Analytics And Intelligent Systems

NUS ISS AIS Practice Group

Dashboard – Marvel Universe — November 9, 2016

Dashboard – Marvel Universe

Business Purpose – To evaluate the performance of Superhero Franchise Movies

Target Audience – The producers and investors for the Marvel Studios




Submitted By:

  • Abdulhannan Patel – A0148494R
  • Gurkiran Kaur – A0148595M
  • Harish Kusumanchi – A0150353R
  • Valluru Chandana Reddy – A0148547U
Geospatial Analysis of World Population —

Geospatial Analysis of World Population

capture7Map Link:


World population is the total number of human beings currently living on the planet. As of August 2016, it was estimated at 7.4 billion. It is estimated to further increase by 11.2 billion in the year 2100. World population has experienced a continuous growth since the end of the Great Famine of 1315–17 and the Black Death in 1350, when it was near 370 million. The growth, although has declined to 1.18% between 2010 -2015, the world population is still increasing exponentially.

Characteristics of World Population:

Population density is a measurement of population per unit area or unit volume.

Life expectancy: It is a statistical measure of the average time an organism is expected to live, based on the year of their birth, their current age and other demographic factors including sex.

Human Sex Ratio: The human sex ratio is the ratio of males to females in a population.

Fertility: Fertility is the natural capability to produce offspring. As a measure, fertility rate is the number of offspring born per mating pair, individual or population.

Birth Rate: It is the number of live births per thousand of population per year.

Death Rate: The ratio of deaths to the population of a particular area or during a particular period of time, usually calculated as the number of deaths per one thousand people per year.

Data Collection:

Data was extracted from different online sources for the following variables for geo-spatial analysis.

Data Source and Indicators:

Data Transformation:

As data was extracted from different online sources, data transformations were done to combine different datasets into one dataset with the required variables. Mostly, the transformations were done in MS-Excel using Fuzzy Lookup. The countries with insignificant population densities were filtered out. The data for countries which was not available, was manually added to the dataset.

Tools Used:

  • Carto
  • MS-Excel


Population Growth: According to the results of the 2014, the world population reached 7.2 billion, implying that the world has added approximately one billion people in the span of the last twelve years. China (1.4 billion) and India (1.3 billion) are the two largest countries of the world, both with more than 1 billion people, representing 19% and 18% of the world’s population, respectively. 60% of the global population lives in Asia (4.4 billion), 16% in Africa (1.2 billion), 10% in Europe (738 million), 9% in Latin America and the Caribbean (634 million), and the remaining 5% in Northern America (358 million) and Oceania (39 million).


Gender Imbalance was represented by percentage of female population in the world.

Higher Gender Imbalance (Sex ratio>50): Asian and North African countries.

Low Gender Imbalance (Sex ratio<=50): There are many countries listed mainly countries in North America, Australia, and Asia.

Gender Balance :Few countries with sex ratio = 50 are as follows:-

  • Africa-Kenya, Zambia, Congo, Cameroon, Mali, Tunisia
  • Europe-Norway, Ireland
  • Asia-Turkey, Vietnam
  • South America-Peru, Ecuador, French Guinea
  • North America-Honduras


Life Expectancy has increased over the years. It can be observed that developed nations such as United States of America and United Kingdom (greater than 78 years) have better life expectancies. While on the other hand, less developed or under developed countries like Namibia, Liberia have lower life expectancies. This could be attributed to the fact that developed countries offer better medical care, better nutrition, better environment and hence better immunity. Whereas, underdeveloped countries suffer from poor sanitation, poverty and poor quality of lifestyle.


Fertility of South Asian countries such as India, Afghanistan and Pakistan was quite high as compared to the rest of the world. Such countries also had a higher population growth rate. Thus, it won’t be long when India takes over China as the country with largest population.



The data of the world population since 1960 till 2015 was used to predict the future values for the same. It can be seen, that the world population will further increase in the fourth coming years, however at a lower growth rate.


