AI Project
AI Project
31.12.2022
─
Devanshu Gupta
Tenth-A,
DLF Public School,
Sahibabad.
1
Table Of Contents
Table Of Contents 1
Certificate 2
Acknowledgement 3
4 W’s Canvas 5
1) Who Block 5
2) What Block 5
3) Where Block 6
4) Why Block 7
Datasets 8
Data Features 10
System Maps 10
Artificial Intelligence 13
Machine Learning 13
Deep Learning 14
Decision Tree 15
Confusion Matrix 16
Evaluation Score 16
Recall 17
Accuracy 17
Precision 17
F-1 Measure 17
2
Certificate
This is to certify that Devanshu Gupta, student of class 10th A, has
successfully completed their artificial intelligence project on AI Project
Cycle, under the guidance of Miss. Ansara Banu.
Acknowledgement
I would like to express my special thanks to my artificial intelligence teacher
Miss. Ansara Banu for their able guidance and support in completing my
project.
I would also like to extend my gratitude to Principal ma’am Mrs. Seema
Jerath for providing me with all the facilities that were required.
4 W’s Canvas
1) Who Block
Who block helps us in comprehending and categorizing who all are affected
directly and indirectly with the problem and who are called the Stakeholders. In
this scenario, Children, lone parents, disabled people and people in households
in which no one works are more likely to experience poverty, to remain in poverty
for longer and to experience deeper poverty, than others. Families with children
face higher risks of poverty because of the extra costs of children and because of
the effect on parents’ working hours. Children’s benefits do not fully compensate.
Lone parents are more likely to experience poverty than those in a couple. 49 per
cent of children in lone-parent families are in poverty.
2) What Block
What block helps us in understanding and identifying the nature of the problem
and how do we get to know what helps to get us to know the evidence. For three
decades, the number of people living in extreme poverty— defined as those who
live on less than $2.15 per person per day at 2017 purchasing power parity—was
declining. But the trend was interrupted in 2020, when poverty rose due to the
disruption caused by the COVID-19 crisis. The number of people in extreme poverty
rose by 70 million to more than 700 million people. The global extreme poverty rate
reached 9.3 percent, up from 8.4 percent in 2019.
The world’s poorest people bore the steepest costs of the pandemic. Their income
losses were twice as high as the world’s richest, and global inequality rose for the
first time in decades. The poorest also faced large setbacks in health and education
which, if left unaddressed by policy action, will have lasting consequences for their
lifetime income prospects. The recovery since then has been uneven. Rising food
and energy prices—fueled in part by the war in Ukraine and by climate shocks and
conflict—have hindered a swift recovery. By the end of 2022, as many as 685 million
people could still be living in extreme poverty.
6
The recent setbacks took place when the speed of progress toward poverty
reduction was already slowing, in tandem with subdued global economic growth.
3) Where Block
"Where" the problem arises, situation and the location. Poverty is a complex
problem. There are many aspects to it, and it has many causes. The most widely
used poverty definition focuses on economic poverty. This definition measures
poverty by the amount of money a person earns and establishes poverty rates for
communities and countries based on income inequality and financially drawn
poverty lines.
In this way, poverty becomes relative. The poverty threshold for a family of four in
the United States is an income just over $26,000 a year. For a family of four living in
absolute poverty in a low-income country, that amount of money is more than 36
times what they are forced to survive on each year.
Many families living in the world’s poorest countries must meet their basic needs
with an income of less than $1.90 a day. Nearly 10 percent of the world's population
live in this type of extreme poverty.
Understanding poverty strictly as economic inequality and measuring it with relative
poverty thresholds makes it difficult to view poverty as more than unemployment,
poor living standards, and a low income. But poverty encompasses more than this.
A proper definition of poverty must address the many different types of poverty and
acknowledge that poverty is hunger and lack of shelter, illiteracy and not having
access to school, being sick and unable to see a doctor, fearing for the future, living
one day at a time and feeling completely powerless and trapped by things beyond
one's control.
Cultures have internal and external elements that contribute to the existence of
poverty. Some of these conditions are tangible and external, like:
● Lack of shelter
● Limited access to clean water resources
● Food insecurity
● Physical disabilities
● Lack of access to health care
● Unemployment
● Absence of social services
● Gender discrimination
● Poor infrastructure
7
● Government corruption
● Environmental circumstances such as natural disasters, droughts, limited
resources or depletion of natural resources
Other elements are intangible and internal—knowledge, aspiration, diligence,
confidence, leadership styles, participatory governance, social capital, values, and
peace, to name a few.
4) Why Block
It is not one person or group who is affected by poverty, it is the whole world
population. We live in a world where everything is interlinked, the repercussions of
an event in one country are felt throughout the world. Poverty is associated with a
host of health risks, including elevated rates of heart disease, diabetes,
hypertension, cancer, infant mortality, mental illness, undernutrition, lead
poisoning, asthma, and dental problems.
