DIGITAL MARKETING AND CUSTOMER ANALYTICS
- Anno accademico
- 2022/2023 Programmi anni precedenti
- Titolo corso in inglese
- DIGITAL MARKETING AND CUSTOMER ANALYTICS
- Codice insegnamento
- EM1412 (AF:358755 AR:188842)
- Lingua di insegnamento
- Inglese
- Modalità
- In presenza
- Crediti formativi universitari
- 6
- Livello laurea
- Laurea magistrale (DM270)
- Settore scientifico disciplinare
- SECS-P/08
- Periodo
- 1° Periodo
- Anno corso
- 2
- Sede
- VENEZIA
- Spazio Moodle
- Link allo spazio del corso
Inquadramento dell'insegnamento nel percorso del corso di studio
The module's objective is to understand the challenges of digital marketing by focusing on the application of data analytics to contemporary marketing practice. Lessons will match marketing theory with marketing problems and machine learning and statistical models. Students are actively involved in hands-on coding exercises to develop solutions using data analytics techniques.
Risultati di apprendimento attesi
Learning outcomes include:
- the impact of digital technologies on marketing;
- the challenges of digital marketing;
- the choice between of prediction and causality;
- the choice between supervised and unsupervised learning algorithms;
- the application of data analytics to marketing intelligence: marketing campaigning, advanced profiling, anti-churn
- the impact of digital technologies on marketing;
- the challenges of digital marketing;
- the choice between of prediction and causality;
- the choice between supervised and unsupervised learning algorithms;
- the application of data analytics to marketing intelligence: marketing campaigning, advanced profiling, anti-churn
Prerequisiti
Statistics and basic coding in R
Contenuti
The course will cover the following topics:
- digital technologies in marketing;
- CRM and consumer behaviour;
- marketing analytics;
- predictive modeling vs. causal modeling;
- supervised vs unsupervised machine learning;
- customer segmentation, marketing campaigning, attrition.
- digital technologies in marketing;
- CRM and consumer behaviour;
- marketing analytics;
- predictive modeling vs. causal modeling;
- supervised vs unsupervised machine learning;
- customer segmentation, marketing campaigning, attrition.
Testi di riferimento
A reading list of papers will be provided on the moodle platform.
Modalità di verifica dell'apprendimento
Attending students: submission of a project based on real data (70%) individual exam with 1 question out of 3 (30%)
Exam for not-attening students is written and includes 3 questions and an empirical exercise in R.
Exam for not-attening students is written and includes 3 questions and an empirical exercise in R.
Modalità di esame
scritto
Metodi didattici
Theoretical lessons; case studies; exercises in RStudio
Programma definitivo.
Data ultima modifica programma: 19/06/2022