Now that countries are identified based on the population, a study can be conducted to understand the factors such as economic, environmental and government policies that influence gender imbalance.


Support Docs: geingAndDevelopment2015.pdf

Submitted By:

  • Abdulhannan Patel – A0148494R
  • Gurkiran Kaur – A0148595M
  • Harish Kusumanchi – A0150353R
  • Valluru Chandana Reddy – A0148547U
Dashboard – Corrupt Practices Investigation Bureau —

Dashboard – Corrupt Practices Investigation Bureau

Corrupt Practices Investigation Bureau (CPIB)

The Corrupt Practices Investigation Bureau (CPIB), an independent agency, is responsible for the investigation and prevention of corruption in Singapore. It is the world’s oldest anti-corruption agency established in 1952 by the British colonial government.

As the sole agency in Singapore which investigates corruption offences, the CPIB is constantly striving to keep Singapore corruption-free and ensuring that offenders are brought to justice.  The Bureau will remain resolute and committed to its mission, as it moves forward to face the complex challenges ahead.

Mission: To Combat Corruption through Swift and Sure, Firm but Fair Action.

Vision: A Leading Anti-Corruption Agency that upholds Integrity and Good Governance towards Achieving a Corruption-free Nation

Core Values: Integrity, Teamwork and Devotion to Duty


Tools Used for Making the Dashboard

  • Tableau – to make general graphs
  • Photoshop – to make it more attractive (as some of the data was mocked)


The above Dashboard was made keeping in mind the User. As this Dashboard was for the Prime Minister of Singapore. We had to give him the detailed status report of the corruption in the country. Lets discuss it graph by graph,

The First Graph displays the Corruption Perception Index vs Number of Corruption Cases in Past 7 Years. The Corruption Perceptions Index ranks countries/territories based on how corrupt a country’s public sector is perceived to be. It is a composite index, drawing on corruption-related data from expert and business surveys carried out by a variety of independent and reputable institutions. Scores range from 0 (highly corrupt) to 100 (very clean). From the graph we can see that even though the number of cases are reducing each year, the CPI score is not improving which means that other nations are doing better than Singapore.

Corruption Rank table ranks each country on the basis of the corruption rank in year 2015 and also tells us if the rank has improved or degraded from last year. Prime Minister needs to know which countries are doing better than them and can ask for new measures other countries are taking to fight corruption. We can see that Singapore’s rank has degraded by 1 from last year.

Next graph shows the Change in Corruption by each department which are lead by the miniters from PMO’s Cabinet. From here they can see the most and the least corrupt departments and ask the respective lead/minister for the reasons.

Last two graphs shows the People’s view about the governments efforts to fight corruption. As a prime minister is a lead of its Political Party also, he needs to make sure that irrespective of his governments efforts, if general people are feeling the change in the corruption in the country. Because, without people’s support, he will not be able to be successfull in the next elections.

Prediction of the Next years Rank of Singapore with respect to corruption is taken from the which helps the prime minister to know which way the CPIB is heading too.

Data Collection

  1. 2015 Annual Report:
  2. 2014 Annual Report:
  3. World CPI Rankings:
  4. World Bank Country-wise Corruption Data:
Co2 Emission Worldwide (1985 – 2015) —

Co2 Emission Worldwide (1985 – 2015)


Carbon dioxide from burning fuels causes global warming, a process capable of changing the world’s climate significantly.

As you can see from the graphs, the amount of carbon dioxide in the atmosphere has increased steadily over the past 150 years, and so has the average global temperature. Some of this is due to human activity.Along with other gases such as methane and water vapors, carbon dioxide is a greenhouse gas. It absorbs heat energy and prevents it escaping from the Earth’s surface into space. The greater the amount of carbon dioxide in the atmosphere, the more heat energy is absorbed and the hotter the Earth becomes.

 Results of global warming

A rise of just a few degrees in world temperatures will have a dramatic impact on the climate:

  • global weather patterns will change, causing drought in some places and flooding in others.
  • polar ice caps will melt, raising sea levels and causing increased coastal erosion and flooding of low-lying land – including land where major cities lie.

