MITS6002 Business Analytics Research Report Sample
Instruction: You are required to submit 2500± 10% words report on the below tasks. Use appropriate headings and subheading in your report.
Task 1: Pivot table exercise
Collect the “Online Retail” dataset from UCI Machine Learning Repository
(https://archive.ics.uci.edu/ml/datasets/online+retail#). Carefully observe the dataset and apply analytics to find answers for the below queries:
I. List the top 5 countries where the greatest number of invoices were generated from and their corresponding number of invoices.
II. Produce a list of customers (CustomerIDs) that placed at least 1000 invoices and include their corresponding number of invoices for customer loyalty program.
III. Generate a pivot table and a suitable chart showing Monthly Invoice counts for the year of 2011.
IV. Identify the months with the highest and lowest number of invoices and comment on the visible sales patterns in the chart.
Task 2: Data Exploration
Collect the “Irish Flower” dataset from any public data source, e.g., the UCI Machine Learning Repository, (https://archive.ics.uci.edu/ml/datasets/iris). Then perform the following tasks:
I. Clearly mention the source where you have collected the dataset. Include a screenshot and URL of the source.
II. Specify the basic details of the dataset, including the number of attributes, names of the attributes, number and names of the classes and the mean and standard deviation of the attribute variables.
III. Convert the dataset into a .csv file with the attribute column headers as Sepal_length, Sepal_Width, Petal_Length, Petal_Width and the 5th column as “Class”.
IV. Normalise the attributes using the following formula:
xi ′ = xi−min (X) ∀xi ∈ X, 0 ≤ xi ′ ≤ 1
max(X)−min (X),
V. Use an analytics tool of your choice (e.g., MS Excel) to compute the class-wise mean and standard deviation of the attributes and present your answer as the table shown below.
.png)
VI. Use an analytics tool of your choice to generate a suitable graph taking only the class-wise mean values of the attributes and comment on how the classes show separability in this dataset.
Justify your answer with screenshots.
Task 3: Correlation Analysis
Correlation analysis is a commonly used technique to find relationships among variables. Perform the below tasks.
I. Data collection: Collect height and weight data from 20 friends/relatives of yours and complete the below table. Every student in class should have a unique set of values.
.png)
II. Analysis & Reporting: Use an analytics tool of your choice to find the correlation between these variables.
Briefly explain with screenshots of analytical tool you used and how you performed this correlation analysis.
Task 4: Written Exercise
Topic: Security, Privacy and Ethics in Business Analytics.
In this task, you are required to write a short report based on the topic of security, privacy and ethics in Business Analytics. You must:
I. identify the major security, privacy, and ethical implications in Business Analytics
II. briefly describe the significance of these implications in business sector
III. support your response with appropriate examples and references
The recommended word length for this task is 1000± 10%words.
Solution
Task 1
I.
The table given below shows the information about the top 5 countries where the greatest number of invoices were generated.
It has been found that United Kingdom leads the top 5 countries where the greatest number of invoices were generated followed by Germany, France, EIRE and Spain.
II. The list of customers (CustomerIDs) that placed at least 1000 invoices is given below:
Customer ID Number of Invoices
III.
IV.
The maximum number of invoices was recorded in the October 2011 (31-10-2011) with the invoices count of 1114 and the minimum number of invoices was recorded in the month of December 2010 (05-12-2010) with the invoice count of one.
Task 2
I.
Descriptive Statistics
The data taken into consideration represents the information about the three class of iris plants and a sample of 50 plants were taken from each class of iris plants. It is found that just one of the three iris plants can be linearly separated from the other two, but they cannot be linearly separated from one another.
We must conduct an independent sample t test or a Z mean test to compare the sales between the two stores. Uni Assignment Help, we must first verify the normalcy assumption. For the sales data of the two stores A and B, this can be accomplished using either a histogram or a box plot. The independent sample t test can be used to test the distribution's normality; otherwise, the Mann Whitney U test, a non-parametric test, was employed to compare the median value between two groups. After deciding to perform the independent sample t test (Levene's test was used to verify the claim), we must examine the F test for homogeneity of variances. We can do an independent sample t test with assumed equal variances if the p-value of Levene's test was larger than 0.05. On the other hand, we must conduct an independent t sample test with unequal variances when the p-value of the t test was less than 0.05. We must now formulate the hypotheses to test the assertion. To see if there was any improvement between before and after the intervention programme, a paired t test was utilised. The implementation of an intervention programme whose efficacy was confirmed was intended to help people with excess body weight transition to people of normal weight (Leilei Sun, 2017).
Outcome Variable: class of iris plant.
Data Extracted from: https://archive.ics.uci.edu/ml/datasets/iris
II.
Attribute Information:
1. Sepal length in cm
2. Sepal width in cm
3. Petal length in cm
4. Petal width in cm
5. Class:
-- Iris Setosa
-- Iris Versicolour
-- Iris Virginica
The variables taken in to consideration represents the sepal length, sepal width, petal length and petal width of three class of iris plants. The three class of iris plants taken in to consideration are Setosa, Versicolour and Virginica and 50 samples from each class was taken for the statistical analysis. The provided variables in this case are sepal width, sepal length, petal width and, petal length, all these variables are continuous variables. Therefore, measured under continuous scale and hence, descriptive statistics was used to determine the distribution of these variables. The distribution is skewed right if the mean value is higher than the median whereas if the mean value is lower than the median then its left skewed. If the mean and median coincide, then the distribution follows normal distribution.
