Big Data Analytics and IBM Watson

This assignment delves into the field of big data analytics, focusing on its applications in healthcare and the role of IBM Watson. It examines various aspects of big data, including its definition, technologies used for analysis, and business intelligence tools like data warehousing. The significance of IBM Watson in processing vast amounts of medical data and aiding clinicians in decision-making is also explored.

MIS781 Business Intelligence
Business Intelligence Solution Development and Report for Social
Enterprise
Name of the student
Name of the University
Author Note

Table of Contents
Introduction......................................................................................................................................3
Objective of BI solution...................................................................................................................3
BI Dashboards.................................................................................................................................5
Predictive Models..........................................................................................................................12
Benefits of BI solutions.................................................................................................................13
Conclusion.....................................................................................................................................14
Reference.......................................................................................................................................15

Introduction
Business Intelligence is programming framework intended to get the Business Values from a
Business and basically, it is no intended to execute the real business and related exercises like
cost figure, generation administration and so forth (Kumar, Morstatter and Liu, 2014, p. 25). Its
prosperity relies upon different components like satisfaction of client necessities, client
encounter and adaptability of the arrangement, force of BI-Savvy methodology at administration
level and the authoritative IT strategies made for the reception BI framework. It is important to
take after the accepted procedures and rules made by an individual or a counseling association to
make the BI activity a major accomplishment with sensationalized ROI (Laursen and Thorlund,
2016, p. 123). With ordinary associations no matter how you look at it are digitizing the data.
This data might be caught in various framework and arrangements. Business Intelligence (BI)
speaks to a corporate activity to move from static representation of information to a more
examination, dynamic and self-administration driven type of detailing. A successful Information
technique, and Business Intelligence arrangement is ending up progressively fundamental for
compelling basic leadership in the current scenario (Kambatla et al. 2014, p. 87). Business
Intelligence is tied in with appearing well and good out of the colossal wellsprings of
information inside the organization and changing over them to significant data that can be
utilized to settle on shrewd business choices.
There are several BI tools available that enables mangers to visualize information in a more
methodical way and therefore business decision making becomes comparatively easier. This is
not only applicable for business purpose. In modern day, application of BI enables social
enterprises to understand historical records effectively (Kimball et al. 2015, p. 12). This
particular study has considered air quality information as one of the significant environmental
issue and prepared a set of dashboards to analyze the aspect clearly.
Objective of BI solution
In order to visualize the air quality data, the analyst has used IBM Watson analytics tool. The
study has been performed considering the G20 nations. The data is comprised of 16 variables,
which are as follows:

Sl.
no.
Property Definition
1 Air Pollution PM2.5 air pollution, population exposed to levels exceeding
WHO guideline value (% of total)
2 CO2 Emissions CO2 emissions (kt)
3 Electric Power Use Electric power consumption (kWh per capita)
4 Electricity Access Access to electricity (% of population)
5 Energy Intensity Energy intensity level of primary energy (MJ/$2011 PPP
GDP)
6 Energy Use Energy use (kg of oil equivalent per capita)
7 Forest Area Forest area (% of land area)
8 Fossil Fuel Fossil fuel energy consumption (% of total)
9 Fresh Water Annual freshwater withdrawals, total (% of internal
resources)
10 Greenhouse Gases Total greenhouse gas emissions (kt of CO2 equivalent)
11 Methane Emissions Methane emissions (kt of CO2 equivalent)
12 Nitrous Oxide
Emissions
Nitrous oxide emissions (thousand metric tons of CO2
equivalent)
13 Non-Solid Fuel
Access
Access to non-solid fuel (% of population)
14 Nuclear Energy Alternative and nuclear energy (% of total energy use)
15 Renewable Electricity Renewable electricity output (% of total electricity output)
16 Renewable Energy
Use
Renewable energy consumption (% of total final energy
consumption)
Assumptions
In order to perform this study, the analyst has considered below mentioned assumptions:
 The study is mainly limited to G20 nations only;
 All the dashboard were designed based on latest available information;
 Only air pollution and associated aspects were taken into consideration. Other
environmental issues were overlooked to narrow done the research area.

