Furphy Product Sales Analysis

This assignment examines the sales performance and customer perception of the Furphy product. It analyzes sales data, customer ratings, and repurchase behavior, identifying key factors influencing repurchase decisions. Regression analysis is used to determine the relationships between variables such as distribution channel, brand image, product quality, and repurchase units. The assignment also forecasts future sales trends for 2018 and provides recommendations for Furphy to enhance its sales and customer satisfaction.

Running Head: DESCRIPTIVE ANALYTICS AND VISUALIZATION
MIS771
Descriptive Analytics and Visualization
Name of the Student
Name of the University
Author Note

1DESCRIPTIVE ANALYTICS AND VISUALIZATION
Table of Contents
1.0 Introduction................................................................................................................................2
2.0 Collection of Data......................................................................................................................3
3.0 Data Description........................................................................................................................3
4.0 Data Analysis.............................................................................................................................3
4.1 Analysis of the Dependent Variable......................................................................................3
4.2 Factors Influencing Repurchasing Intentions........................................................................4
4.2.1 Variable Identification....................................................................................................4
4.2.2 Prediction of Repurchasing Intention.............................................................................6
4.2.3 Separate Analysis............................................................................................................7
4.3 Furphy Recommendation.......................................................................................................8
4.4 Analysis of Time Series.......................................................................................................10
5.0 Conclusion and Recommendations..........................................................................................10
References......................................................................................................................................12

2DESCRIPTIVE ANALYTICS AND VISUALIZATION
1.0 Introduction
Furphy Beer is a micro-brewery organization which was started in Australia. The
organization is new in the country with under 15 years of involvement in the preparing of brew.
The sales and production of the organization is under a limit in the city of Melbourne and reginal
Victoria. The demands of the product of the company are expanding quickly in the various parts
of Australia. Over the most recent two years huge development in the products and services of
the company have been taken note of. The request of the organization has been expanding to
such a great amount of that in the year 2016 they chose to rise the production of beer to 3 million
liters for each year to adapt up to the expanding interest of the item.
There are two market sections, which purchase the Furphy pale beer. One is pubs, bars
and restaurants and the other is bottleshops. The beer that has been produced by Furphy are sold
in these two markets either specifically or with the assistance of some sales agents.
The organization has encountered colossal achievement in their operations and monetary
turnovers in the past two years. At that point additionally, the organization can detect an
adjustment in the business atmosphere in the up and coming five years. This can be the result of
the high prominence of craft beer and microbrewery culture in Victoria and its encompassing
areas. In this manner, with the expansion in the opposition, the organization has felt the need of
building a solid association with the clients. In this way, to comprehend and recognize the
components that are dependable to manufacture a solid client relationship the organization has
named a statistical surveying organization named Beautiful Data. They have made a request to
direct a huge scale overview of the customers of the organization to have a reasonable
comprehension of the customers attributes and their repurchasing aims.

3DESCRIPTIVE ANALYTICS AND VISUALIZATION
2.0 Collection of Data
Furphy has decided to run a data analysis to analyze and increase the repurchasing
intentions of the customers. Thus, to run this analysis, Furphy has appointed a market research
company named Beautiful Data. This market research company has asked some of the clients to
fill up an online survey. Various factors that are necessary for the calculations were contained in
the questionnaire. The data on the past years sales in the four quarters per year have been
collected from the information stored and compiled through Furphy’s datamart.
3.0 Data Description
The data collected from 200 clients of the company has 9 different perceptions of the
customers or clients. These perceptions have been recorded in a scale of 1 – 10. Other variables
give qualitative information about the outcomes of the purchases by the clients and their business
relationship with the respective clients. The analysis has been done using the MS Excel software.
4.0 Data Analysis
4.1 Analysis of the Dependent Variable
The dependent variables that has to be analyzed and predicted with the data collected are
the quality of the product and the social media presence. These factors are responsible for the
purchasing intention of the customers in repurchasing Furphy’s products and recommending the
products of the company Furphy to others. The test results show that the mean rating for quality
of the product is given by 7.84, which is quite high. Thus, it can be said that the company
produces good quality beer. The average rating for the presence of social media is found to be
3.7 which is not that high. Thus, it can be said that social media is not much involved in

