Business Statistics
A.Y. 2019/2020
Learning objectives
The course of Business Statistics aims to provide the knowledge of the main Data Mining techniques addressed to the analysis of business data. Indeed, the increasing availability of data, typically generated by the information society, has brought out the need to deal with methodologies and tools for the quantitative decision-making processes in economic and business applications. Data may have source within the firm, such as those related to customers or users, or may derive from appropriate market researches. The presence of data of different nature (i.e., both qualitative and quantitative) requires that the student achieves suitable skills which allow him to justify the logical process underlying the adoption of a specific technical analysis, to formulate a reasoning in a critical and rigorous way and to detect the synthetic information to support decisions especially in the risk management process.The skills achieved in the course of Business Statistics will be useful for the courses whose main issues are related to marketing, market research and decision-making processes.
Expected learning outcomes
At the end of the course the student will have achieved the skills for the theoretical and practical formalization of the Data Mining techniques presented along the course. In particular, the student will be able to: recognize the differences between supervised methods, non-supervised methods, descriptive models and predictive models; demonstrate an adequate ability to choose the most suitable model based on the features of the available data and the purpose of the analysis to be led; select, among several models, the model characterized by the greatest predictive accuracy; implement the models using the programming language of the statistical R software; correctly interpret the analysis outputs by extracting information that can support the decision-making processes.
Lesson period: Second trimester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Lesson period
Second trimester
Course syllabus
The topics of the Business Statistics course are mainly focused on:
· the introduction of the Data Mining features and R software;
· the illustration of the Market Basket Analysis technique through the implementation of the association and link analysis rules (e.g., for the analysis of a consumer's shopping cart);
· the introduction of sequential rules (e.g., for making predictions on the patterns of visits to an e-commerce site);
· the illustration of the cluster analysis as a methodology to proceed with grouping and segmentation analysis (e.g., identification of different customer profiles);
· the illustration of the logistic regression models and decision trees (e.g., for assessing the customer churn risk);
· the introduction to the survival analysis technique (e.g., for forecasts on loyalty behavior and churn of customers).
· the introduction of the Data Mining features and R software;
· the illustration of the Market Basket Analysis technique through the implementation of the association and link analysis rules (e.g., for the analysis of a consumer's shopping cart);
· the introduction of sequential rules (e.g., for making predictions on the patterns of visits to an e-commerce site);
· the illustration of the cluster analysis as a methodology to proceed with grouping and segmentation analysis (e.g., identification of different customer profiles);
· the illustration of the logistic regression models and decision trees (e.g., for assessing the customer churn risk);
· the introduction to the survival analysis technique (e.g., for forecasts on loyalty behavior and churn of customers).
Prerequisites for admission
In order to adequately understand the contents of the course, the students must have basic knowledges in Statistics and Mathematics.
Teaching methods
The course will be organized through lectures with support tools consisting in the employment of the overhead projector, through which the mathematical passages underlying the Data Mining models and methodologies will be illustrated, and of the teacher's laptop, through which the slides of the course topics will be shown. Students will also have to bring their personal laptop in order to replicate the implementation of the Data Mining models and techniques in R.
Teaching Resources
The main reference books for the preparation of the exam are indicated below.
Main reference text with theoretical and descriptive contents of the Data Mining techniques:
· Giudici P., Metodi informatici, statistici e applicazioni, 2° Edizione, McGraw-Hill (2005).
An English version is available online:
· Giudici P., Figini S., Applied data mining for business and industry, Second Edition, Wiley (2009), available at the link
https://epdf.tips/applied-data-mining-for-business-and-industry-2nd-edition.html.
More reference books for further information on some Data Mining techniques are:
· De Lillo A., Argentin G., Lucchini M., Sarti S., Terraneo M., Analisi multivariata per le scienze sociali, Pearson EDUCATION (2007) - Topics: logistic regression (important integration with respect to what is described in the textbook "Metodi informatici, statistici e applicazioni, 2° Edizione, McGraw-Hill (2005)"), Cluster Analysis.
· Cerioli A., Zani S., Analisi dei dati e Data Mining per le decisioni aziendali, Giuffré Editore (2007) - Topics: Cluster Analysis and Decision Trees (Classification Trees).
Some possible reference books for the use of R are:
· Ieva F., Masci C., Paganoni A.M., Laboratorio di Statistica con R, II Edizione, Pearson (2016).
· Coccarda R., Frascati F., Manuale interattivo di Statistica con R, Pearson (2015).
· Iacus S. M., Masarotto G., Laboratorio di Statistica con R, II Edizione, McGraw-Hill (2007).
· Kabacoff R.I., R IN ACTION: Data analsis and graphics with R, available at the link http://kek.ksu.ru/eos/DataMining/1379968983.pdf.
Main reference text with theoretical and descriptive contents of the Data Mining techniques:
· Giudici P., Metodi informatici, statistici e applicazioni, 2° Edizione, McGraw-Hill (2005).
An English version is available online:
· Giudici P., Figini S., Applied data mining for business and industry, Second Edition, Wiley (2009), available at the link
https://epdf.tips/applied-data-mining-for-business-and-industry-2nd-edition.html.
More reference books for further information on some Data Mining techniques are:
· De Lillo A., Argentin G., Lucchini M., Sarti S., Terraneo M., Analisi multivariata per le scienze sociali, Pearson EDUCATION (2007) - Topics: logistic regression (important integration with respect to what is described in the textbook "Metodi informatici, statistici e applicazioni, 2° Edizione, McGraw-Hill (2005)"), Cluster Analysis.
· Cerioli A., Zani S., Analisi dei dati e Data Mining per le decisioni aziendali, Giuffré Editore (2007) - Topics: Cluster Analysis and Decision Trees (Classification Trees).
Some possible reference books for the use of R are:
· Ieva F., Masci C., Paganoni A.M., Laboratorio di Statistica con R, II Edizione, Pearson (2016).
· Coccarda R., Frascati F., Manuale interattivo di Statistica con R, Pearson (2015).
· Iacus S. M., Masarotto G., Laboratorio di Statistica con R, II Edizione, McGraw-Hill (2007).
· Kabacoff R.I., R IN ACTION: Data analsis and graphics with R, available at the link http://kek.ksu.ru/eos/DataMining/1379968983.pdf.
Assessment methods and Criteria
The exam consists of a written test structured in two parts. The first part includes two theoretical questions on the Data Mining techniques illustrated along the course. The second part is devoted to the interpretation of an R output related to the implementation of a specific Data Mining methodology. The exam is completed also by a set of assignments provided along the lectures and concerning the analysis of datasets through the implementation in R of the most appropriate Data Mining techniques.
The structure of the exam will allow to evaluate the student's knowledge on the theoretical aspects of the Data Mining methods, the capability of interpreting the related results and the expertise achieved in the use of the statistical R software language.
The structure of the exam will allow to evaluate the student's knowledge on the theoretical aspects of the Data Mining methods, the capability of interpreting the related results and the expertise achieved in the use of the statistical R software language.
SECS-S/03 - ECONOMIC STATISTICS - University credits: 6
Lessons: 40 hours
Professor:
Raffinetti Emanuela
Shifts:
-
Professor:
Raffinetti Emanuela