BUSINES INTELLIGENCE

&
ANALYTICS
(MS6840)

Introduction
Saji K Mathew, PhD
Professor, Department of Management Studies
INDIAN INSTITUTE OF TECHNOLOGY MADRAS
Acquisitions in the digital world
 Patterns in large volumes of data

Travel from UK, 1998-2008 (Chris Anderson, http://www.longtail.com)

 The Long Tail

Source: Brynjolfsson, Hu, and Smith, “Consumer Surplus in the Digital Economy,” Management
Science, November 2003.
Product variety comparison: Online vs
brick and mortar
Drivers of data mining
} ICT in industry and society
} Rise of transaction processing systems/ERPs
} Internet commerce
} Social media
} Technological progress
} Storage power and technologies
} Computing power
} Data mining technologies
} Rise of service industry
} Customer orientation
Vocabulary
} Data warehousing
} Data marts
} Databases
} ETL
} Big data, data engineering
and then
} Data mining
} Knowledge discovery in databases (KDD)
} OLAP
} Analytics
} Advanced analytics
} DSS
} Business Intelligence,..data science
The dark side
Course Philosophy
Some companies have built their very businesses on
their ability to collect, analyze and act on data. Every
company can learn from what these companies do.
--Thomas Davenport, Competing on Analytics, HBR Jan 2006

The use of management science tools and models

represents the future of best-practices for tomorrow’s
successful companies. When used wisely, these models
and tools have enormous power to enhance the
competitiveness of almost any company or enterprise.
It is therefore imperative that tomorrow’s business
leaders be well-versed in the modeling techniques and
also in the software skills to develop and use the
models.
-- Freund, R. and Wang Y., MIT Sloan School of Management, 2003.
 Course objectives

} Introduce business intelligence architecture and its

components covering databases, data warehouse,
OLAP and data mining in business context
} Learn to convert business problems into data mining
problems and thus understand data mining process.
} Explore data mining algorithms for classification,
prediction and text data mining along with applications
in business domains
} Develop skills for using data mining software tools to
solve business problems.
Pedagogy
} The course will be conducted through classroom
lectures, lab sessions, exercises, quizzes, assignment
discussions/presentations and mini projects.
} Small groups of students will be formed in the
beginning of the course.The team projects will be
based on business problems involving modeling,
selected from various domains depending on the
interest/experience/ambitions of the teams. The
teams will also work on brief analytical presentations
of research papers, BI applications in organizations,
news analysis etc.
 Evaluation
} Written examinations (individual) 35%
} Project work (group) 35%
} Assignments (group) 30%
Text books
Datamining
in practice
Reference books
 Teaching Assistant

Krutheeka Jayendiran, Research Scholar

DoMS, IIT Madras
Visiting Scholar, University of Passau, Germany
Email: krutheekab@gmail.com