ITECH 7407 Data Analytics Report: Aqua Sipi Business Intelligence

This report presents a comprehensive data analytics project conducted for ITECH 7407, focusing on providing business intelligence solutions for Aqua Sipi, a water purification company. The project analyzes a UNICEF dataset related to drinking water, sanitation, and hygiene. The report details the appli...Read More

Running head: ITECH 7407 0
ITECH 7407
Name of Student
Institution affiliation
0

ITECH 7407 1
Overview
Data analytics is an important skill. The ability to analyze a dataset and derive
meaningful data patterns that can be applied in business is very important and crucial (Furht and
Villanustre, 2016) and (Nikam, 2015). In business, data analytics and business intelligence
reporting have become some very fundamental building blocks of success (Bahari and Elayidom,
2015). The emergence of very efficient tools such SAP HANA web-based platform for data
analytics has even made data analytics and business intelligence reporting much easier. All the
task in the proposal rely on the knowledge and expertise of use of the SAP HANA web-based
platform. At the end of it some important decisions will be made using the results of the data
analytics conducted to make Aqua Sipi better.
Background
Clean and safe drinking water, proper sanitation and the need for proper hygiene are two
of the most fundamentals of healthy living for any human being. Globally, a lot of countries have
made some big steps forward in these three areas. Others are still struggling with the basics of
these key areas of interest. Legally and from the WHO and United Nations standpoint, the access
to safe and ample drinking water is one of the fundamental needs and is now listed as a human
right. Currently, nations are now required by the international law to secure access the three
important items because they are related to the reduction of many diseases and mortality across
all age-sets but with a bias towards children under the age of 10 years.
From the year 2000, the statistics indicate that over 1.4 billion people now have access to
basic drinking water, they have proper sanitation services and they live in a personal space that
has proper hygiene. UNICEF reports that these people get services such as piped water into their
homes and places of work, and the water sources they rely on are well protected in avoidance of
contamination. Further, the 2015 statistics indicate that a total of 844 million people globally still
do not have access to the basic water service and of those, there are up to 159 million of them
that collect water from unsafe and untreated sources such a lakes, rivers and other surface water
springs. The datasets used support and offer a clear picture of the distribution of the use and

ITECH 7407 2
access to drinking water, hygiene and sanitation services. The data covers statistics from every
country in the world for proper comparison.
The dataset and the data included form a very important foundation for the business
analytics report that is being conducted on behalf of Aqua Sipi Incorporated. The company
majors in water purification for human consumption and hygiene. The company also specializes
in water for sanitation purposes. It has operations in four continents and still look forward to
improving and widening the scope to every nation by the year 2030. The data is very important
because it offers Aqua Sipi a basis for which to target the next phase of coverage. The data will
be vital in conducting and generating an innovative analytics solution for Aqua Sipi.
Data Mining
Data mining refers to the process of finding small nuggets of information from an
otherwise large data pool (Allahyari et al, 2017) and (Dua and Du, 2016). The nuggets are based
on some patterns or some indicative characteristics that the data may have and they form part of
the reason why the data in question was collected in the first place (Gandomi and Haider, 2015)
and (Dua and Du, 2016). In the modern day world, data mining is currently one of the most
important disciplines in many fields. The reason data mining has become very important is
because the use of computers and the big migration from analog data keeping to digitization of
data. In the past data was kept in hard copies and that made it very difficult for its analysis in
bulk (García, Luengo and Herrera, 2015). In today’s data collection and storage, digitization and
automation have made it much easier for data collection and storage and has cut down the need
for hard copies. Furthermore, data analysis is now even easier and quite efficient (Ashouri,
Haghighat, Fung, Lazrak and Yoshino, 2018). In the modern day world of super computer
servers and excellent applications that require little skill, data analysis and data mining is now
very possible and very quick. In the Aqua Sipi project at hand, data mining was very quick and
quite productive (Gandomi and Haider, 2015).
The reason why data mining is an important skill is because it requires knowledge
discovery as opposed to the former post data collection techniques is because data mining
becomes more reliable and efficient as the dataset grows in size (Han, Pei and Kamber, 2011).
The modern world has become data oriented (Moro, Rita,and Vala, 2016). There are millions of
computer servers that hold huge amounts of data and the rush today is geared towards ways of

