition. Springer. Available online at https://web.stanford.edu/~hastie/Papers/ESLII.pdf

Silge, J. and Robinson, D. (2017). Text Mining with R: a tidy approach. O’Reilly. Available online at https://www.tidytextmining.com

Wickham, H. (2016). ggplot2: Elegant Graphics for Data Analysis. Springer. Available online at http://moderngraphics11.pbworks.com/f/ggplot2-Book09hWickham.pdf

Coursework (30%) in the MT.
Project (70%) in the LT.

The project will be a group project with maximum 3 members per group. The detailed instruction will be handed out in Week 5 of Michaelmas term, and students need to submit a written report by Week 2 of Lent term.

Students are required to hand in the solutions for 2 sets of exercises (5% each) and 2 sets of data analysis using R (10% each).