Teaching‎ > ‎

Data Mining Technology for Business and Society

Master's Degree in Data Science
Data Mining Technology for Business and Society
Academic year 2020/2021

- Instructor: 

  Prof. Stefano Leonardi 
  leonardi -- at -- diag.uniroma1.it

- Tutor and Laboratory:

  PhD Adriano Fazzone 
  fazzone -- at. -- diag.uniroma1.it


Schedule: 

Tuesday, 08:00 - 10:00, Room 15 - DSS, Piazzale Aldo Moro 5
Thursday, 15:00 - 19:00, Room 15 - DSS, Piazzale Aldo Moro 5

For meeting the instructors arrange an appointment by email 


Program of the course:

The course will cover the following topics with lessons, laboratory and seminars from experts of specific applications. 

Section I – Search Engine Technology

Boolean queries, Document Ranking and vectorial model
Recall e Precision e valutazione delle prestazione di un SE
Search Engine Technologies - Crawling
Locality - Sensitive Hashing e Duplicate detection 
Link-analysis ranking: HITS, Personalized PageRank and Salsa

Section II – Recommender Systems 

Content-based Recommendation
Collaborative Filtering
Graph-based Recommendation
Matrix factorization
Dimensionality reduction
Singular Value Decomposition - Principal Component Analysis - LSI
Graph-based Recommendation
Multi-armed bandit and personalization

Section III – Classification and Learning

Text Classification
kNN
Naive Bayes
SVM

Section IV 
Dr. Giorgio Barnabò e Federico Siciliano

Machine Learning and NLP technology for  
detecting and demoting misinformation on the Web

Section V – Applications 

Computational Advertising


More details at the Piazza site. 

Exam:

There are two possibilities for the exam: 

i) Deliver three homeworks assigned during the term and show good knowledge of the 
topics of the course during an oral exam of discussion of the homeworks (Highly Recommended)
ii) Deliver a project assigned by the instructor and take a written exam 

More details will be given during the class.

References

Ref 1. Christopher D. Manning, Prabhakar Raghavan,  Henrich Schueze Introduction to Information Retrieval, Cambridge University Press, 2008 

Ref 2. J. Leskovec, A. Rajaraman, and J. Ullman, Mining of Massive Datasets, Cambridge University Press. 

A textbook reference on algorithm design for Master students: 

Ref 3. J. Kleinberg and E. Tardos. Algorithm Design. Pearson Education (Paperback), 2013. 
Comments