ITECH 7407 3
turning the data into useful information that can be applied in many applications in the various
fields. In the current project, the data is vital because it will form the foundation of a very
important step that Aqua Sipi intends to make in its bid to make itself a company that will have
operations in all the nations of the world.
The data mining techniques chosen in the implementation of the project are very vital and
hold the key towards making the project a success (Agrawal and Agrawal, 2015) and (Li,Wang
and Li, 2015). Therefore, out of the very many approaches in which the data analysts can make
sense of then dataset, they narrowed down to a few data mining techniques. The techniques
chosen when working with the data cube included data classification, data association, time
series technique, and clustering. Using these different techniques, then it became very possible
for the team to come up with a business intelligence solution that the operational manager for
Aqua Sipi can apply and mastermind the growth of the company to a true global conqueror.
Time Series Clustering Technique
The time series technique demands that data be chunked in partition time and similar data
be kept in a related cluster (Shmueli, Bruce, Yahav, Patel, and Lichtendahl, 2017). Under this
technique, the most important process is what referred to as the dynamic time warping (Tan,
2018) and (Raj, 2016). The dynamic time warping procedure is crucial because it aligns data in
the two or more time series chunks based on the dataset composition. For instance, in the
UNICEF dataset we used for drinking water, sanitation and hygiene, we have 464 items of the
control chart for each of the three major items. From the three major items, we have 43 values
for each. The breakdown of these into times series results into a distribution matrix as derived
from the HANA data cube and it is shown in figures 1.1 and 1.2 below

ITECH 7407 4
Figure 1.1
Figure 1.2
Association Technique
Association technique is a commonly used technique and it delivers accurate and
eye-opening results if well applied (Tan, 2018). In the project, the association technique was
very vital because it brings out some very distinct patterns on the data. For instance, using the
technique, it is very clear that every nation listed in the dataset has made some drastic
improvements in all the three areas of sanitation, hygiene, and in the provision and access of
drinking water. The graphical pattern for two the countries which are France (representing the

ITECH 7407 5
first world countries) and Egypt (representing the third world countries) are indicative of the
pattern. Any trend that the operational manager for Aqua Sipi may need from the dataset can be
derived from the data and it will offer a key nugget of information from the dataset.
Figure 1.3

ITECH 7407 6
Figure 1.4
Classification Technique
The classification technique is simple and stands as the oldest data mining techniques
available (Gonzalez, Tahsin, Goodale, Greene, and Greene, 2015) and (Singh and Yassine,
2018). The technique has now been simplified and made more resourceful due to the modern
advancement in machine learning (Chen, Deng, Wan, Zhang, Vasilakos, and Rong, 2015) and
(García, Luengo, and Herrera, 2016). The SAP HANA web-modeling tool is based on some
great deal of machine learning and it immensely simplified the classification process. The tool
was vital in developing the required decision trees and the foundations of linear programming
that are necessary in the business intelligence reporting required in the Aqua Sipi project. As an
example, the technique was used in classifying all the countries based on their urban and rural
sanitation services deficits for countries that Aqua Sipi does not operate. From the deficits list,
the project manager then has some evidence of the countries that Aqua Sipi does not operate in
but have some serious deficits in terms of sanitation. The information is of great value because
the management can then decide on which ones to start operations based on the mined data as
opposed to relying on the entire dataset.