Data Collection

All the data for this analysis and visualization was collected from Links for the data are below:

Data transformation

Data for both Co2 emission and world population were collected from 1980 – 2011 but for our study we considered the data from 1991-2011. Co2 emission per metric ton ranges from 0-70 metric ton per year and it was very difficult for us to visualize it in Carto. So as to make the visualization simple, we derived some variables which made the visualization simple and also more understandable. Some of the derived variables are mentioned below:

  • Mean of Co2 Emission by Country – we took the average of Co2 Emission by each country and then assigned a value of 1 the Co2 emission in that year is more than the average emission of all the years and 0 otherwise.
  • Level_Score – We divided the countries by giving them a score from 1-10 as per the level of Co2 emission in a year, by giving a country emitting in range of 0-5, a score of 1 and a country emitting more than 50, a score of 10.

We automated the procedure of deriving a variable by writing a r script for both the variable derivation, so as to save the time.

Geo Spatial Analytics

For geospatial analysis, we used Carto and by changing the sql query and putting some filters in Carto itself, we came up with some very beautiful analysis. This analysis is done for the year of 2011 only.

From the graph below we can clearly see that only a very little part of world i.e.  Oman and United Arab Emirates are the only countries which are emitting Co2 at a very alarming rate in 2011 i.e., more than 50 metric tons a year and also more than any of the other countries.


Inspite of being such a small nation, we can see that Oman and United Arab Emirates are emitting more Co2 in the environment than many of the big nations of the world which emit less than 40 metric tons each year.



Point Visualization(Animated)

For Geovisualisation, we used 2 methods one by dropping points at each country so as to animate it and other by marking the whole country with a polygon which could not be animated because of the Carto constraints.


This visualization is animated and is showing the Co2 emission by each country from 1991-2011. We have used 2 layers in this case:

  • 1st Layer is made using Torque Cat which shows the level of Co2 is above or below the Country’s average Co2 emission. Green markers are to show that the Co2 Emission of the country has gone below the average and Red Markers are to show that the Co2 Emission has gone above the average.
  • 2nd layer is made using Simple wizard which places a marker on each Country showing the country’s name on hovering over the marker and the level of Co2 emission.

There was a need of using 2 layers because when we use Torque Cat the Infowindow is disabled and also there was a need to showing county’s name on hovering as it is not user friendly to zoom all the time to see which country’s marker is red/green. So we put a Simple Wizard layer over the Torque Cat layer to solve this problem.

  • We have put our custom legends and label so as to make the map and points more understandable.
  • We also changed the duration of animation in CARTOCSS to 30 seconds and the frame count to 20(as there are only 20 years), so that it can show visualization of each year just once and we kept torque data aggregation method to linear only as linear is more appropriate than cumulative method in this case. Then we also changed the color of each marker by using green for marker[value=1] and red for marker[value=2].

Polygon Visualization(Static)


This visualization is better than the point visualization, but this cannot be animated using Carto as animating polygon feature is not available in Carto. We were able to achive this polygons using the carto update query only which is mentioned in the data transformation technique mentioned above. But we can always change the SQL query or put filters using SQL to get this kind of visualization.

For this visualization, we derived a variable LEVEL_SCORE (described above) and defined different color for each category (green for the least Co2 Emitting country to Dark Red and Black for the most Co2 emitting Country).

  • We used category wizard to make this visualization by selecting Level_Score as the differentiating feature.
  • Used Infowindow to put country’s name and the level of Co2 Emitted on hover.
  • Changed the legend tag to put custom legends showing the range of Co2 emitted by each country.
  • Updated the CARTOCSS to change the color of each polygon from green to Dark Red.





Terrorism has been around since the beginning of time, and has caused empires to rise, fall, and allowed people to gain power. It is a growing problem in this unstable world. A simple act of terrorism can cause tensions between two countries, as seen with Israel and Palestine’s conflicts due to religious beliefs and territory disputes. Among the various potential threats are wars with neighboring countries, missile attacks on cities, biological and chemical terrorism, suicide bombings, and hostage taking.

