Abstract— R Programming Language for compiling the pro- gram.

Abstract— The prototype data mining system that I designed
and implemented in this project is an application for macro
economical analysis. I built an application for analyzing one
of the major issue of developing countries. The main purpose
of the application is classification and prediction some kind of
situations of economy in a country scale. One of these situations
is, so called, the middle income trap. The risks of falling into
the Middle Income Trap have increasingly become a focus of
discussions on the long-term economic and social development
prospects of developing countries. These risks, and how to
minimize them, are being debated at the highest levels of policy
making in some of the fastest growing emerging economies, even
while these countries remain a source of envy to the rest of the


We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

I built a classification model. The program consist of
several stages. Each stage use different data. Gross Domestic
Product (GDP) is a monetary measure of the market value of
all final goods and services produced in a period of time. It’s
perfect data for classifying countries in the middle income
trap. I also take population and exportation databases for
finding out Middle income trap countries. First of all, I found
out the values in Gross Domestic Product per capita data
which refers to middle income countries (MIC). Secondly, I
set the interval, between which, the countries with middle
income might be. Then, for better filtering out, I select
the countries with exportation is slowing down, but there
are still in the middle income. For that, I found out the
countries which export growth from 2009 to 2012 years
getting decreased over this time interval. In addition, I
defined the countries that Gross Domestic Product per capita
behave in the same meaner as exportation, but they are also
in the middle income list. I also used exportation data with
population for increasing the accuracy of the model. The last
stage is merging all results together.


The project was done in Google Cloud Platform. Google
Cloud Platform, offered by Google, is a suite of cloud
computing services that runs on the same infrastructure that
Google uses internally for its end-user products, such as
Google Search and YouTube. Alongside a set of management
tools, it provides a series of modular cloud services including
computing, data storage, data analytics and machine learning.
Google Cloud Platform lets you build and host applications
and websites, store data, and analyze data on Google’s
scalable infrastructure.

I use R Programming Language for compiling the pro-
gram. R is language and environment for statistical comput-
ing and graphics which provides a wide variety of statistical

and graphical techniques: linear and nonlinear modeling,
statistical tests, time series analysis, classification, clustering,

I worked with some packages for handling data. The readxl
package makes it easy to get data out of Excel and into R.
Compared to many of the existing packages (e.g. gdata, xlsx,
xlsReadWrite) readxl has no external dependencies, so it’s
easy to install and use on all operating systems. It is designed
to work with tabular data.


A. the algorithm

A classification model attempts to draw some conclusion
from observed values. Given one or more inputs a classi-
fication model tries to predict the value of one or more
outcomes. Outcomes are labels that can be applied to a
dataset. In this project, I find the countries in the middle
income trap and figure out the possible reasons why they fell
into such an Income Trap, e.g., the decrease of exportation.
Because the majority of data values are numeric, I try to use
the classification algorithms, which handle numeric attributes
better than nominal values. Thus, it increases the accuracy
of my results.

I chose One Rule” classification algorithm. OneR, short for
“One Rule”, is a simple, yet accurate, classification algorithm
that generates one rule for each predictor in the data, then
selects the rule with the smallest total error as its “one rule”.
OneR induces classification rules based on the value of a
single predictor.

B. the functionality

My model should find those countries in the middle
income trap situation using features like population, im-
portation, exportation, etc. In addition, the model should
predict as well. It means that the model could forecast the
economy growth of the country. As a result, looking at the
machine’s prediction, economists can use in advance their
known patterns and solutions to avoid the Middle Income
Trap situation.

C. the output

I got the results based on GDP, population, and Export
data sets. The model could classify all major players of
the MICs, such as China, Brazil, South Africa, Malaysia
and others. The list of Middle income Trap countries is in
Figure 4. However, the program also finds a little number
high income countries. It happens because those classified
countries’ characteristics actually are clear middle income
trap characteristics. I strongly believe and it’s highly possible