ITECH 7407 7
Figure 1.5
Research
As a science, data mining is very vital because it dictates that the researcher or the
practitioner justify the means used to come up with a specific solution. As discussed earlier, the
project used several techniques to come up with the business intelligence report that forms the
basis for which Aqua Sipi is meant to use to grow its business and extend its reach globally. The
three techniques used in task 3 were chosen for a reason. First, time series clustering was used
because it allows for the chunking of related data into manageable and related sizes for easier
analysis. During data mining, one of the goals of the project was making a business intelligence
recommendations on the countries that Aqua Sipi will operate based on the need and the
sanitation patterns. Next, the association technique was vital in linking and relating the subsets of
the datasets based on certain attributes that they possess. For instance in the dataset, related
attributes such as the countries poor urban sanitation but with fresh water sources in the rural
areas require an association of the two attributes (Chaurasia and Pal, 2017) and . The dataset
points that bear the information when deduced graphically tell a very clear story based on the
relationship between the two and together form a good and business intelligent sub-report
applicable in management decision making (Murray and Scime, 2015). Thirdly, the classification
techniques was chosen because there were other data points that required a technique that will
group data points together so that these can be analyzed together. In the project, it would not be
possible to analyze data points of countries based on their regions or based on their per capita
without the classification technique.

ITECH 7407 8
After explaining the justification behind the use of the three selected data mining
techniques, it is vital that the project lead explains the justification behind the business
intelligence reporting solution applied (Yassine, Singh and Alamri, 2017). The reporting was
preferred because it is uses a hierarchical process that factors in raw data and turns that into
cleaned data. The cleaned refers to the data that has been classified into vivid visualizations that
can be altered depending on the changes to some items on the dashboard. The data is then turned
into standard reports and then to ad hoc and OLAP reports as a way of giving it meaning and
weight. Then agile visualizations are made and from these the project manager can report on the
very detailed information that form the foundational building blocks of a proper data mining
process. After that the data mined can now be put through the predictive analysis stage and later
through the optimization stage that focuses on what best could happen based on the results from
the predictive analysis and modeling stages carried out.
The only assumption that is made in this project was that the Aqua Sipi required the full
length maturity capabilities possible from the data sets. Therefore the project manager analyzed
and reported on the data from the first step of data analytics capability which is raw data, all the
way to the last step which is optimization. All the visual samples derived from the reports are
attached within the write-up whereas the rest are attached in the appendix section of the report.
Recommendations for CEO
The CEO of Aqua Sipi is Ms. Janet Ashira. She has made it very clear that she wants to
improve the operations of the company. She therefore expects some fact-based recommendations
from the team conducting the research and data analytics. The recommendations are as discussed
below.
Logical Recommendations
In light of extensive data analytics conducted in the study, there are several
recommendations that can be made and the CEO should consider them during decision making.
First, the logical thing that the company that has operations in more than 200 countries and areas
would be to look at the countries and areas that have the least favorable figures on all data on
sanitation, hygiene, and drinking water. The reasoning behind the recommendation is because
these areas are unclaimed business frontiers and they will form the basis for the future revenue.
From the data analyzed, these countries and areas are mostly in South America, South Asia and
in Sub-Saharan Africa. In most cases, the areas have large water bodies but the relevant

ITECH 7407 9
technologies applicable in delivering water for drinking, for hygiene and proper sanitation seems
to be lacking. The areas are also purely of nations that are developing. Developing countries may
not lead to immediate revenue and high profits, but in the long-run, Aqua Sipi may find itself
with a proper business monopoly in many of the nations because the nations have not many large
firms investing in the water and sanitation services. The other key factor is that the nations have
a growing population so each passing day strains the water resources further and as a domino
effect then that leads to a rising demand for water and sanitation.
Another logical recommendation to the CEO would be to find ways and means of
forming partnerships with governments of the different countries in the target countries as
opposed to staring the water services enterprises as standalones. The importance here is that in
these countries water and sanitation services are seen as pure roles and responsibilities of the
government and therefore they own all the infrastructure. The partnership would therefore see
Aqua Sipi have access to already established infrastructure and hence lead to lowered costs.
Lowered costs is an important advantages especially because the predictive analysis indicates
that there is not much to be made in terms of revenue in the first decade because it will take time
to fully operationalize the water and sanitation systems in many of the third world targeted.
The last logical recommendation would be that the CEO must try and apply the best
practices used in the developed countries in the developing countries. For instance, there are
many good practices that Aqua Sipi uses in managing water resources in nations like France,
Germany, Japan and Canada that are applicable in the third world nations. For example, Aqua
Sipi relies on the assistance of small council sub-contractors when it comes to the distribution of
sanitation water, litterbins, and also in the preparation and packaging of drinking water. The
subcontractor understand the regions and areas they serve very well and therefore make it much
easier for Aqua Sipi to streamline its business model and rake in more profits through increased
efficiency and reliability. In the developing countries, the same could be replicated and that
would get much of the work efficient too. In Egypt, sanitation is handled very efficiently but
provision of drinking water is still not very efficient. Aqua Sipi’s entry into the market can go on
and streamline the provision of drinking water by ensuring that they work with reliable sub-
contractors who will prepare and distribute safe drinking water for all at fair prices. The same
goes for provision of hygiene-related services and equipment services.

