You are on page 1of 2

Lahore University of Management Sciences

CS 5312 Big Data Analytics


Spring 2017

Instructor Imdadullah Khan


Room No. 9-G10A, CS Dept., SBA-SSE Building
Office Hours
Email imdad.khan@lums.edu.pk
Telephone 8198
Secretary/TA Zulfiqar N Malik
TA Office Hours
Course URL (if any)

Course Basics
Credit Hours
Lecture(s) Nbr of Lec(s) Per Week 2 (WF) Duration 75 Minutes each (4:30-5:45)
Recitation/Lab (per week) Nbr of Lec(s) Per Week 0 Duration
Tutorial (per week) Nbr of Lec(s) Per Week 0 Duration

Course Distribution
Core No
Elective Yes
Open for Student Category Senior/Graduate
Closed for Student Category

COURSE DESCRIPTION

With the explosion of unstructured data in quantities that dont allow usual statistical techniques. New techniques are needed to analyze such
data. New algorithms are needed to be able to deal with distributed approaches in order to be responsive. New methods to store and retrieve
data are needed.
Many of the algorithms originate from well-known owners of big data like Google (search, ad-words), Amazon (similar books recommendations),
and Facebook (social network analysis). As more players enter the arena, new needs will drive new methods. As this is a field in its infancy, while
we look at these specific problems, we formulate general rules.

COURSE PREREQUISITE(S)

Data Structures, Algorithms,


Discrete Math,
Probability
Databases and Linear Algebra (useful, not required)

COURSE OBJECTIVES

To develop the ability to understand and implement analysis of large data sets.

Learning Outcomes

Presented with data, the student should be able to:


Appreciate the strengths and weaknesses of different solutions,
Select the appropriate statistical tool and algorithm
To understand and convey the result generated by the algorithm, as well the assumptions and limitations of the methods.
Lahore University of Management Sciences
Grading Breakup and Policy

Homework Assignments: 20%


Quizzes, Attendance and class participation: 20%
Project: 60%

Examination Detail

Yes/No: No
Combine Separate: -
Midterm
Duration: -
Exam
Preferred Date: -
Exam Specifications:

Yes/No: No
Combine Separate: -
Final Exam
Duration: -
Exam Specifications: -

COURSE OVERVIEW
Week/
Recommended Objectives/
Lecture/ Topics
Readings Application
Module
1 Basics Data Concepts Ch. 1, MMDS
2
3 Finding Similar Items Ch. 3
4
5 Streaming Data Ch. 4
6 Link Analysis (PageRank) Ch. 5
7
8 Clustering Ch. 7
9
10 Recommendation Systems Ch. 9
11
12 Social Networks Ch. 10
13 Dimensionality Reduction Ch. 11
14

Textbook(s)/Supplementary Readings

Mining of Massive Datasets by Jure Leskovec, Anand Rajaraman, Jeffrey D. Ullman


http://infolab.stanford.edu/~ullman/mmds/book.pdf

The textbook will be supplemented with other readings

You might also like