Analysis Of Sales For Harvest Kitchen

Problem Statement

Due to global inflation that affected the world in 2008, many business enterprises have been finding it difficult to cope in the market (March, 2009) and (Romano, 2009). The economic turmoil dealt many industries a heavy blow. And until recently it has been difficult for various businesses to get up to their knees. Worse is for the new entrants in various industries. The new entrepreneurs have had to face the stiff competition waged by very established businesses in those particular industries (Mowlana & Smith, 2003) and (March, 2009). So for the new businesses to thrive in the global market they have to strategize to counter their competitor’s strong selling points. These strategies might include very elaborate sales and marketing approaches so as to increase their sales and hence widen their profit margins.

Strong profit margin is very fundamental aspect of any business organization which needs to remain competitive in the market. This is because is a wider profit margin that will support various operations of the business from paying of salaries, business inputs, advertisement costs, logistics costs to production costs. This means that if any business does not pay attention to how it can solidify its sources of profits, then the business might be in a state of jeopardy. Harvest Kitchen is a young company that has been dealing with fruits and vegetables. The problems facing other new companies have also been playing out in Harvest Kitchen Company. They have being faced by low gross profits which is being attributed to low sales annually. The low amount sale on the other hand is believed to be due to lack of conversion of leads to actual business opportunities. Lastly, the cost of goods has also been a factor contributing to low sales. It for this reason the management of the organization has decided to carry out a research report on their business operations in order to identify areas that are directly affecting their revenues so that they can improve on them.

It can be observed from the graph above that the best performing product from Harvest Kitchen was drinks. This is because it had an annual sales amount of 20,673.81 in thousand dollars. This was an amount far beyond other products in the company. Other relatively performing well products were bakery products. From these the company as can be seen from the graph was able to make an annual sale of 10,137.55 in thousand dollars. The worst performing products in terms of sales were Ayurvedic and Chocolate & slices. These were only able achieve 678.75 and 135.92 respectively in thousand dollars.

Harvest Kitchen Company allows their customers to pay for their products using various methods of payments; the common ones being credits and visas. Since these are internationally accepted methods of payments, it has given the business an opportunity to even sell products internationally. It has also help widen the customer base since customers have been allowed to pay using methods that they are comfortable with. In order to assess the payment method that is most convenient to majority of customers, the company sought to determine whether there was a reason to conclude that there was a major difference in the two major payment methods. To establish this, a paired sample t-test was used to determine whether there was a significant difference in the two payment methods. The test hypothesis was as illustrated below,

Amount of annual sales for various products

H₀: There is no significant difference between payments through credit and visa.

 Versus

H₁: There is significant difference between payments through credit and visa.

The test results were as below at 95% confidence level

Paired Samples Statistics
	Mean	N	Std. Deviation	Std. Error Mean
Pair 1	credit	584.8115	366	228.86716	11.96308
visa	555.8443	366	244.88987	12.80060

Table 1

Paired Samples Correlations
	N	Correlation	Sig.
Pair 1	credit & visa	366	.931	.000

Table 2

Paired Samples Test
	Paired Differences	t	df	Sig. (2-tailed)
Mean	Std. Deviation	Std. Error Mean	95% Confidence Interval of the Difference
Lower	Upper
Pair 1	credit – visa	28.96721	89.48246	4.67732	19.76933	38.16510	6.193	365	.000

From the paired t-test results above, it can be observed that the Pearson correlation coefficient is .9. This value is close to 1 which usually indicates a perfect positive correlation between any two variables. It can therefore be concluded that there is a very strong positive relationship between the two payment methods in the positive direction. On the other hand, comparing the p-value computed (.00) and the level of significance (.05), it can be observed that the p-value is less than the level of significance. This therefore means that the null hypothesis is rejected and the alternative hypothesis accepted. The conclusion then is that there is significant difference between payments through credit and visa.

Placing items in different locations can indeed influence the amount of those items that can be bought. Exposing items in a shop make them to be seen by customers thereby prompting the customers to buy them. On the other hand, products which are placed in crowded shelves or far from the entrance of the shop can minimize the attention they get from customers thereby decreasing their chances of being bought too. Research has it that if products that do not attract much attention or are not so much on demand placed close to fast moving goods, then their chances of being bought always increase by some percentage. This is explained by influence of impulse buying. Harvest Kitchen has five locations where they place their products. What is not clear is whether the five locations get equal attention and hence purchase from customers. It is for this reason that this research report decided to carry out an analysis to determine whether there is significant difference in sales levels from the five different locations. The test statistic to be employed is an analysis of variance. This test is appropriate since the variables involved are more than two. The test hypothesis has been illustrated as below;

The test hypothesis

H₀: There is no significant difference in the sales of products from the five locations.  

Versus

H₁: At least sales from one location are different.