Descriptive Statistics
Sepal Length Sepal Width Petal Length Petal Width
The mean Sepal Length is 5.843 ± 0.828 and the median Sepal Length is 5.8. This shows that over 50% of the sample Sepal Length is below 5.8 and almost 50% is above 5.8, respectively. Kurtosis and skewness are 0.5521 and -0.686, respectively. The 4.3 and 7.9 are the smallest and largest recorded Sepal Lengths, respectively. The distribution of sepal length is skewed right because the mean sepal length is somewhat longer than the median sepal length.
The mean Sepal Width is 3.054 ± 0.434 and the median Sepal Width is 3. This demonstrates that roughly 50% of the sample Sepal Width is below 3, and nearly 50% is above
3. Skewness and kurtosis are, respectively, 0.188 and 0.2908. The lowest and largest Sepal Widths ever observed are 2 and 4.4, respectively. The distribution of sepal width is skewed right because the mean sepal width is somewhat larger than the median sepal width.
3.759 ± 1.764 is the mean Petal Length and 4.35 is the median of Petal Length. Almost 50% of the sample Petal Length falls below 4.35, and almost 50% of the sample Petal Length falls over 4.35, according to this data. Skewness and kurtosis are respectively 3.11 and -1.4019. Petal Length measurements range from 1 to 6.9, respectively. Because the mean petal length is a little bit longer than the median petal length, the distribution of petal length is skewed to the right.
The median and mean petaled widths are 1.3 and 1.199 (± 0.763), respectively. Almost half of the sample Petal Width falls below 1.3, and rest of the sample Petal Width falls over 1.3, according to this data. The kurtosis and skewness are, respectively, -1.3398 and 0.582. The lowest and largest Petal Widths ever observed are 0.1 and 2.5, respectively. The distribution of petal width is skewed right because the mean petal width is somewhat larger than the median petal width.
V.
Class-wise mean ± standard deviation
The mean Sepal Length for Setosa is 0.196 ± 0.098, the mean Sepal Width for Setosa is 0.591 ± 0.159, the mean Petal Length for Setosa is 0.079 ± 0.029 and the mean Petal Width for Setosa is 0.06 ± 0.045
The mean Sepal Length for Versicolour is 0.454 ± 0.143, the mean Sepal Width for Versicolour is 0.321 ± 0.131, the mean Petal Length for Versicolour is 0.553 ± 0.08 and the mean Petal Width for Versicolour is 0.511 ± 0.082
The mean Sepal Length for Versicolour is 0.636 ± 0.177, the mean Sepal Width for Versicolour is 0.406 ± 0.134, the mean Petal Length for Versicolour is 0.772 ± 0.094 and the mean Petal Width for Versicolour is 0.803 ± 0.114
VI.
When compared to other class plants, the mean petal width of Virginica, Versicolor, and Setosa are all higher than the mean petal width of other class plants. The mean sepal width of Setosa is also higher than the mean petal width of other class plants.
Task 3
I)
The height and weight of 20 friends is given below:
II)
Analysis and Reporting
The correlation table output is given below:
From the above table, we see that the correlation between height and weight of 20 friends is found to be negative and almost close to zero. This indicates that there exists very weak negative linear relationship between height and weight. That is height of the individuals do not depend on their weights.
Task 4
I)
The ethics in data science plays a major role in business analytics and it certainly earns the data ownership. The data collection certainly involves the consent form to be filled by the participants as data collection without their permission seems to be considered illegal and therefore, it is mandatory to ask the participants to fill the consent form while collecting the data from them.
Thus, either signed written agreements along with digital privacy policies are required that accepts company terms and conditions and these things will certainly allow the website to track consumers online behaviour and to track all customers basic information they need to fill the consent form. This will certainly prevent the researcher from ethical and legal issues. Intentions of data collection should be clear as it will certainly help them to analyse the data and interpret them in a unbiased manner. Before the data collection, the researcher must be clear regarding the data interpretation and analysing the data. If the researcher is good in data collection preparation, then it would certainly help in manage cost expenses then it is moving in the good direction (Leilei Sun, 2017).
Regarding the transparency, data subjects have all right to know about the plan to acquire and utilize their personal details as the data certainly belongs to him. Transparency plays a major role while acquiring data from the consumers. During the online survey, the consumer should be explained clearly about the cookies and tracking user activity and relatively showing the details of how the data was kept secure and safe. With the modern techniques, business analytics frame an algorithm that certainly shows online experience in keeping the data secure and safe. Since the consumer has all rights to access his information and therefore, they have all rights to decide whether or not to accept the cookies available in the online sites.
Big Data plays a major role in determining privacy rights, data validity and the fairness of the algorithm and the artificial intelligence along with machine learning certainly provides additional facilities and features in providing ethical challenges which involves more thorough investigation.
