DATA ANALYSIS FOR BUSINESS

DATA ANALYSIS FOR BUSINESS

Matteo Iacopini

Instructional goals

This course shows how to help organizations collect, analyze, store and interpret large-scale data in order to develop informed business strategies, by providing a framework to improve students' understanding of data analytics, and enhance their critical thinking and decision making. In particular, students will acquire skills to recognize business problems, gain an understanding of data collection techniques and principles of data analysis, learn how to take data from the technical domain, bridge the data gap between the technical domain and business analysts, analyze and present valuable findings and recommend action to business leaders.

Intended learning outcomes

1) Knowledge and understanding. The course will present the tools to collect, organize, model and process data from both a theoretical and practical point of view. Concerning this last point, during the course an extensive use of software tools will be made. 2) Applying knowledge and understanding. The students are expected to use the tools presented during the course to deal with data coming from several fields. On one hand they should be able to process the data to obtain useful information. On the other hand they should be able to present their findings and to address business decisions. To develop and evaluate these skills, students will be offered several practical lab sessions and will be asked to work on project assignments. 3) Making judgements. Students are expected to be able to identify the problem they need to face and define it properly. Students should be able to decide which models are the most suitable to deal with the defined problem and how to use them to identify and process useful data. 4) Communications Skills. The students are expected to be able to organize and present their findings in a clear way. They should be be able to understand the language and the tools of the technical domain and should be able to provide recommendations supported by quantitative results. 5) Learning skills. The course is intended to give the students the tools to cope with “real world” scenarios. After the course they should have improved their critical spirit and become more independent in approaching problems. They should be able to support their arguments with evidence based on data and mathematical models.

Course Contents

The course will focus on collection, exploration, analysis and visualization of data, and presentation of results with and hands on approach. Emphasis will be given to applications. During the course the R programming language will be presented and extensively used.

Reference Books

Jank W. (2011) Exploring and Discovering Data. In: Business Analytics for Managers. Use R. Springer, New York, NY James, Witten, Hastie, Tibshirani (2017) An Introduction to Statistical Learning with Applications in R. Springer Verlag.

Teaching Methods

On-campus classes and Lab sessions, with a mixed-use of presentations, e-board and statistical software

Assessment Method

Assessment will constitute of a mixture of: - Individual continuous assessments (e.g. quiz) - Midterm group project - Final Theory Exam

Thesis assignment criteria

Interview with candidate

Week 1

- Overview of the course (bureaucracy, resources, exams) - Introduction to Data Analysis and Statistical Learning - Introduction to R

Week 2

- Data structures and statistical learning problems - Data pre-processing - Practical session with R

Week 3

- Linear regression: simple, multiple, and multivariate - Practical session with R

Week 4

- Linear regression: simple, multiple, and multivariate - Practical session with R

Week 5

- Logistic regression: classification - Practical session with R

Week 6

- Classification vs Clustering - Practical session with R

Week 7

- Model evaluation and Resampling methods: cross-validation, bootstrap - Practical session with R

Week 8

- Model evaluation and Resampling methods: cross-validation, bootstrap - Practical session with R

Week 9

- Model selection and regularization - Practical sessions with R

Week 10

- Model selection and regularization - Tuning of the model - Practical sessions with R

Week 11

- Non-linear methods - Practical sessions with R

Week 12

- Tree-based methods - Practical sessions with R