4DESCRIPTIVE ANALYTICS AND VISUALIZATION
promoting the brand. Thus the brand is not recommended to most of the people of the country as
they are not quite aware of it. It can only be recommended to others from its existing clients. The
results of the descriptive analysis are shown in table 4.1.
Table 4.1: Descriptive Statistics
4.2 Factors Influencing Repurchasing Intentions
It is important to identify the potential variables that are responsible in influencing the
repurchasing intention of Furphy beer. To identify the variable regression analysis has been done
on the complete dataset.
4.2.1 Variable Identification
The factors that are included to predict the repurchasing intentions are Product quality
perception, social media presence, advertising, brand image perception, competitive pricing,
price flexibility, order and billing, shipping speed, shipping cost and recommending furphy to
others. These variables were chosen for predicting repurchase decisions because from a customer
point of view, they are important in repurchasing decisions. The ignored variables are

5DESCRIPTIVE ANALYTICS AND VISUALIZATION
Identification number and the location of the customers. These variables are related to business
yet not important for the customer to make the repurchase decision. The results of the regression
analysis are shown in table 4.2. The estimated predictive model is;
Repurchase_Int = 3.314 + 0.279*quality + -0.169*SM_Presence + -0.034 * Advert + 0.366 *
Brand_Image + -0.041 * Comp_Pricing + -0.139 * Order Fulfilment + 0.006 * Flex_Price +
0.364 * Shipping_Speed + 0.088 * Shipping_Cost
Table 4.2 shows the regression coefficients and the p-values of the independent variables
individually. From the table, it can be seen that the variables that mostly influence the purchasing
intention of the customers are given as follows:
 Social media presence
 Advertizing.
 Perceived level of quality of Furphy’s products (Quality).
 Overall image of Furphy’s brand (Brand_Image).
 Competitive Pricing
 Flex price
 Shipping speed
 Shipping Cost
Table 4.2: Regression Output Involving all Independent Variables
Coefficien
ts
Standard
Error t Stat P-value Lower 95% Upper 95%
Intercept 3.314 0.55689619
5.95047173
3
1.26478E-
08
2.21530163
3
4.4122884
43
Quality 0.279 0.044874391
6.21451815
9 3.1867E-09
0.19035671
9
0.3673887
16
SM_Presence -0.169 0.102839068
-
1.64719797
1
0.1011702
2
-
0.37224925
9
0.0334566
51
Advert -0.034 0.055559407 - 0.5373205 - 0.0752572

6DESCRIPTIVE ANALYTICS AND VISUALIZATION
0.61799216
5 52
0.14392777
2 16
Brand_Image 0.366 0.07888075
4.63444479
8
6.63571E-
06
0.20997398
3
0.5211629
82
Comp_Pricing -0.041 0.038711676
-
1.06135940
6
0.2898738
38
-
0.11744687
2
0.0352728
69
Order_Fulfillme
nt -0.139 0.086464976
-
1.61139630
9
0.1087533
03
-
0.30988394
0.0312252
55
Flex_Price 0.006 0.066595535
0.09042406
9
0.9280454
85
-
0.12533972
7
0.1373834
05
Shipping_Spee
d 0.364 0.159821014
2.27732547
8
0.0238807
05 0.04871302
0.6792159
15
Shipping_Cost 0.088 0.085893162
1.01987123
8
0.3090863
79
-
0.08182671
4
0.2570266
45
Considering all the variables it can be seen from table of regression summary statistics
(Table 4.3) that the independent variables can predict the repurchasing intentions of the
customers 44.8 percent correctly. The variables, which has been identified as insignificant also,
has very little impact on the repurchasing intentions of the clients. With the exclusion of those
variables, the correctness of the prediction will be affected but not to a huge extent. This
difference will not be a problem.
Table 4.3: Regression Statistics
Multiple R 0.669226614
R Square 0.447864261
Adjusted R Square 0.421710463
Standard Error 0.679261797
Observations 200
4.2.2 Prediction of Repurchasing Intention
With the elimination of the insignificant factors from the regression model, it can be seen
that there is not much change in the R Square value. Thus, these variables can be termed as
insignificant variables. The regression statistics and the coefficients table are given in table 4.4
and table 4.5 respectively. The modified regression model can be estimated by the following
equation:

