Food Consumption and Production Analysis: A Global Perspective

This project delves into the global food consumption and production landscape, analyzing a comprehensive dataset from 1961 to 2013. Using IBM Watson Analytics, we explore key trends, outliers, and growth patterns in food production and consumption across various countries and continents. The analysis aims to provide insights for a Global Food Consulting Firm, focusing on factory farming and animal agriculture, to understand food management strategies and identify potential areas for growth and optimization.

Table of Contents
BACKGROUND INFORMATION.........................................................................................................3
DESCRIPTION...............................................................................................................................3
DATASETS AND FIRM...................................................................................................................3
PROJECT IMPROTANCE................................................................................................................3
REPORTING......................................................................................................................................4
RESEARCH........................................................................................................................................6
RECOMMENDATIONS....................................................................................................................10
COVER LETTER................................................................................................................................11
List of Figures
Figure 1: Dashboard for the Basic Work..........................................................................................4
Figure 2: Dashboard for the Advanced Work..................................................................................5
Figure 3: Outliers in the Data using the Breakdown Diagram.........................................................6
Figure 4: Outliers in Data using the Distribution Graph..................................................................6
Figure 5: Bar Graph for finding the Fastest growing countries.......................................................7
Figure 6: Comparison between Food and Feed consumption in the year 2013.............................8
Figure 7: Comparison between Food and Feed consumption in the year 1961............................8

BACKGROUND INFORMATION
Description of Project, Datasets and firm. The importance of the project for the firm
DESCRIPTION
The aim of this project is to gain the insight over the datasets using the Business Analytics skill.
This project is developed for the Global Food Consulting Firm that is working in the field of
Factory Farming along with Animal Agriculture. This project is aimed to analyse which countries
are able to manage all the available food resources in effective and efficient manner. Further,
this project is based on analysing the dataset that is available and how could analysing that data
could help in establishing the Business Marketing analytics in Real-time (Pllana, Memeti and
Chozas 2017).
DATASETS AND FIRM
The dataset that is used in this project is available from the data.the world, the dataset is based
on the overall consumption of Food from the Year 1961 to the year 2013 for different countries
present (Trivedi, Mesterhazy, Laguna et al). The main dataset is taken from
https://data.world/mchadhar/worldfood-dataset. The dataset includes over 245 countries data
in a systematic manner. The first dataset chosen is the Food Balance Sheet. As it helps in
providing a pattern for the analysing the comprehensive picture over the supply of all countries.
This dataset is going to help in determining the food supply and utilization of food in all the
countries by the implementation of the food balance sheet. Further, this dataset is going to be
focused on the utilization of the food Items available. This dataset is based on the food and
feed utilization (Chozas, Memeti & Pllana 2017).
Dataset link: https://www.ers.usda.gov/data-products/food-availability-per-capita-data-
system/food-availability-per-capita-data-system/#Food%20Availability
Firm in this Project is Global Food Consulting Firm. This firm is based in Factory Farming and
Animal Agriculture area. Apart from this, the Firm needs to know what are the strategies that
could be implemented over dataset for better implementation of the food management and its
adoption (Eysenbach, Bhattacharya, McGregor, Ramachandran, Hoyt, Mantravadi 2016).
PROJECT IMPORTANCE
This project is going to be used by the Consulting Firm in order to analyse the food usage in
different countries and any method that could be adopted in finding out which country is highly
efficient in managing the food resources. This is done by using IBM Watson as a BI analysing
tool. Further, this project is going to help the firm in depicting some other values by the data
analytics (‘IBM to Collaborate with Nuance to Apply IBM's 'Watson' Analytics Technology to
Healthcare’ 2011).

