This document discusses factors that influence property prices in Ahmedabad, India. Key factors mentioned include the type of property (independent or flat), distance from amenities like markets, airports and train stations, socioeconomic class of residents in the area, amenities near the location, and upcoming development projects. Government policies are also noted as impacting prices. The document provides a table outlining how different factors would affect prices for high, medium and low salaried home buyers.

1. Kamal Gupta Roy
Decision Tree

2. | 2

3. | 3
Realty Hot Spot Series in Economic Times::
https://economictimes.indiatimes.com/wealth/real-estate/realty-hot-spot-series-this-ahmedabad-
locality-is-well-developed-real-estate-market/articleshow/70202560.cms
https://economictimes.indiatimes.com/wealth/real-estate/realty-hot-spot-series-affordable-housing-
make-this-developing-ahmedabad-locality-attractive/articleshow/69383669.cms
Property Rates and Trends in Ahmedabad:
https://www.99acres.com/property-rates-and-price-trends-in-ahmedabad

4. Reasons of higher prices
Reason Impact
Independent property or flat Flat will be less
Distance from good market places Far would be less
Distance from airport Far would be less
Distance from railway station/metro station Far would be less
Type of people stay at a location/ class of people High end would be higher
Basic amenities around the location like hospital,
school
More would be better
Proximity to the market in own location Closer is better
Brand of the builder Certain brands fetch more value
Ameneties in the complex More better
Corner plots/ less common walls Corner plots fetch higher
Upcoming projects around the area/perception Higher is better
Govt policies Better
Age of the building New is better | 4

5. All Cases
High Salaried People
4 High Amenities
2 Low amenities
Medium Salaried
people
Low Salaried people
3 Access to local
transportation is easy
1 Local transportation
is difficult
| 5

6. Kamal Gupta Roy
Decision Tree

7. | 7

8. Tree
- Thickest at
the bottom
and keeps on
thinning while
it go up
| 8

9. Analytical Decision
Tree
| 9

10. Typical Decision Tree
Root
Node
Decision
Node
Terminal
Node
Decision
Node
Terminal
Node
Terminal
Node
Decision
Node
Terminal
Node
Terminal
Node
| 10
Branch / Sub-Tree
Splitting
A
C
B
A is the
parent node
of B & C

11. Terminology
Root Node: It represents the entire population or sample and this further gets
divided into two or more homogeneous sets.
Splitting: It is a process of dividing a node into two or more sub-nodes.
Decision Node: When a sub-node splits into further sub-nodes, then it is called
the decision node.
Leaf / Terminal Node: Nodes do not split is called Leaf or Terminal node.
Pruning: When we remove sub-nodes of a decision node, this process is called
pruning. You can say the opposite process of splitting.
Branch / Sub-Tree: A subsection of the entire tree is called branch or sub-tree.
Parent and Child Node: A node, which is divided into sub-nodes is called a
parent node of sub-nodes whereas sub-nodes are the child of a parent node.
| 11

12. Decision Tree?
Decision trees classify instances or examples by starting at the root of the
tree and moving through it until a leaf node.
Supervised Algorithm
Decision trees are powerful and popular tools for classification and
prediction.
Decision trees represent rules, which can be understood by humans and
used in knowledge system such as database
It is one of the easiest and popular classification algorithms to understand
and interpret
| 12

13. Split
The tree can grow huge
These trees are hard to understand.
Larger trees are typically less accurate than smaller trees.
| 13

14. | 14

15. Little Mathematics
| 15

16. Entropy is a measure
of uncertainty
| 16

17. | 17

18. | 18
• In the case of
Bernoulli trials,
entropy reaches
its maximum
value for p=0.5

19. • Three patients went for
a medical test at
doctor’s office
• Test results can be
positive or negative
| 19

20. | 20
- It becomes certain to
predict if all values are same

21. | 21
Entropy
Information
Gain

22. | 22
Overall
14
7 good, 7 bad
Excellent
1 bad, 3 good
Good
2 bad, 3 good
Bad
4 bad, 1 good
Excellent Good Poor
Yes No Total Yes No Total Yes No Total
# 1 3 4 # 2 3 5 # 4 1 5
probability 0.25 0.75 probability 0.40 0.60 probability 0.80 0.20
log p (2.00) (0.42) log p (1.32) (0.74) log p (0.32) (2.32)
p log p (0.50) (0.31) p log p (0.53) (0.44) p log p (0.26) (0.46)
Entropy(S) 0.81 0.285714 Entropy(S) 0.97 0.357143 Entropy(S) 0.72 0.357143
Entropy 0.84
Liability Liability Liability
Yes No Total
# 7 7 14
probability 0.50 0.50
log p (1.00) (1.00)
p log p (0.50) (0.50)
Entropy(S) 1.00
Liability
Information Gain = 1-0.84=0.16