MGT 3213

Management
Information Systems
Dr. A. Rukshan
Senior Lecturer in IT
Dept of Management and Entrepreneurship
Faculty of Business Studies
University of Vavuniya
 The Database Approach to
Data Management: Artificial
Intelligence (AI) and Machine
Learning (ML)
Evolution of Database Technology
Stream data management and
RDBMS, advanced data
mining
models (extended-relational,
OO, deductive, etc.) Data mining and its
Data collection, database applications
Application-oriented DBMS
creation, IMS and (spatial, scientific, Web technology (XML, data
network DBMS engineering, etc.) integration) and global
information systems.

1970s 1990s 2020

1960s 1980s 2000s

Relational data model, Data mining, data

relational DBMS warehousing, multimedia AI technology
implementation databases, and Web
databases
Why Not Traditional Data Analysis?
• Tremendous amount of data
• Algorithms must be highly scalable to handle such as tera-bytes of data
• High-dimensionality of data
• Micro-array may have tens of thousands of dimensions
• High complexity of data
• Data streams and sensor data
• Time-series data, temporal data, sequence data
• Structure data, graphs, social networks and multi-linked data
• Heterogeneous databases and legacy databases
• Spatial, spatiotemporal, multimedia, text and Web data
• Software programs, scientific simulations
• New and sophisticated applications
 Artificial Intelligence
(AI) and Machine
Learning (ML)
• Artificial Intelligence (AI):
• Artificial Intelligence is the
simulation of human
intelligence processes by
machines, especially
computer systems.
• It enables systems to
perform tasks that typically
require human intelligence,
such as reasoning, problem-
solving, understanding
natural language, and
learning from experience.
Relations
between AI,
Machine
Learning, Neural
Network, and
Deep Learning
What is Machine Learning
• Machine learning is the field of study
that focuses on computer systems
that can learn from data
• Machine learning trains the
machines to learn specific tasks
without being explicitly programmed
(allow computers learn from data)
• So, computers are going to learn
from themselves like hums are doing.
So the machine itself will identify with the data and
discover pattern.
They can learn how to label pictures by different animals
with different label
It identifies important features to identify lables
The important think is the picture is not necessarily a data that you provided previously to
the machine to learn.
Machine
Learning Vs.
Classical
Programming
Computer itself
(What is expect
learn the model and
the output)
give the model
which is like a
program that we
want
 Theoretical knowledge

Machine
Learning is an
inter disciplinary
field

• Domain Knowledge - Understand the Application,

where are you going to apply the machine
learning model.
• Knowledge about the application
• Data related to the application
• After getting the outcomes, how the outcomes will be used
ML Applications in
Business

• Credit card fraud detection –

• Current purchases can be analysed
with your past purchased.
• Based on the patten that you
followed in the past, the system will
check the current purchases for the
legitimate or suspicious activity.
ML Applications in Business
• Handwritten Digital Recognition
• Handwritten cheques that are deposited in bank.
• To check what is written and convert them into
electronic numbers
ML Applications in Business
• Recommendations on websites
• When you buy items in
websites you will get more
related items
• This is done, because what you
purchased is similar to the
other item
• This item you purchased is
associated with other items in
the list.
• So, it is suggested those to
you.

To calculate the similarity, the

machine learning model is
used.
 Recommendations on
ML Applications in Business websites
ML
Applications
in Business
Recommendations on
websites
Recommendation System
Recommendation
systems rely on
feedback data
regarding ratings,
clicks, likes or
dislikes, etc.

The two main types

of feedback:

Explicit vs Implicit Feedback

Rating Matrix
• Content-based recommendation systems
focus on the characteristics of items and
users’ preferences as expressed through their
interactions with items.
• This type of system recommends items by
matching the attributes of items with users’
preferences. If a user has enjoyed movies like
“Batman Begins” and “The Dark Knight”
the system might suggest a similar movie,
“The Dark Knight Rises,” because it
features the same actors or belongs to a
similar genre.
• Collaborative filtering predicts a
user’s preferences by using the
collective knowledge and
behaviours of a large pool of users.
• Unlike content-based filtering,
which relies on the properties of
items, CF focuses on user-item
interactions, utilizing the feedback
or activity history of all users to
make predictions.
Content-Based vs Collaborative Filtering
Discussing Different Terms
• encompasses the algorithms and techniques used to
Machine Learning learn from data

• activities related to find patterns in databases and

Data Mining data warehouses

Predictive Analytics • analyzing data in order to predict future outcomes

• includes approaches for collection, storing, and

Data Science managing big data.
Data warehousing
Knowledge Discovery (KDD) Process
Online Analytical
Processing Server
(OLAP)
APPLICATIONS OF DATA
WAREHOUSES:

• Data warehouses help analysts or senior

executives analyze, organize, and use data
for decision making.
• It is used in the following fields:
• Consumer goods
• Banking services
• Financial services
• Manufacturing
• Retail sectors
ADVANTAGES OF DATA WAREHOUSING:

• Cost-efficient and provides quality of data

• Performance and productivity are improved
• Accurate data access and consistency
DATA MINING
Data Mining: Confluence of Multiple Disciplines
Data Mining: Confluence of Multiple
Disciplines
FEATURES OF DATA
MINING:
• It is good with large databases and datasets
• It predicts future results
• It creates actionable insights
• It utilizes the automated discovery of patterns
ADVANTAGES OF DATA MINING:
• Fraud Detection:
• It is used to find which insurance claims, phone calls, debit or credit
purchases are fraud.
• Trend Analysis:
• Existing marketplace trends are analyzed,which provides a strategic
benefit as it helps in reduction of costs, as in manufacturing per
demand.
• Market Analysis:
• It can predict the market and therefore help to make business
decisions. For example: it can identify a target market for a retailer, or
certain types of products desired by types of customers.
References
• https://slideplayer.com/slide/17057482/
• https://www.topcoder.com/thrive/articles/data-warehousing-and-
data-mining
• https://www.investopedia.com/terms/d/datamining.asp
• https://www.geeksforgeeks.org/difference-between-file-system-and-
dbms/
Thank you