REPORTING
This phase is going to be working for performing the relevant Data Analysis tasks in order to
perform the several questions in order to create a BI solution that could help in making the
decision for the analysis. There are several questions that are to be analysed in order to make a
predictive Recommendations for the CEO later (Poole, Goodson, Melissa, & Smith, Joanne
2016). The Global Food Consulting Firm is going to be using this analysis report in order to find
out how can they target a specific region in order to efficiently manage the food production and
Consumption rates in the countries. Further, this will help in analysing the dataset that could
help in the better strategical planning of the development of the whole process.
Basic Work Dashboard
Figure 1: Dashboard for the Basic Work
Figure 1 represents the Dashboard Image of the Basic Work that has been performed in order
to analyse the Dataset. The main aim of this dashboard is to display all the Discoveries that are
done for the Basic Work. This is going to help in making a better system analysis design model
from the basic needs. For this IBM Watson tool is used. IBM Watson Analytics is a tool that is
used to decrease the complexity of the data analysis. The data analytics tool is used to enhance
the relationships by help in discovering the correlations of the system. This tool is also going to
help in creating a tool that can help in creating a smart analysis over the data and it can also
help in automatic predicting for the data (Nagwanshi & Dubey 2018).
Using IBM Watson, Basic Work is analysed it is done in order to find out the analysis of the food
data. It is going to help in making the analysis report from the provided data (Guidi, Miniati,
Mazzola, & Iadanza 2016). Also, by this analysis, those countries that are consuming the food at
a very fast rate are depicted. This dashboard also shows the analysis by which we can analyse
the consumption of food with the consumption of feed. The food all the amount of eatable
food that is available for the human from 1961 to 2013 (‘IBM to Collaborate with Nuance to
Apply IBM's 'Watson' Analytics Technology to Healthcare’ 2011). While the feed is the eatable
food available for the livestock during 1961 to 2013. This analysis is going to help in creating a
systemic Business plan on what are the countries that need to focus much more than the other

countries or what are the countries that are highly efficient in the management of the food
products (Poole, Goodson, Melissa, & Smith 2016).
Advance Work Dashboard
Figure 2: Dashboard for the Advanced Work
Figure 2 is the dashboard for the advance work in which another dataset is used. Further, this
analysis is going to help in deciding:
 What is the per capita consumption of the Food around the world?
 What is the population density for the food consumption and production?
 What is the inequality between the food distribution?
 What is the meat supply according to the continents?
IBM Watson Analytics is the tool that is going to produce the analysis report for the Advance
Work. IBM Watson is chosen because it is easy to use and the User Interaction is very
understandable. Further, IBM Watson provides some questions from itself and this could help
in understanding the data prior to the analysis. IBM Watson also helps in depicting the quick
trends in the data that could be used in order to find interesting outliers in the data. It also uses
a predictive modelling technique by which the system is going to create a better solution over
any dataset (Guidi, Miniati, Mazzola, & Iadanza 2016). Some important features that it
possesses are that it helps in creating a tool that helps in smart recovery and better data
visualizations. The Data Visualization is going to help in creating graphs and another model that
could help in building a better Business plan. IBM Watson also provides a tool by which the
Competitive Intelligence of the data could be found out.
To analyse this data much further and gain more insight over the chosen data IBM Watson
could use Decision Making and other predictive modelling techniques that can help in making
the analysis much better and could help the Global Food Consulting Firm in depicting the data
much more efficiently and a better data analysis could be done over that data. The analysis of
this dataset is going to help in creating a strategy that could help in depicting the country that

can manage the food resources for this country. IBM Watson is going to help in creating a
solution that can help in making this analysis for the Global Food Consulting much better.
RESEARCH
In task 2 that is the Reporting task, there were two dashboards that were made for Basic work
and Advanced work. For the Basic work, there was three question that needs to be answered
for in order to create an analysis of the given data. Those questions are:
A. Can you find interesting outliers in the data?
The outlier means an observation point that can help in reducing different types of information.
Outliers are the key points in any Data Analytics (Gaardboe, Nyvang, & Sandalgaard 2017). As
agriculture in Animal and poultry farming is growing rapidly the firm needs to make sure that
there are countries that are progressing in this area of food consumption and production. This
Outlier is going to help in finding those critical data that is going to be helpful in depicting that.
For food, the area code 231 is also one of the top contributor consumed human food.
Figure 3: Outliers in the Data using the Breakdown Diagram

Figure 4: Outliers in Data using the Distribution Graph
The above graph only depicts the values for the year 1961 by both of the elements and with the
respective area codes. Form the above diagram some of the data that could be depicted is that:
Feed consumption is much more in the area code 231 which represents the United States. Food
Consumption breakdown shows that the highest consumption is done in the 41 area_code
segment that represents the China Mainland (Botoş 2017).
The above figure is a Breakdown figure that is chosen because it is very helpful in finding out
the main regions on which this research could be centred. Further, the breakdown is going to
help in finding out the regions that could be helpful in making the analysis much better (Weng,
Yang, Koo & Hsiao 2016).
B. What are the fastest growing countries in terms of food production\consumption?
Figure 5: Bar Graph for finding the Fastest growing countries
Figure 5 represents a Bar Graph of the year 1961 that could help in finding out the food
products that are widely used in the fastest growing country. Further, this graph is also going to
provide a significant idea by which the analysis report could be created for the firm for better
finding implementation of this data.

