using for students

1. Decision Tree
Group Member:
Md Ibrahim Adham Mesu
Sakib Hasan Rial
Lifonar Afrin Lifa
Md Islam Khan
Abdullah Al Redwan

2. Content:
Introduction
Types
Algorithm
Cart Algorithm
C5.0 Algorithm
Advantages
Limitation
Application

3. What is Decision Tree?

4. Decision Tree:
A decision tree is a graphical representation of possible solutions to a
decision based on certain conditions.
It's called a decision tree because it starts with a single box (or root),
which then branches off into a number of solutions, just like a tree.
Decision trees provide an effective method of Decision Making.

5. Decision Tree:
A decision tree consists of 3 types of nodes
1. Decision nodes - commonly represented
by squares
2. Chance nodes - represented by circles
3. End nodes - represented by triangles
A decision tree consists of 2 types of
branches :
1. Decision branches
2. Event branches

6. Fig: Decision Tree

7. Algorithm
Input:
D // Training data
Output:
T //Decision tree
DT Build algorithm
// Simplistic algorithm to illustrate naive approach to building DT

8. Types of Decision Trees:
Types of decision tree is based on the type of target variable we
have. It can be of two types:
Categorical Variable Decision Tree
Continuous Variable Decision Tree

9. Categorical Variable Decision Tree:
Categorical Variable Decision Tree:
Decision Tree which has categorical
target variable then it called as
categorical variable decision tree.
E.g.:- In scenario, where the target
variable was “Student will distributed
in gender and height” i.e. YES or NO.

10. Continuous Variable Decision Tree:
Continuous Variable Decision Tree:
Decision Tree has continuous target variable then it is called as
Continuous Variable Decision Tree.
E.g.:-
A worker thinking about his salary and take decision. Is he accept
new job offer(yes/ no). In this case, we are predicting values for
continuous variable.

11. Continuous Variable Decision Tree:

12. Assumptions while creating Decision Tree:
Some of the assumptions we make while using Decision tree:
At the beginning, the whole training set is considered as the root.
Feature values are preferred to be categorical. If the values are
continuous then they are discretized prior to building the model.
Records are distributed recursively on the basis of attribute values.
Order to placing attributes as root or internal node of the tree is done
by using some statistical approach.

13. Different types of Algorithm:
HUNTS
CART
ID3
C5.0
SPRINT
CHAID

14. Cart Decision Tree:
sprit
Gini Index
Cost complexity pruning

15. C5.0 Decision Tree:
Multi sprit
Info gain
Pessimistic pruning

16. Advantages:
Decision Trees are easy to explain. It results in a set of rules.
It follows the same approach as humans generally follow while
making decisions.
Interpretation of a complex Decision Tree model can be simplified by
its visualizations. Even a naive person can understand logic.
The Number of hyper-parameters to be tuned is almost null.
It can be combined with other decision techniques.

17. Limitation:
There is a high probability of overfitting in Decision Tree.
Generally, it gives low prediction accuracy for a dataset as compared
to other machine learning algorithms.
Information gain in a decision tree with categorical variables gives a
biased response for attributes with greater no. of categories.
Calculations can become complex when there are many class labels.

18. Application of decision Tree:
Decision tree has been used to develop models for prediction and
classification in different domains some of which are:
Business management
Customer relationship management
Fraudulent statement detection
Engineering
Energy consumption
Fault diagnosis
Healthcare management
Agriculture

19. Applications in Real Life
Selecting a flight to travel
Choosing a best friend
Handling late night cravings

20. Applications in Business
Alternatives: Decision tree helps organizations to view the
alternatives way that can happen.
Events: Possible result may have two events.
Outcomes: Possible result from the decision tree.

21. References:
Kamiński, B.; Jakubczyk, M.; Szufel, P. (2017). "A framework for
sensitivity analysis of decision trees“
Quinlan, J. R. (1987). "Simplifying decision trees". International
Journal of Man-Machine Studies.
Venky Rao(2013 ).Journal “Introduction to Classification & Regression
Trees (CART).
Utgoff, P. E. (1989). “Incremental induction of decision trees”.
Machine learning.