BI Dashboards
Figure 1: Dashboard 1
The examination of the information of Energy Intensity against nation has been plotted in a bar
graph. The qualities, which has been plotted in the diagram, is the power of vitality level of
essential vitality. The qualities are ascertained as Mega Joule. The measure of vitality is the
vitality level, which is being utilized by the nation. From the qualities, one might say that the
most extreme measure of vitality power has been recorded in Aruba (Gandomi and Haider, 2015,
p. 96). The least has been recorded in Hong Kong. The information helps in knowing the way the
nations utilize their vitality assets for the improvement of their nation.
The investigation of the information of Nuclear Energy against nation has been plotted on a zone
diagram. The qualities that has been plotted in the chart is the level of the aggregate use of the
vitality that is an originating from atomic sources. The utilization of atomic vitality however
creates a gigantic measure of vitality than the traditional route yet thus delivers probably the
most risky contaminations on the planet. The poisons as carbon mixes is substantially less
hazardous than the radioactive toxins, which may cause change of qualities in mankind. Along
these lines, the discarding the toxins is essential strategy (Isik, Jones and Sidorova, 2013, p. 47).
This again represents a hazard for nature on the grounds that the contaminations must be
arranged in the ground. They may leak through the underground compartment, blend out with the
dirts and underground water, and spread the contamination. The contamination caused by any

radioactive squanders can't be cleaned effortlessly. The contaminations stay in the ground for a
long time and cause radiation contamination without others notwithstanding thinking about it.
The nations like France, Canada, Republic of Korea and Brazil are a portion of the best most
client of atomic vitality on the planet. Nonetheless, the waste must be discarded precisely.
The examination of the information of Energy use against nation has been plotted in a tree map.
The qualities, which has been plotted in the diagram, is the measure of vitality utilized by the
nation, which is computed as for the measure of kilogram of oil proportional to the per capita of
the populace. The measure of oil vitality utilized by the nation influences the natural factor of the
nation (Hu et al. 2014). The utilization of oil is straightforwardly influenced because of the
measure of oil that is accessible in the nation. The most elevated measure of vitality utilize has
been recorded in China and US. The diagram depicts the estimations of the dataset obviously for
the investigation to be done effortlessly.
The examination of the information of Fresh Water against nation has been plotted on a pie
graph. The qualities, which has been plotted in the diagram, is level of the aggregate sum of new
water that is being pulled back by the nation from the inner assets in the nation on a yearly
premise. This variable is essential for the estimation in the investigation about nature since
increasingly the measure of new water being utilized the less there is for the others to utilize. It
has been discovered that there is a low amount of new water on the planet departed to be utilized
by mankind (Herath et al. 2014, p. 22). It this drains at that point there is no other option
accessible for the mankind for survival. In this manner, the nation should investigate the issue
that the measure of crisp water use be lessened and to take up the utilization of various
techniques for the reusing of water from different sources. This would to a great extent help the
world. The most astounding measure of water is utilized by Saudi Arabia, Korean Republic and
India. This is because of the way that the surface range of the nation is bone-dry which makes
the nation difficult to utilize some other wellspring of water for their everyday life.

Figure 2: Dashboard 2
The investigation of the information of air contamination against nation has been plotted in a bar
outline. This demonstrates the nations over the world who has the most measure of air poisons in
their environment. The contamination of the air, which surpasses the WHO rules, has been
classified. The qualities are given as a rate estimation regarding the aggregate sum of
contaminations noticeable all around. It can be seen that the qualities are moderately higher for a
large number of the nations. It can be seen that 46 out of the 200 nations have a 100% of higher
contaminations noticeable all around. The nations should focus to making the air contamination
of their nation lower than whatever remains of the world (George et al. 2015, p. 142). The
expansion in the Earth-wide temperature boost is straightforwardly identified with the measure
of contaminations noticeable all around. The measure of air contamination additionally
represents a danger for the strength of the residents of the nation.
The investigation of the information of CO2 Emission against nation has been plotted in a pie
outline. The information depends on the carbon dioxide outflow from the vehicles and the
production lines in the nation. The most elevated measure of carbon dioxide discharge has been
found in China. Taking a gander at the investigation one might say that the measure of
emanation of carbon dioxide is straightforwardly identified with the measure of surface territory
thee nation has. The more measure of surface territory implies more number of individuals living
in the nation, which specifically identifies with the quantity of autos and the measure of plants
experiencing childhood in the nation. The nations with a moderately higher measure of carbon
dioxide discharge ought to consider the utilization of inexhaustible assets (Chang, 2014). The

measure of carbon dioxide discharge is the most astounding in china took after by United States
of America and nearly took after by India. The nations needs to consider the utilization of
sustainable power source for the improvement of the nation and for the earth.
The investigation of the information of Greenhouse Gasses against nation has been plotted on a
guide outline. The qualities which has been plotted in the chart is the measure of nursery gasses
radiated by the number of inhabitants in the nation in kilo ton of CO2 outflow identical. The
qualities are straightforwardly identified with the measure of populace of the nation. The higher
the measure of populace of the nation the more number of individuals utilize machines which is
in charge of the arrival of nursery gasses into the earth (Doyle-Lindrud, 2015). These gasses are
responsively for the warming up of the earth and thusly makes hurt nature. This can be halted by
utilizing better electrical apparatuses or to utilize an option for the machines. It should be
decreased as the impact nursery gasses makes the polar ice tops to soften and the ocean level to
rise. This causes low lying area and ocean shorelines to get submerged. Aside from this
individuals endure because of anomaly of thee climate conditions and skin sicknesses. The
nation needs to diminish the discharge of nursery gasses. China has the most elevated measure of
ozone depleting substance discharge on the planet. China creates the twofold measure of nursery
gasses contrasted with the United States of America.
The investigation of the information of Methane Emission against nation has been plotted on a
pie outline. The qualities which has been plotted in the diagram is the measure of methane gas
discharged by the number of inhabitants in the nation in kilo ton of CO2 outflow equal. Methane
gas is for the most part went with the nursery gasses. A little segment of methane is additionally
discharged from the bogs and sewers in the nation. Methane additionally acts as an ozone
depleting substance and can help in the ascent of temperature of earth (Devreese, 2013). It
should be observed by the engineers of various apparatuses to take care of the way that they
ought to supplant the methane gas with a less destructive gas or limit the utilization of the gas
however much as could reasonably be expected for the improvement of the earth. The most
astounding recorded esteem is from china where there us the most elevated populace and
consequently the huge number of apparatuses being utilized by the subjects. It is taken after
nearly by India in the generation of methane gas. India and Russia are close rivals in the most
noteworthy generation of methane gas by the number of inhabitants in the nation.

Figure 3: Dashboard 3
The examination of the information of Forest Area against nation has been plotted on a bar
graph. The qualities, which has been plotted in the diagram, is the level of land territory that is as
yet canvassed in woods region. The more the level of region of woods the better it is for the earth
to have a maintainable ecological hotspot for the survival of the diverse widely varied
vegetation. The qualities on the chart hued dull proposes that the nation has the most astounding
area to woodland proportion which improves it a place which should be safeguarded for the
future and for the advancement of the world (Chen, Argentinis and Weber, 2016). The most
astounding level of woods region on the planet is in Suriname and Seychelles. More than fifty
nations around the globe has a woodland range scope of half which helps in keeping an adjust
with the mechanical world and nature. The higher the quantity of this diagram the better it is for
the nation and in addition the earth.
The examination of the information of Fossil Fuel against nation has been plotted on a tree map.
The qualities, which has been plotted in the chart, is the level of aggregate sum of non-renewable
energy source utilization that has been devoured by the nation. This influences the earth as the
higher the measure of petroleum product utilization the higher is the measure of contamination
that is being caused by the consuming of the non-renewable energy sources either in the
enterprises or by the vehicles of the nation. The information has been broke down and one might
say that the most noteworthy measure of non-renewable energy source utilization is specifically
identified with measure of fills that is accessible in the nation (Devarakonda, and Tsou, 2015).
On the off chance that the nation has a vast hold of petroleum product then they would not need

to pay progressively and will have the capacity to get fills at a modest cost. This makes them go
through their save totally. The most astounding client of non-renewable energy sources has been
figured by nations in the mid-eastern piece of the world. The most noteworthy clients are Saudi
Arabia, Russian Federation and Japan. These urban communities have the biggest oil hold on the
planet hence; they have the most astounding measure of petroleum product utilization on the
planet.
The examination of the information of Renewable Electricity against nation has been plotted on a
bar graph. The qualities, which has been plotted in the chart, is the level of the aggregate power
yield of the vitality that is an originating from inexhaustible sources. The utilization of
sustainable power source is the best choice for the world (Alexandrov et al. 2014). The word is
now experiencing the contaminations and the nonstop increment in the contamination because of
the utilization of the fossils energizes and the chemicals. The choices for the utilization of
inexhaustible wellsprings of vitality identifies with the utilization of sunlight based cells,
hydroelectric and wind turbines. The nation with the most astounding rate number can be said to
be adding to the world's wellbeing more than whatever is left of the world. The most eminent
supporters of this reason are Brazil, Canada and Saudi Arabia.
The investigation of the information of Renewable Energy Use against nation has been plotted
on a tree outline. The qualities which has been plotted in the chart is the level of the aggregate
last vitality utilization that is originating from sustainable sources. The use of practical power
source is the best option for the world. The world is starting at now encountering the pollution
and the steady addition in the sullying in view of the use of the fossils powers and the chemicals.
The choices for the usage of reasonable wellsprings of essentialness relates to the use of sun
oriented cells, hydroelectric and wind turbines. The country with the most essential rate number
can be said to be adding to the world's prosperity more than whatever is left of the world. The
most remarkable supporters of this reason are Brazil, India and Indonesia. The nations living in
the foothills of the Himalayas utilizes the sustainable assets to contribute in the advancement of
the world. The nations utilizes the inexhaustible assets to contribute in the advancement of the
world.

Figure 4: Dashboard 4
The investigation of the information of Nitrous Oxide Emissions against nation has been plotted
on a bar graph. The qualities, which has been plotted in the chart, is the measure of nitrous oxide
gas radiated by the number of inhabitants in the nation in thousand metric ton of CO2 emanation
identical. Nitrous oxide is like methane gasses and causes the warming up of earth. This is
likewise straightforwardly identified with the number of inhabitants in the nation. Consequently
the most noteworthy measure of nitrous oxide radiated is by china and after that took after by
United States of America and afterward by India. The nursery gasses cause the warming up of
the earth. The procedure must be halted or else the world may very well be pulverized later on.
The examination of the information of Non-Solid Fuel Access against nation has been plotted on
a range graph. The qualities that has been plotted in the diagram is the level of the number of
inhabitants in the nation that approaches the fluid and vaporous non-renewable energy sources.
The Middle Eastern nations and the created nations of the world are the best most shopper of the
petroleum product. The petroleum derivatives either are uncovered from their nation arrive or is
transported in from different nations creating them. The Saudi Arabia and the USA holds the
biggest repositories of common oils and gasses for the entire world to utilize. The fare them to
different nations at an exceptionally modest cost. The utilization of petroleum products likewise
influences the earth as progressively the measure of non-renewable energy sources are utilized
by the nation the more measure of contamination is made and dirties the air. In this way, it is
fitting for the nationals of the world to decrease the utilization of petroleum products and spare
the world from the contamination.