8
Datasets
The most widely used baseline amount is $1.90 per day, measured in 2011
PPP international dollars (INT), a theoretical unit of currency used to make
country-to-country comparisons easier. People who make less than this
amount are considered to be in "extreme poverty", which is to say they are
the poorest of the poor. Additional baselines such as $3.30/hr and $5.90/hr
are often employed to help count people whose poverty is slightly less
extreme.
The second way to measure a country's poverty level is to determine the
percentage of people or families who earn less than the "national poverty
line", or poverty threshold—meaning, the annual income below which a
person or family is considered impoverished. The national poverty line is
calculated independently for each country because each country's economy
is different. For example, a person earning $25,000 a year in the United
States would have different opportunities than a person who earned $25,000
a year in Somalia.
9
The poverty rate in the United States varies depending upon the method of
measurement. According to the U.S. Census Bureau, the official 2017 poverty
rate in the U.S. was 12.3%. However, other sources placed it as high as 17.8%.
Despite being the largest economy in the world, the U.S. also has a significant
wealth inequality gap. The 2021 poverty threshold in the United States is
$26,246 for a family of four. This means that households with two adults, two
children, and a pre-tax income of less than $26,246 are considered to be
living in poverty. Some states are more impoverished than others, and their
poverty is exacerbated by high unemployment rates and a lack of
high-paying jobs.
According to World Bank, the countries with the highest poverty rates in the
world are:
1. South Sudan - 82.30%
2. Equatorial Guinea - 76.80%
3. Madagascar - 70.70%
4. Guinea-Bissau - 69.30%
5. Eritrea - 69.00%
6. Sao Tome and Principe - 66.70%
7. Burundi - 64.90%
8. Democratic Republic of the Congo - 63.90%
9. Central African Republic - 62.00%
10. Guatemala - 59.30%
Data Features
In the above provided data, the data features are:
(i) Poverty rates in different countries
(ii) Number of people below in the poverty line in developing and developed
countries
(iii) In which countries poverty is more and in which countries poverty is less
System Maps
A system map shows the components and boundary of a system and the
components of the environment at a point in time. A system map is effectively a list
11
Stage 4- Modelling
Modeling is the process in which different models based on the visualized data can be
created and even checked for the advantages and disadvantages of the model.
Artificial Intelligence
Artificial intelligence (AI) is the ability of a computer or a robot controlled by a
computer to do tasks that are usually done by humans because they require
human intelligence and discernment
Machine Learning
Machine learning is a branch of artificial intelligence (AI) and computer science
which focuses on the use of data and algorithms to imitate the way that humans
learn, gradually improving its accuracy.
14
Deep Learning
Deep learning is a subset of machine learning, which is essentially a neural network
with three or more layers. These neural networks attempt to simulate the behavior
of the human brain—albeit far from matching its ability—allowing it to “learn” from
large amounts of data. While a neural network with a single layer can still make
approximate predictions, additional hidden layers can help to optimize and refine
for accuracy.
15
Decision Tree
Decision Tree is the most powerful and popular tool for classification and
prediction. A Decision tree is a flowchart-like tree structure, where each internal
node denotes a test on an attribute, each branch represents an outcome of the
test, and each leaf node (terminal node) holds a class label.
Construction of Decision Tree: A tree can be “learned” by splitting the source set
into subsets based on an attribute value test. This process is repeated on each
derived subset in a recursive manner called recursive partitioning. The recursion is
completed when the subset at a node all has the same value of the target variable,
or when splitting no longer adds value to the predictions. The construction of a
decision tree classifier does not require any domain knowledge or parameter
setting, and therefore is appropriate for exploratory knowledge discovery. Decision
trees can handle high-dimensional data. In general, the decision tree classifier has
good accuracy. Decision tree induction is a typical inductive approach to learn
knowledge on classification.
16
Stage 5- Evaluation
Evaluation is the method of understanding the reliability of an API Evaluation and is
based on the outputs which are received by feeding the data into the model and
comparing the output with the actual answers.
Confusion Matrix
A Confusion Matrix is a table that is often used to describe the performance of a
classification model (or "classifier") on a set of test data for which the true values
are known. A 2x2 matrix denoting the right and wrong predictions might help us
analyze the rate of success.
Evaluation Score
Evaluation Score means the numerical score resulting from the adjectival
evaluation and numerical conversion of a particular portion of the Proposals.
17
Recall
Accuracy
Precision
F-1 Measure
Conclusion
Eradicating poverty is the need of the hour and needs to be given appropriate attention.
Artificial intelligence combined with its branch fields is a powerful tool that can help in
eradicating poverty, more effectively and efficiently. The United Nations has adopted the
sustainable development goals, but in this modern age, it seems impossible to achieve
these goals without automating many tasks. Many tasks can be done effectively only with
the help of AI. Thus, AI and its branch fields need to be adopted for each and every goal so
as to ensure that these goals are achieved within the given time, making the world a better
place to live in. Governments need to come together and cooperate so that other still
developing countries can also benefit from the developed countries technologies.
19
Remarks: