Internet analytics

COM-308 / 6 crédits

Enseignant: Grossglauser Matthias

Langue: Anglais

Summary

Internet analytics is the collection, modeling, and analysis of user data in large-scale online services, such as social networking, e-commerce, search, and advertisement. This class explores a number of the key functions of such online services that have become ubiquitous over the past decade.

Content

The class seeks a balance between foundational but relatively basic material in algorithms, statistics, graph theory and related fields, with real-world applications inspired by the current practice of internet and cloud services.

Specifically, we look at social & information networks, recommender systems, clustering and community detection, search/retrieval/topic models, dimensionality reduction, stream computing, and online ad auctions. Together, these provide a good coverage of the main uses for data mining and analytics applications in social networking, e-commerce, social media, etc.

The course is combination of theoretical materials and weekly laboratory sessions, where we explore several large-scale datasets from the real world. For this, you will work with a dedicated infrastructure based on Hadoop & Apache Spark.

 

Keywords

data mining; machine learning; social networking; map-reduce; hadoop; recommender systems; clustering; community detection; topic models; information retrieval; stream computing; ad auctions

Learning Prerequisites

Required courses

COM-300 Modèles stochastiques pour les communications

Recommended courses

Basic linear algebra

Algorithms & data structures

Important concepts to start the course

Graphs; linear algebra; Markov chains; Python

Learning Outcomes

By the end of the course, the student must be able to:

  • Explore real-world data from online services
  • Develop framework and models for typical data mining problems in online services
  • Analyze the efficiency and effectiveness of these models
  • Data-mining and machine learning techniques to concrete real-world problems

Expected student activities

Lectures with associated homeworks explore the basic models and fundamental concepts. The labs are designed to explore very practical questions based on a number of large-scale real-world datasets we have curated for the class. The labs draw on knowledge acquired in the lectures, but are hands-on and self-contained.

Assessment methods

Project 35%, final exam 65%

Resources

Bibliography

C. Bishop, Pattern Recognition and MachineLearning, Springer, 2006

A. Rajaraman, J. D. Ullman: Mining of Massive Datasets, 2012

M. Chiang: Networked Life, Cambridge, Cambridge, 2012

D. Easley, J. Kleinberg: Networks, Crowds, and Markets, Cambridge, 2010

Ch. D. Manning, P. Raghavan, H. Schütze: Introduction to Information Retrieval, Cambridge, 2008

Ressources en bibliothèque

Moodle Link

Dans les plans d'études

  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Internet analytics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 1 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Internet analytics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 1 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Internet analytics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 1 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Internet analytics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 1 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel

Semaine de référence

Cours connexes

Résultats de graphsearch.epfl.ch.