7DESCRIPTIVE ANALYTICS AND VISUALIZATION
Repurchase_Int = 3.282 + 0.272*Quality + -0.167*SM_Presence + -0.026 * Advert + 0.352 * Brand_Image +
-0.037 * Comp_Pricing + -0.007 * Flex_Price + 0.285 * Shipping_Speed + 0.060 * Shipping_Cost
Table 4.4: Regression Statistics
Multiple R 0.66357
R Square 0.44032
Adjusted R Square 0.41688
Standard Error 0.68209
Observations 200
Table 4.5: Regression Output Involving the selected Independent Variables
Coefficient
s
Standard
Error t Stat P-value Lower 95% Upper 95%
Intercept 3.282 0.558862408
5.87220760
7
1.8762E-
08
2.17942125
1
4.38409091
7
Quality 0.272 0.044862995
6.06495184
1
6.9355E-
09
0.18360135
2
0.36058245
1
SM_Presence -0.167 0.103256716
-
1.61681397
7
0.1075688
4
-
0.37061684
4
0.03672304
1
Advert -0.026 0.055570526
-
0.47473763
8
0.6355163
4
-
0.13599216
8
0.08322932
8
Brand_Image 0.352 0.078752637
4.46883527
8
1.3456E-
05
0.19659598
3
0.50726914
1
Comp_Pricing -0.037 0.038781692
-
0.94917935
1
0.3437288
4
-
0.11330619
4
0.03968463
1
Flex_Price -0.007 0.066385099
-
0.10425987
5
0.9170725
2
-
0.13786338
4 0.12402078
Shipping_Spe
ed 0.285 0.152769574 1.86595102
0.0635813
4
-
0.01627162
9
0.58639271
3
Shipping_Cost 0.060 0.084560826
0.71345959
3
0.4764322
5
-
0.10646227
8
0.22712374
3
4.2.3 Separate Analysis
The manager of the research team has conducted a different analysis. From the analysis,
it is observed that repurchasing units significantly depend on the perception about beer quality.

8DESCRIPTIVE ANALYTICS AND VISUALIZATION
Another related findings is that there is a common tendency among the customers to link brand
image with quality of the product. Therefore, these two variables should be used for a good
prediction of repurchasing intention. The regression analysis shows that perception about quality
of beer and brand image explained 34% variation in repurchasing intention (Table 4.6). As
explanatory variables both quality and brand image are statistically significant. There P values
are less than 0.05 (Table 4.7). The estimated relationship of repurchasing intention with that of
quality and brand image are given as-
Repurchasing Intentions = 3.59 + (0.31 * Quality) + (0.31 * Brand Image)
Table 4.6: Regression Statistics of Manager Identified
Independent Variables
Multiple R 0.584
R Square 0.341
Adjusted R Square 0.334
Standard Error 0.729
Observations 200
Table 4.7: Regression Output Involving Manager Identified Variables
Coefficient
s
Standard
Error
t Stat P-value Lower 95% Upper 95%
Intercept 3.58749267
7
0.407503955 8.80357757
6
6.78306E-
16
2.78386269 4.39112266
3
Quality 0.30941394
9
0.037618814 8.22497879
1
2.60564E-
14
0.23522667
6
0.38360122
2
Brand_Imag
e
0.31154603
8
0.046100345 6.75799795 1.54395E-
10
0.22063251
6
0.40245956
4.3 Furphy Recommendation
Next agenda of the team manager is to recommend Furphy. There are clients who are
neutral about delivery speed of Furphy depending on the quality and images of the brand. There
are also clients who make purchase either directly or through sales representatives. Special
attention has been given to these groups of clients.

9DESCRIPTIVE ANALYTICS AND VISUALIZATION
An important determinant of this is the ratings given by clients. To make the analysis
simple, ratings are rounded off to get the nearest whole number. Clients who have given a 5
ratings are collected to confirm the likely for Furphy recommendation. The likely hood of
recommendation is 29 percent for the clients who are neutral about Furphy’s delivery speed as
shown from table 12.
Perception of clients varied with different levels of product quality. With this varying
level, the likely hood for recommending Furphy to other clients is 0.505, as stated in table 14.
From the table it is seen that the lowest recorded rating is 6. Therefore, from the rating statistics
it is clearly evident that the product delivered by Furphy is quite satisfactory and is of a good
quality product.
The likely hood for different brand images is represented in tale 16. The brand images are
categorized in three groups positive brand image, neutral brand image and negative brand image.
1 percent of the clients having neutral brand preference recommend Furphy’s product. Clients
with positive and negative brand image constitutes likely hood of 31% and 18.5% respectively.
These are the recommendation statistics for clients influencing others toward making purchase of
Furphy’s beer brand.
The tendency for recommendation by customers who directly purchase the product or
purchase with intermediation by the sales representatives is shown in table 18. It is seen that
those who directly purchase the product have a higher tendency for recommendation as
compared to those purchase the product with sales representative. Percentage of customers
recommending Furphy to others in directly purchasing group is 34% while that for buyers with
sales representative is 16.5 percent.