The investigation of the information of Electricity Access against nation has been plotted in a
tree delineate. The chart has the property of having a little box zone for each of the nation with
the region in light of the power get to and the shading is additionally in view of the measure of
power access of the particular nation. The number speaks to the level of populace of the nation,
which approaches power in their nation. From the information diagram, it can be seen that the
greater part of the nations around the globe has conveniences to give power to the greater part of
its populace. For alternate nations where there is less access of power for the populace, they
ought to consider the choice of giving power to the entire populace of their nation. The best
thought of a similar diagram should look full dim in shading for the improvement of their nation.
From the chart one might say that over half of the total populace has the entrance to power.
The examination of the information of Electric Power Use against nation has been also plotted in
a tree map. The information on the chart signifies the measure of energy utilization as kWh per
Capita of the populace. The measure of utilization of the power straightforwardly influences the
earth in light of the fact that the power is delivered specifically because of the utilization of coals
and petroleum products. This influences nature as CO2 is straightforwardly discharged into the
environment. The most extreme measure of electric power utilize has been recorded by Iceland
and Norway. It ought to be trailed by the general population of the world to confine the
utilization of the power, which would help in diminishing the contamination on the planet.
Predictive Models

Figure 5: Predictive Model 1
The above predictive model is all about air pollution. From the predictive model, it is clear that
green house gases and nuclear energy are the major contributors towards air pollution. Similarly,
forest area, fossil fuel, fresh water, nitrous oxide emissions are also equally responsible for air
pollution.
Again, the predictive model 2 as mentioned below has shown the drivers of co2 emissions. The
below predictive model is also indicating that greenhouse gas emissions, nuclear energy, electric
power use, nitrous oxide emissions, energy intensity, etc are major drivers for co2 emissions.
Figure 6: Predictive Model 2
Social media analysis
It has seen that many of the social media users believes that the social media platform like
facebook, twitter, etc are mainly used to interact with friend, follow celebrities or similar
activities. However, as time passed, such social media platforms started to utilize as a medium of
promoting business. At present all most every organization have their own social media page
through which they interact or reach to their customer. Since, the two out of three people use
social media, such technique help them to promote their products or services effectively than
ever before.

The increasing demand for social media platform in each field influence stakeholders those who
concern about society, started thinking about utilization of social media platform to monitor and
thus control environmental issues like air pollution. The first initiative was taken by China. In
China, a popular social media platform named Sina Weibo, similar to twitter to track real time air
pollution data in different cities in China.
Figure7: Social Media Analysis
Figure 8: Social Media Analysis
In this social media platform, it was measured how many people have posted complaining about
the air pollution aspect. Subsequently, the correlation value between time and space among cities
were measured. From this study, it was revealed that in between 350000 to 500000 Chinese

citizens died only because of air pollution. Now only has that in recent time, social media
platform was used in US as well as several G20 nations to understand the severity level of air
pollution in their respective economic zone. Recent study has also shown that several
governments have adopted social media platform as one of the essential medium to reach every
individual to plea about the seriousness of this issue and invites all populations to step ahead to
prevent such major environmental issue. In addition to this, several government published the
policies related to air pollution and prevention technique and monitor frequently with the help of
social media.
Benefits of BI solutions
The advantages of doing such information examination on an informational index are as per the
following:
 It helps in the ID of the most basic and essential patterns in the earth.
 It causes the association to comprehend the issues in the association, which would require
quick activity (Agarwal, R. what's more, Dhar, V., 2014).
 It shows the information in an outwardly justifiable way, which is less demanding than
understanding columns of information.
 It can help the organization to get an aggressive edge over the rivals in the market.
 It additionally helps in understanding the future pattern in the information.
Recommendations
Till now, the study has been performed to understand what the factors are that causes air
pollution and the current status of air pollution in all G20 nations. The business analytics tools
provides enough support to visualize all such information. Nevertheless, all these dashboards as
well as analysis has effectively identified the causes. Now, it is time to recommend to prevent
such issue all over the G20 nations in near future.
First of all, from the analysis it has been clear that the use of fossil fuel is one of the major
concern behind air pollution. Use of renewable energy will be a fruitful solution to reduce the
usage of fossil fuel and thus reduction of air pollution.