C. Compare food and feed consumption
Figure 6: Comparison between Food and Feed consumption in the year 2013
Figure 7: Comparison between Food and Feed consumption in the year 1961
The food and Feed Consumption is done over two years one in 1961 and the other is 2013.
Figure 6 represents the food and feed comparison between the all the countries in the year
2013. So, the year 2013 shows that the most food consumed by the China mainland and the
second best consumption is done by the United States. The feed consumption is the
consumption of eatable food that is done by the poultry animals within the year 2013. Further,
the data shows that many other countries have the same type of distribution but on the lower
scale like Iceland or Botswana they have the same food and feed distribution like the China and
United States Respectively (Nedelcu 2014).
Figure 7 shows the Comparison between Food and Feed consumption in the year 1961. This
shows that China was not a major contributor to the feed in that year leaving the United States
to be the top feed consumption country that year. Further, the data for the food consumption
shows that China was main consumption country for food that year and Hungary follows with the
United States (Zhang, Ren, Liu, & Si 2017).

The main purpose of choosing these diagram is to find the main techniques that could be used in order
to analyze the data much efficiently. Another Distribution diagram was also analysed but they were not
supporting the hypothesis using which the data could be analyzed.
Advanced Work
A. World Food production and consumption by per capita?
From the above diagram, the total production and consumption of the food per capita in all
over the world is being described. There are various producers all over the world who produce
the food capita and increase the production rate. There is also a large number of consumers
who are responsible for the consumption of that food. In the diagram, the various colour circle
represents the average production per capita of food all over the world. In the right side of the
diagram, the average production is shown by making a comparison of the various import retails
and their total production per capita from all across the world. Per capita production or
consumption defines more accurate result and can help in achieving the extra growth in future
for various food items. These reports and analysis are made by doing various surveys and
efforts by the firm (Tang, Norman & Vendrzyk 2017).

B. World food production and consumption according to population density (divided by
population in each country) in 2013 (particular year/s)
According to the survey, the total production and total consumption are defined by the
population density of the work for each country for the particular year. In the above graph, the
vertical scale represents the average production rate and on the horizontal scale, it represents
the total U.S population for the month of July and the particular year 2012. In the above
diagram, the graph describes the total production contribution to the population of the U.S
country for the July month for the particular year of 2012 (Ur Rehman, Batool, Liew, Teh & Ur
Rehman Khan 2017). This shows the continuous growth in the contribution production over the
population of the U.S. by the increases in the population the production is also increased. As
more population requires more amount of consumption, therefore, the production is also
increased by increasing. As per the density of the population, the production and consumption
rate varies from region to region. At some lower populated region, the consumption is more
and in higher populated regions consumption is more. It depends on the total productivity and
consumption rate of the food and the analytical reports for various regions.

C. Inequality of Food production/ consumption by region/continents?
In this, the reports and graph are discussed for the inequality of the production and
consumption of food given by various regions and constituents. In the above graph, the vertical
scale represents the total average production rate and the horizontal scale represents the
carcass produces. The graph defines the comparison between the average production and the
average imports. In the graph line values with green colour represent the average imports and
the column value with the blue colour and it shows the average production. With the increase
in the production, the growth of carcass is also increasing. Import value is very low in the
starting but it takes the exponential change after the one-point value. The average production
is increasing linearly by the continuous increase in the carcass.

D. The global perspective of meat supply by region/continents? (Item Code 2731 to 2735
student have to check more carefully is there any item code which associated with
meat).
In the above question, the supply of meat over various regions or continents having some item
code for the meat from the global perspective or view. In the above diagram, the vertical scale
represents the area or location or simply different countries which supply the meat globally.
And on the horizontal scale, it represents the item code as per the area or location. In this
graph, the compatibility of each area with the item code is given on a large scale. The defined
item code for the individual region help in the better calculation of the total production,
consumption, and supply of the per capita unit (Coatney & Safari 2017).