Ethical issues in the workplace certainly provides a background of the research and it certainly resolves many issues in an organization. Unethical accounting, harassment, health and technology advancements, social media and privacy are considered as the five types which is considered as main ethical issues that occurs in the workplace (Leilei Sun, 2017).
II
Ethics certainly blocks the freedom in accessing unauthorized access to private data which is unsafe. When considering the data collection that certainly collects the individual details by using technology certainly determines accuracy and completeness. The definition of workplace ethics that certainly shows an examples for arising modern dilemma and it needs to be resolved by an organization. Certainly, Unethical accounting, harassment, health and technology advancements, social media and privacy are considered as the five types which is considered as main ethical issues that occurs in the workplace (Korobova L.A. et al, 2020).
Data privacy needs to be addressed properly as it would certainly affect the organization as they need to pay high amount if the data privacy is breached and the amount seems to be very high such as financial penalties imposed such as compensation payments to avoid lawsuits).
Even though cultures of privacy policy differ with respect to the organization and therefore, it seems to be impossible to frame a standard format in the privacy policy as a universal value and therefore, it is classified as a privacy certainly have an intrinsic, core and social value. Therefore, it is mandatory to enforce the law, principles and societal and also environmental concerns required in defining the complexity of the privacy and also the difficulties faced in upholding data privacy policies.
The protection of data is necessary and it certainly implemented the privacy policy in thinking of its advantages and technology driven environment. The major benefits of this trend are shown in the market place and it considered to be transparent and it was considered as the better informed and fairer in trade practices. The socio – techno risk certainly originated with the technology and other kind of human theft as the data seems to be considered as an opportunity for organized and cybercriminals to exploit (Korobova L.A. et al, 2020).
III.
The ethical issues in business section is to find an optimal way to navigate the ethical issues in business and some ethical issues certainly covered by laws and the requirements.
Navigating ethical concerns in company is one of the biggest hurdles for any business owner. While certain business ethics are governed by regulations, others have requirements that make it necessary to post in the shadows. The business owner and managers must therefore develop a model for ethical behaviour if they want to hold employees accountable for sharing immoral information.
According to Richard Vidgen (2020), business analytics plays a significant role in daily lives and it has a significant impact on the modern job applications and medical treatment conditions. It also moved into the financial services by appropriately deciding the loan approval to its bank customers. Artificial Intelligence certainly helps the medical doctors to detect the early stages of colorectal cancer with an accuracy rate of 86%. With its advancement in medical treatment conditions, UK Government is willing to spend millions of amount to Artificial Intelligence in determining the early diagnosis of cancer and other high risk chronic disease which would certainly save lives of millions of people and their money. It was also found that many organizations started to implement General Data Protection Regulation (GDPR) which was now considered as an ethical importance in the analytics development in machine learning.
According to W?odzimierz Sroka (2015), Ethics in business plays a significant role in the company existence in various countries and if a company wants to be had a reliable partner, then, there should be mutual understanding between them and they need to implement the ethics legally and should adhere to the ethics rules and principles. Thus, it is found that business ethics is considered as a greater significant factor that certainly influencing both the profits and success of the growing companies and their role seems to be determined and fixed in setting their goal to higher profits in future.
References
1. Richard Vidgen, Giles Hindle, Ian Randolph, (2020). Exploring the ethical implications of business analytics with a business ethics canvas, European Journal of Operational Research, Volume 281, Issue 3, 2020, Pages 491-501, ISSN 0377-2217. Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S037722171930373X?via%3Dihub
2. W?odzimierz Sroka, Marketa L?rinczy, (2015). The Perception of Ethics in Business: Analysis of Research Results, Procedia Economics and Finance, Volume 34, 2015, Pages 156-163, ISSN 2212-5671. Retrieved from the link https://www.sciencedirect.com/science/article/pii/S2212567115016147?via%3Dihub
3. Leilei Sun, Guoqing Chen, Hui Xiong, Chonghui Guo, (2017). Cluster Analysis in Data?Driven Management and Decisions, Journal of Management Science and Engineering, Volume 2, Issue 4, 2017, Pages 227-251, ISSN 2096-2320, https://www.sciencedirect.com/science/article/pii/S2096232019300368?via%3Dihub
4. Korobova L.?, Savvina E.A, Kovaleva E.N, Gladkikh T.V, Lukina O.O and Tolstova I.S., (2020). Application of Cluster Analysis for Business Processes in the Implementation of Integrated Economic and Management Systems, 2020 The Authors. Published by Atlantis Press SARL. https://www.researchgate.net/publication/343582019_Application_of_Cluster_Analysis_for_Business_Processes_in_the_Implementation_of_Integrated_Economic_and_Management_Systems
Would you like to schedule a callback?
Send us a message and we will get back to you
Highlights
Earn While You Learn With Us
Confidentiality Agreement
Money Back Guarantee
Live Expert Sessions
550+ Ph.D Experts
21 Step Quality Check
100% Quality
24*7 Live Help
On Time Delivery
Plagiarism-Free
81 Isla Avenue Glenroy, Mel, VIC, 3046 AU