ITECH 7407 10
Cover Letter to the CEO
Johnas King
897-8989-899
Sydney, Australia
To:
Ms. Lina Hendrix
Chief Executive Officer
Aqua Sipi Inc.
3784 Dewtone Avenue
Sydney, Australia
RE: ABOUT DATA INSIGHTS AND RECOMMENDATIONS AND OBJECTIVES
Important data insights and direct and workable recommendations are vital in
achieving operational and strategic objectives. Therefore to take it upon ourselves as the
researchers to justify the proposals have developed and also offer explanation on how it will
contribute towards the advancement of Aqua Sipi Inc. The proposal we worked on is supposed to
act as very important foundation for the business analytics report that is being conducted on
behalf of Aqua Sipi Incorporated. As a company that majors in water purification for human
consumption and hygiene for the global market, the statistics on global water sanitation and
hygiene are of great usefulness. The data is very important because it will offer Aqua Sipi the
basis for which to target the next phase of coverage and enable the management form a
springboard for the next business frontier. The data has been vital in conducting and generating
an innovative business intelligence analytics solution for Aqua Sipi.
As per the information gathered from Aqua Sipi Inc, main strategic objective for the
organization is the expansion of business operations across all nations and areas of the globe. On
this objective, the proposal offers a very crucial springboard because the proposal converges all
the data complete with the visualizations of the areas and nation that require a proper supply of
drinking water, sanitation and good hygiene. Therefore based on completed data insights in the

ITECH 7407 11
SAP HANA work the CEO will rely on the data and decide which nations Aqua Sipi will set up
operations in the next phase, a trend which is supposed to culminate to full global coverage by
the year 2030.
Operationally, Aqua Sipi plans on increasing its coverage in Africa because most of the
unclaimed business in water and sanitation are in the African continent. According to Dewan and
Sharma (2015), Africa is one of the most important market in the globe right now. We therefore
have substantiated the claim by backing it with real data. Based on the insights, the continent has
a growing demographic of youths and the population is currently over 1 billion people. With that
kind of a population, the continent acts a solid market for any business venture. Water and
sanitation services are not very well organized in most of the African countries and Aqua Sipi
expanding its operations in many African countries means more revenue and an increase in the
operational challenges. Nonetheless, the business risk is worth taking and the returns, though not
immediate will still form a good incentive due to the promising nature of the market within the
next decade.
Thank you for your consideration
Johnas King
Conclusion
Based on the tasks conducted and data analyzed, it is right to conclude that data analytics
is an important skill. The Aqua Sipi case study is proof that businesses can rely on data analytics
to make decisions. The Aqua Sipi case and the data used to come up with the business analytics
report have culminated to the researcher proposing some real-life solutions to the CEO of Aqua
Sipi.

ITECH 7407 12
References
Agrawal, S., & Agrawal, J. (2015). Survey on anomaly detection using data mining
techniques. Procedia Computer Science, 60, 708-713.
Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E. D., Gutierrez, J. B., & Kochut, K.
(2017). A brief survey of text mining: Classification, clustering and extraction
techniques. arXiv preprint arXiv:1707.02919.
Ashouri, M., Haghighat, F., Fung, B. C., Lazrak, A., & Yoshino, H. (2018). Development of
building energy saving advisory: A data mining approach. Energy and Buildings, 172,
139-151.
Bahari, T. F., & Elayidom, M. S. (2015). An efficient CRM-data mining framework for the
prediction of customer behaviour. Procedia computer science, 46, 725-731.
Chaurasia, V., & Pal, S. (2017). A novel approach for breast cancer detection using data mining
techniques.
Chen, F., Deng, P., Wan, J., Zhang, D., Vasilakos, A. V., & Rong, X. (2015). Data mining for the
internet of things: literature review and challenges. International Journal of Distributed
Sensor Networks, 11(8), 431047.
Dewan, A., & Sharma, M. (2015, March). Prediction of heart disease using a hybrid technique in
data mining classification. In 2015 2nd International Conference on Computing for
Sustainable Global Development (INDIACom) (pp. 704-706). IEEE.
Dou, D., Wang, H., & Liu, H. (2015, February). Semantic data mining: A survey of ontology-
based approaches. In Proceedings of the 2015 IEEE 9th international conference on
semantic computing (IEEE ICSC 2015) (pp. 244-251). IEEE.
Dua, S., & Du, X. (2016). Data mining and machine learning in cybersecurity. Auerbach
Publications.

ITECH 7407 13
Furht, B., & Villanustre, F. (2016). Big data technologies and applications (pp. 978-3). Springer
International Publishing.
Gandomi, A., & Haider, M. (2015). Beyond the hype: Big data concepts, methods, and
analytics. International journal of information management, 35(2), 137-144.
García, S., Luengo, J., & Herrera, F. (2015). Data preprocessing in data mining (pp. 59-139).
New York: Springer.
García, S., Luengo, J., & Herrera, F. (2016). Tutorial on practical tips of the most influential data
preprocessing algorithms in data mining. Knowledge-Based Systems, 98, 1-29.
Gonzalez, G. H., Tahsin, T., Goodale, B. C., Greene, A. C., & Greene, C. S. (2015). Recent
advances and emerging applications in text and data mining for biomedical
discovery. Briefings in bioinformatics, 17(1), 33-42.
Han, J., Pei, J., & Kamber, M. (2011). Data mining: concepts and techniques. Elsevier.
Li, D., Wang, S., & Li, D. (2015). Spatial data mining. Berlin, Heidelberg: Springer Berlin
Heidelberg.
Moro, S., Rita, P., & Vala, B. (2016). Predicting social media performance metrics and evaluation
of the impact on brand building: A data mining approach. Journal of Business
Research, 69(9), 3341-3351.
Murray, G. R., & Scime, A. (2015). Data Mining. Emerging Trends in the Social and Behavioral
Sciences: An Interdisciplinary, Searchable, and Linkable Resource, 1-15.
Nikam, S. S. (2015). A comparative study of classification techniques in data mining
algorithms. Oriental journal of computer science & technology, 8(1), 13-19.
Raj, K. B. (2018, October). Opinion Mining Techniques-A Review. In ICRTEMMS Conference
Proceedings (Vol. 583, No. 587, pp. 583-587). Swarna Bharathi lnstitute of Science and
Technology.

ITECH 7407 14
Shmueli, G., Bruce, P. C., Yahav, I., Patel, N. R., & Lichtendahl Jr, K. C. (2017). Data mining for
business analytics: concepts, techniques, and applications in R. John Wiley & Sons.
Singh, S., & Yassine, A. (2018). Big data mining of energy time series for behavioral analytics
and energy consumption forecasting. Energies, 11(2), 452.
Tan, P. N. (2018). Introduction to data mining. Pearson Education India.
Yassine, A., Singh, S., & Alamri, A. (2017). Mining human activity patterns from smart home big
data for health care applications. IEEE Access, 5, 13131-13141.

ITECH 7407 15
Appendix
Figure 1.6

ITECH 7407 16
Figure 1.7

ITECH 7407 17
Figure 1.8