Justification of Choosing these Graphs for Representation
There are several types of graphs that were analysed in order to detect data. The graphs that were used
as much Noise meaning the Visualised data that were representing was not helpful in understanding
what kind of result they need to show. The visualised data needs to be highly self-explanatory as it is
going to help the firm in finding out what are the basic result of the data analysis of the featured data
diagram. Also, the Graphs that are used in this report is highly self-explanatory for the analysis and that
diagram could be easily understood by the CEO. The Analytical approach used in order to perform this
data analysis needs to be efficient that can only be done if the Visualized Diagram is highly explanatory
and could help in depicting the Information flow in order to help in creating better Business Planning.

RECOMMENDATIONS
The data analysis is done for the food data in order to find out a better analysis of that file
system. This system poses a lot of bugs that need to be analysed before but these bugs possess
a lot of positive points that can help in making the system much more efficient. There are some
are in which the CEO needs to work in order to make a better prediction for the future work.
So, by implementing those changes in the system the system analyst could help to order to
minimize those bugs with the associated risks. Without the analysis at present, the user or the
Firm has to put a lot of efforts for understanding that data (Chen, Elenee Argentinis & Weber
2016).
The recommendation made to the CEO are:
 Every country data should be saved separately
 Every year data should be saved in the different workbooks
 Complexity could be reduced by this
 The metadata should be clearly defined
 The Location data should be defined more clearly
 The data should be Managed in different cells
 There should be a proper distribution of the data in the separate sheets
 The year wise separation of the data has to followed that can help in making a better
understanding in the system
 A separate data sheet should be managed in order to manage the Food and Feed
Consumption
 Along with a meat data that needs to be implemented in a different sheet
The above recommendations are some of the many recommendations that could be
implemented by the CEO right now. Other recommendations include those recommendations
that could be applied when the system is applying those data mining techniques on the present
data.

COVER LETTER
To,
The CEO
Global Food Consulting firm
Date: May 23, 2017
Subject: Recommendation and vision that can help in Achieving vision and Objectives
Sir,
The Food data along with one other dataset is analysed thoroughly. The Data that was provided
by you have some analysis importance and that data is going to help in creating a better
analysis model for your firm. The Analysis that has been done is going to help in creating a
better analysis model which in turn help in getting a better understanding for the user
perspective. The Current scenario is analysed and that data is going to help in creating and
understanding the implementation of the analysis model. After, analysis of this data I have
found some recommendations that could be useful for the firm.
 The Company should create a staff that is going to help in making better datasets
 The responsiveness must be increased in data collection
 The countries whose data is not present in the current dataset needs to be added
 The firm should focus on underdeveloped countries for their betterment
Sincerely
Student Name