Secondly, consumption of energy beyond requirements leads to air pollution. Hence, mindful
consumption of energy will also results such reduction of air pollution.
Thirdly, recycling of wastage is another mean of reduction of air pollution.
Conclusion
To finish up this report one might say that the utilization of information investigation can help in
the great comprehension of vast measure of information. The discoveries of the dashboards has
been talked about to make the answer to be justifiable for the readers. The report has been
aggregated utilizing diverse charts and outlines. The information of insights can help a man to
comprehend the numbers utilized as a part of the informational collection yet the charts
composed utilizing the information investigation helps in understanding the informational
collection effortlessly.

Reference
Alexandrov, A., Bergmann, R., Ewen, S., Freytag, J.C., Hueske, F., Heise, A., Kao, O., Leich,
M., Leser, U., Markl, V. and Naumann, F., 2014. The stratosphere platform for big data
analytics. The VLDB Journal, 23(6), pp.939-964.
Chang, V., 2014. The business intelligence as a service in the cloud. Future Generation
Computer Systems, 37, pp.512-534.
Chen, Y., Argentinis, J.E. and Weber, G., 2016. IBM Watson: how cognitive computing can be
applied to big data challenges in life sciences research. Clinical therapeutics, 38(4), pp.688-701.
Devarakonda, M. and Tsou, C.H., 2015, January. Automated Problem List Generation from
Electronic Medical Records in IBM Watson. In AAAI (pp. 3942-3947).
Devreese, J. ed., 2013. Highly conducting one-dimensional solids. Springer Science & Business
Media.
Doyle-Lindrud, S., 2015. Watson will see you now: a supercomputer to help clinicians make
informed treatment decisions. Clinical journal of oncology nursing, 19(1).
Gandomi, A. and Haider, M., 2015. Beyond the hype: Big data concepts, methods, and
analytics. International Journal of Information Management, 35(2), pp.137-144.
George, J., Kumar, V. and Kumar, S., 2015. Data Warehouse Design Considerations for a
Healthcare Business Intelligence System. In World Congress on Engineering.
Herath, D.H., Wilson-Ing, D., Ramos, E. and Morstyn, G., 2016. Assessing the natural language
processing capabilities of IBM Watson for oncology using real Australian lung cancer cases.
Hu, H., Wen, Y., Chua, T.S. and Li, X., 2014. Toward scalable systems for big data analytics: A
technology tutorial. IEEE access, 2, pp.652-687.

Isik, Ö., Jones, M.C. and Sidorova, A., 2013. Business intelligence success: The roles of BI
capabilities and decision environments. Information & Management, 50(1), pp.13-23.
Kambatla, K., Kollias, G., Kumar, V. and Grama, A., 2014. Trends in big data analytics. Journal
of Parallel and Distributed Computing, 74(7), pp.2561-2573.
Kimball, R., Ross, M., Mundy, J. and Thornthwaite, W., 2015. The Kimball Group Reader:
Relentlessly Practical Tools for Data Warehousing and Business Intelligence Remastered
Collection. John Wiley & Sons.
Kumar, S., Morstatter, F. and Liu, H., 2014. Twitter data analytics (pp. 1041-4347). New York:
Springer.
Laursen, G.H. and Thorlund, J., 2016. Business analytics for managers: Taking business
intelligence beyond reporting. John Wiley & Sons.