Owing to the growing global terrorist activities, we wanted to explore how analytics could help in understanding the various patterns and trends in these terrorist activities.

To compare or quantify the effect of terrorism on different countries, we tried to bring in the below-mentioned indices that directly/indirectly affect terrorist activities:

  1. Global Terrorism Index – which provides a comprehensive summary of the key global trends and patterns in terrorist activities for each country.
  2. Human Development Index – which is a composite statistic of life expectancy, education, and per capita income indicators
  3. Political Stability and Absence of Violence Rank – measures perceptions of the likelihood that the government will be destabilized or overthrown by unconstitutional or violent means
  4. Percentage share of Military expenses in a country’s GDP – this is representative of how seriously a country takes its security and how much it’s willing to spend to protect their nation


For our analysis, we took data from Global Terrorism Database which is an open-source database that contains information on global terrorist activities between 2001 and 2015. For each attack, information is available on the date and location of the incident, the weapons used and the target, the number of casualties, and the group, if identifiable.


The latitudes and longitudes which were a part of the original data source and the same was used for tagging cities to represent the number of casualties while the country names were used to tag the various indices.


  • Microsoft Excel : Used to perform initial exploratory analysis and for data preparation for subsequent Geo Visualization.
  • Tableau: To develop insights and analytics on the top 10 ranked countries by GTI scores.
  • Carto : Used to perform geo visualization on this dataset on the global level.


Tableau Dashboard Link

We analyzed patterns using the Top 10 GTI rankings for various countries which have highest terror activities on various levels overtime across the years like

  1. Volume of Attack – Includes No. of causalities, injuries, GTI score and no of attacks
  2. No of attacks vs No of killings
  3. Type of weapons used for terrorist activates
  4. Type of targets for terrorist activities



Carto Link

Carto was used for Geo-Visualization. We have used following 5 layers:

  1. International Logistically: The terrorist activities are divided into two categories, international logistically (which means that the perpetuators are of different nationality than the place of attack or not).
  2. Types of Weapons Used : This layers shows the types of weapons used by terrorist. We can see from the map that firearms and explosives are most common weapons.
  3. Types of Attacks: In this layer we show the different types of attacks by terrorist. Bombing, Armed Assaults and Hostages are most common attacks types.
  4. Intensity of Casualties: The heat map in this layer shows the severity of the casualties in the terrorist attacks.
  5. Suicide Attack: This layer indicates whether the attack was suicide attack or not.

Do let us know in case of any feedback/ suggestions/ queries.

Created By:

  • Disha Grover (A0148618W)
  • Manan Katiyar(A0148510M)
  • Ram Thilak Prem Kumar (A0148522H)
  • Shweta Sharma (A0148486N)
5 Questions – Impact of Climate Change on Winter Tourism —

5 Questions – Impact of Climate Change on Winter Tourism

The winter sports industry/community is deeply dependent upon predictable, heavy snowfall, but climate change is expected to contribute to warmer winters, reduced snowfall, and shorter snow seasons. The estimated $12.2 billion U.S. ski and snowmobile winter sports industry have already felt the direct impact of decreasing winter snowpack and rising average winter temperatures. Warmer climate translates into less snow and fewer people on the slopes, which results in massive economic hardship for resorts, states, local communities, businesses and their employees.

The purpose of the tableau is to help policy makers understand both the ski and snowmobile industry’s current economic scale and the potential economic impacts that climate change may cause.


We have come up with 5 questions using GQM technique directed towards the United States National Tourism Office- Labor and Commerce Department. 


Do let us know in case of any feedback/ suggestions/ queries.

Created By:

  • Disha Grover (A0148618W)
  • Manan Katiyar(A0148510M)
  • Ram Thilak Prem Kumar (A0148522H)
  • Shweta Sharma (A0148486N)