REFERENCES
1. S, Pllana, S, Memeti, and C, Chozas 2017, ‘IBM Watson, IDx collaborate on imaging
applications’, Slack Incorporated, Viewed from
https://search-proquest-com.ezproxy.cqu.edu.au/docview/1902613428?
accountid=10016
2. Trivedi, H, Mesterhazy, J, Laguna, B et al, ‘J Digit Imaging’ 2018, 31: 245, https://doi-
org.ezproxy.cqu.edu.au/10.1007/s10278-017-0021-3
3. Chozas, Memeti, & Pllana 2017, ‘Using Cognitive Computing for Learning Parallel
Programming: An IBM Watson Solution’, Procedia Computer Science, 108(C), 2121-2130.
4. Eysenbach, G, Bhattacharya, S, Li, C, McGregor, C, Ramachandran, A, Hoyt, R, . . .
Mantravadi, S 2016, ‘IBM Watson Analytics: Automating Visualization, Descriptive, and
Predictive Statistics’. JMIR Public Health and Surveillance,2(2), E157.
5. IBM to Collaborate with Nuance to Apply IBM's 'Watson' Analytics Technology to
Healthcare 2011, Biotech Week, 490
6. Nagwanshi, K, & Dubey, K 2018, ‘Statistical Feature Analysis of Human Footprint for
Personal Identification Using BigML and IBM Watson Analytics’, Arabian Journal for
Science and Engineering, 43(6), 2703-2712
7. Guidi, G, Miniati, R, Mazzola, M, & Iadanza, E 2016, ‘Case Study: IBM Watson Analytics
Cloud Platform as Analytics-as-a-Service System for Heart Failure Early
Detection’, Future Internet,8(3), 32
8. Data discovery and q&a power of Watson Analytics: Half a million professionals access
IBM Watson Analytics in less than a year, (2015), Software World, 46(6), 23.
9. Poole, J, Goodson, Melissa, & Smith, Joanne 2016, ‘Lucy: IBM Watson Analytics Meets
Madison Avenue—Considering Cognitive Computing Artificial Intelligence Tools
Employed for Advertising Media Planning and Buying’, ProQuest Dissertations and
Theses.
10. IBM to Collaborate with Nuance to Apply IBM's 'Watson' Analytics Technology to
Healthcare 2011, Biotech Week, 490.
11. Nagwanshi, K, & Dubey, K 2018, ‘Statistical Feature Analysis of Human Footprint for
Personal Identification Using BigML and IBM Watson Analytics’, Arabian Journal for
Science and Engineering, 43(6), 2703-2712.
12. Guidi, G, Miniati, R, Mazzola, M, & Iadanza, E 2016, ‘Case Study: IBM Watson Analytics
Cloud Platform as Analytics-as-a-Service System for Heart Failure Early
Detection’, Future Internet,8(3), 32.
13. Poole, J, Goodson, Melissa, & Smith, Joanne 2016, ‘Lucy: IBM Watson Analytics Meets
Madison Avenue—Considering Cognitive Computing Artificial Intelligence Tools
Employed for Advertising Media Planning and Buying, ProQuest Dissertations and
Theses’.
14. Arsenault, H 2017, ‘Statistical Screen: Synthesis Design Architecture and IBM Watson
Analytics collaborate on a data-driven installation’, Contract, 58(5), 136.

15. Nedelcu, B 2014, ‘Business Intelligence Systems’, Database Systems Journal, (4), 12-20.
16. Kao, Hao-Yun, Yu, Min-Chun, Masud, Mehedi, Wu, Wen-Hsiung, Chen, Li-Ju, & Wu, Yen-
Chun Jim 2016, ‘Design and evaluation of hospital-based business intelligence system
(HBIS): A foundation for design science research methodology, Computers in Human
Behavior’, 62(C), 495-505.
17. Gaardboe, Nyvang, & Sandalgaard 2017, ‘Business Intelligence Success applied to
Healthcare Information Systems’, Procedia Computer Science, 121, 483-490.
18. Botoş, H 2017, ‘Bitcoin Intelligence – Business Intelligence meets Crypto Currency. CES
Working Papers’, 9(3), 488-505.
19. Weng, S, Yang, M, Koo, T, & Hsiao, P 2016, ‘Modeling the prediction of business
intelligence system effectiveness’, SpringerPlus, 5(1), 1-17.
20. Zhang, Ren, Liu, & Si 2017, ‘A big data analytics architecture for cleaner manufacturing
and maintenance processes of complex products, Journal of Cleaner Production’, 142,
626-641.
21. Wang, Kung, & Byrd 2018, ‘Big data analytics: Understanding its capabilities and
potential benefits for healthcare organizations, Technological Forecasting & Social
Change’, 126, 3-13.
22. Ur Rehman, M, Batool, A, Liew, C, Teh, Y, & Ur Rehman Khan, A 2017, ‘Execution Models
for Mobile Data Analytics’, IT Professional, 19(3), 24-30.
23. Tang, F, Norman, C, & Vendrzyk, V 2017, ‘Exploring perceptions of data analytics in the
internal audit function’, Behaviour & Information Technology, 1-12.
24. Coatney, M, & Safari, an O’Reilly Media Company 2017, ‘Introduction to Cognitive
Computing with IBM Watson Services’, 1st ed.
25. Chen, Elenee Argentinis, & Weber 2016, ‘IBM Watson: How Cognitive Computing Can Be
Applied to Big Data Challenges in Life Sciences Research’, Clinical Therapeutics, 38(4),
688-701.