Dipartimento di InformaticaUniversità degli Studi di Milano
Dario Malchiodi

Big scale analytics2014/15

MSc in Computer science · University of Milan · Lectures are in Italian · 6 credits · 48 hours

Archived edition: this page is kept for reference, and some materials or links may no longer be available.

This course introduces the principal techniques related to the analysis of large amounts of data.

News

  1. Office hours of May 28th canceled

    The office hours of May 28th are canceled; students can arrange an appointment via e-mail.

  2. Office hours of April 2nd canceled

    The office hours of April 2nd are canceled; students can arrange an appointment via e-mail.

  3. Office hours rescheduled on 12/3

    Office hours of today will start at 16:00.

  4. Office hours for the spring semester

    Office hours for the spring semester will be on Thursday at 14:30 in the teacher's office, starting from 5/3.

  5. Office hours canceled

    Regular office hour are canceled until next semester; students can arrange an appointment via e-mail.

  6. Office hours rescheduled on 25/11

    Office hours of today will last until 15:00; students can arrange an appointment via e-mail.

  7. Tutorial about MapReduce in AWS

    I published a tutorial about running JAR-encoded MapReduce jobs in AWS.

  8. AWS in Education grant for the Big scale analytics course

    Students enrolled in the course of Big scale analytics may benefit by a grant of 100US$ to access to the tools provided by Amazon Web Services.

  9. Tutorial about Hadoop installation

    I published an updated tutorial about installing Hadoop on a virtual machine.

  10. Office hours for the fall semester

    Office hours for the fall semester will be on Tuesday at 14:30 in the teacher's office, starting from 9/9.

Course schedule

Lectures will take place at the Computer science department, according to the following tentative schedule:

Day Hour Place
Tuesday 16:30 - 18:30 aula 5
Thursday 15:30 - 17:30 aula 5

Any change to the schedule will be announced in class and published in paragraph News of this page.

Office hours

By appointment, room 5015 of the Computer Science Department. It is possible contact the teacher by e-mail, taking care to read in advance the guide prepared by Prof. Sebastiano Vigna and clearly specifying in the message the course name and the academic year. In particular, students are encouraged to always use their academic address (i.e. based on the domain studenti.unimi.it) signing with name and student ID number and recalling that the response time may vary depending on the teacher commitments.

Course material

The course is based on the following textbook: Anand Rajaraman and Jeff Ullman, Mining of Massive Datasets, available both as a freely downloadable PDF and published in hardcopy by Cambridge University Press (ISBN:9781107015357)

The part on distributed file systems and MapReduce is based on the adopted textbook and on the Hadoop tutorial published by Yahoo!

Students enrolled in this course may benefit of a 100US$ credit to use the tools provided by Amazon Web Services.

The part on machine learning is described on the additional chapter of the textbook available online, in the third chapter of S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, 1999 (ISBN 0-13-908385-5) and in two online tutorials about classification and regression.

The part on dimensionality reduction is described on the additional chapter of the textbook available online.

Syllabus

The course explains the topics listed in the lecture calendar, covering the textbook contents in chapters 1, 2 (until section 2.6.2 included), 3 (until section 3.7 included), 4 (until section 4.5 included), 5 (excluding sections 5.2.4 and 5.2.5), 6 (until section 6.5.1 included), 7 (until section 7.5 included), 8 (until section 8.4.6 included), 9 (until section 9.4 included), 10 (sections 10.1, 10.2, 10.4, and 10.5), 11 (until section 11.3 included) and 12 (until section 12.3 included), as well as the contents of the remaining documents listed in Course material.

Lectures calendar

Lecture Date Topic Material
L01 30/09/2014 Introduction to data mining
    L02 02/10/2014 Large-scale file systems and Hadoop
    L03 07/10/2014 Map-reduce algorithms
      L04 09/10/2014 Map-reduce and Hadoop
      L05 14/10/2014 Analysis of map-reduce algorithms
        L06 16/10/2014 noSQL
        L07 21/10/2014 Finding similar items
          L08 23/10/2014 Finding similar items
            L09 28/10/2014 Mining data streams
              L10 30/10/2014 Link analysis
                L11 04/11/2014 Link analysis
                  L12 06/11/2014 Frequent itemsets
                    L13 11/11/2014 Frequent itemsets
                      L14 13/11/2014 Amazon Web Services: S3, EC2, and EMR
                        L15 18/11/2014 Frequent itemsets
                          L16 20/11/2014 Web advertising
                            L17 25/11/2014 Clustering
                              L18 27/11/2014 Clustering
                                L19 02/12/2014 Recommendation systems
                                  L20 04/12/2014 Recommendation systems
                                    L21 09/12/2014 Perceptrons
                                      L22 11/12/2014 Support vector classification
                                        L23 16/12/2014 Dimensionality reduction
                                          L24 18/12/2014 Social networks analysis

                                            Exam modalities

                                            The exam consists in an oral test, by appointment.