10DESCRIPTIVE ANALYTICS AND VISUALIZATION
Furphy’s beer brand is quite popular in the state. Mixed responses are obtained from the
clients purchasing the products. There are both positive and negative ratings obtained from the
clients. Despite negative and neutral return from customers, there is an overall good image for
the product. Recommendations come from all the groups of customers. The Customers
recommend the product to others irrespective of their ratings.
4.4 Analysis of Time Series
A time series analysis is made for foresting sales of Furphy in the next quarter. Using
sales data until 2017, prediction is made for the tear 2018. Quarterly moving average method
(Granger and Newbold 2014) has been used to predict quarterly sales in 2018. When past data
points are available then moving average methods are suitable for making forecast (Brockwell
and Davis 2016). The trend obtained from the data is likely to depict a clear trend for forecast
(Boxet al. 2015). Moreover, moving average method is widely used because of simplicity in
calculation and easy interpretation (Montgomery, Jennings and Kulahci 2015). The predicted
sale in first quarter of 2018 is 1699.40 litres per ale. An increase in quarterly sales prediction is
found for the next quarter. In the second quarter of 2018, the expected sale is 1714 litres per ale.
This trend declines in the third and fourth quarter of 2018. Forecasted sales for the third and
fourth quarter of 2018 are 1656.66 litres per ale and 1688.71 litres per ale.
5.0 Conclusion and Recommendations
The paper summarizes sales and ratings of the Furphy product with reference to
repurchase unit. Most people using the product have given high rating for the product. The
significant variables affecting repurchase units are distribution channel, loyalty of the customers
towards product, brand image and perceived product quality. The adjusted R square for the

11DESCRIPTIVE ANALYTICS AND VISUALIZATION
regression analysis is 0.44. This implies the explanatory variables taken in the regression
analysis explained nearly 44% variation in repurchase unit. Again, brand quality and image
predicts 34% of the repurchasing intensity. As per recommendation is concerned, people with
positive ratings recommends the product most. Finally, forecast is made for future sales.
Predicted sales is higher for first two quarters of 2018 while for later two quarters sales is
predicted to be declined slightly.
Furphy should consider some policy changes to increase its sales and improve ratings.
For repurchasing units the significant variables are distribution channel, brand image and quality
and customer loyalty. Improvement of these aspects can lead to an improvement in sales of the
concerned company. Once the company improves distribution channels or customer loyalty those
giving a neutral rating or negative ratings currently might give a positive response. With increase
in positive responses, more people will recommend the product to others. This will further
enhance sales.

12DESCRIPTIVE ANALYTICS AND VISUALIZATION
References
Box, G.E., Jenkins, G.M., Reinsel, G.C. and Ljung, G.M., 2015. Time series analysis:
forecasting and control. John Wiley & Sons.
Brockwell, P.J. and Davis, R.A., 2013. Time series: theory and methods. Springer Science &
Business Media.
Cameron, A.C. and Trivedi, P.K., 2013. Regression analysis of count data(Vol. 53). Cambridge
university press.
Chatfield, C., 2016. The analysis of time series: an introduction. CRC press.
Chatterjee, S. and Hadi, A.S., 2015. Regression analysis by example. John Wiley & Sons.
Draper, N.R. and Smith, H., 2014. Applied regression analysis. John Wiley & Sons.
Granger, C.W.J. and Newbold, P., 2014. Forecasting economic time series. Academic Press.
Kleinbaum, D., Kupper, L., Nizam, A. and Rosenberg, E., 2013. Applied regression analysis and
other multivariable methods. Nelson Education.
Montgomery, D.C., Jennings, C.L. and Kulahci, M., 2015. Introduction to time series analysis
and forecasting. John Wiley & Sons.
Montgomery, D.C., Peck, E.A. and Vining, G.G., 2015. Introduction to linear regression
analysis. John Wiley & Sons.
Nelson, E., 2016. Radically Elementary Probability Theory.(AM-117) (Vol. 117). Princeton
University Press.