ANOVA
	Sum of Squares	df	Mean Square	F	Sig.
location1	Between Groups	295770218.364	185	1598757.937	4.448	.000
Within Groups	44931115.379	125	359448.923
Total	340701333.743	310
location2	Between Groups	51535594.667	185	278570.782	2.754	.000
Within Groups	12643881.982	125	101151.056
Total	64179476.650	310
location3	Between Groups	244998995.000	11	22272635.909	.	.
Within Groups	.000	0	.
Total	244998995.000	11
location4	Between Groups	177884531.450	147	1210098.853	1.389	.139
Within Groups	27873309.500	32	871040.922
Total	205757840.950	179

Table 4 above is an illustration of analysis of variance results. From the results it can be observed that the p-values computed are generally less than the level of significance which is .05. The decision therefore is, the null hypothesis is rejected while the alternative hypothesis is accepted. The conclusion therefore is that at least the sales level from one or more locations is different. For the research to establish the different locations, then a Duncan’s test is recommended.

It is a conventional norm in any business that the more the sales the more the gross profit realized. However sometimes more sales do not translate to more gross profit as products might be fetching low prices in the market. Again, sales across the year can also not be constant due to various factors. The factors may include market conditions that do not favor sales such as excessive supply of a given commodity in the market. Sometimes factors such as weather may affect the amount of production and hence the amount of sales. Since Harvest Kitchen deals with agricultural products, due to the above mentioned factors, the sales levels cannot be the same across the months of the year.

Testing whether there is a significant difference in payment techniques

H₀: The mean sales level is the same across all the months of the year.

Versus

H₁: At least one month is different in terms of sales. 

The test’s confidence level is 95%

ANOVA
	Sum of Squares	df	Mean Square	F	Sig.
Net sales January	Between Groups	3678107.097	30	122603.570	.	.
Within Groups	.000	0	.
Total	3678107.097	30
Net sales February	Between Groups	1492938.000	28	53319.214	.	.
Within Groups	.000	0	.
Total	1492938.000	28
Net sales March	Between Groups	4187028.774	30	139567.626	.	.
Within Groups	.000	0	.
Total	4187028.774	30
Net sales April	Between Groups	2786878.800	29	96099.269	.	.
Within Groups	.000	0	.
Total	2786878.800	29
Net sales May	Between Groups	3317298.839	30	110576.628	.	.
Within Groups	.000	0	.
Total	3317298.839	30
Net sales June	Between Groups	1418345.467	29	48908.464	.	.
Within Groups	.000	0	.
Total	1418345.467	29
Net sales July	Between Groups	1765256.194	30	58841.873	.	.
Within Groups	.000	0	.
Total	1765256.194	30
Net sales Aug.	Between Groups	2698581.935	30	89952.731	.	.
Within Groups	.000	0	.
Total	2698581.935	30
Net sales Sep	Between Groups	2248828.000	29	77545.793	.	.
Within Groups	.000	0	.
Total	2248828.000	29
Net sales Oct	Between Groups	3395575.419	30	113185.847	.	.
Within Groups	.000	0	.
Total	3395575.419	30
Net sales Nov	Between Groups	2655303.367	29	91562.185	.	.
Within Groups	.000	0	.
Total	2655303.367	29

The table 5 above, the analysis of variance results show that there p-values calculated are generally larger than the significant level used in the test. In anova test, if the p-value is less than the level of significance, then the decision is always that the null hypothesis is rejected and the alternative is not rejected. The reverse is also true. In regard to this test rule, since it has been found in this test that the p-values are less than .05, then the decision rule is that the null hypothesis is rejected and the alternative is accepted. This means then that at least sales from one month are different. For the test to determine from which month or months are sales different, then further tests such as Duncan’s tests are recommended.

Test for gross profit difference between the months

Hypothesis

H₀: There is no significant difference in gross profit across the 12 months of the year.

Versus

H₁: At least one month is different in terms of gross profit. 

In this hypothesis, 95% confidence level has been applied.

ANOVA
	Sum of Squares	df	Mean Square	F	Sig.
jan_gp	Between Groups	50905.200	28	1818.043	4.474	.199
Within Groups	812.659	2	406.329
Total	51717.859	30
feb_gp	Between Groups	7919.956	27	293.332	.164	.980
Within Groups	1791.610	1	1791.610
Total	9711.566	28
march_gp	Between Groups	7419.298	28	264.975	1.097	.586
Within Groups	482.904	2	241.452
Total	7902.202	30
Apr gp	Between Groups	3216.693	27	119.137	.156	.995
Within Groups	1528.049	2	764.024
Total	4744.742	29
may_gp	Between Groups	12456.400	28	444.871	36.134	.027
Within Groups	24.623	2	12.312
Total	12481.023	30
june_gp	Between Groups	6554.626	27	242.764	25.033	.039
Within Groups	19.395	2	9.698
Total	6574.022	29
july_gp	Between Groups	8586.214	28	306.651	2.287	.350
Within Groups	268.174	2	134.087
Total	8854.388	30
aug_gp	Between Groups	12119.709	28	432.847	1.136	.574
Within Groups	762.284	2	381.142
Total	12881.994	30
sept_gp	Between Groups	22640.467	27	838.536	.116	.999
Within Groups	14424.341	2	7212.171
Total	37064.809	29
oct_gp	Between Groups	42678.595	28	1524.236	1.087	.590
Within Groups	2803.541	2	1401.771
Total	45482.136	30
nov_gp	Between Groups	68636.751	27	2542.102	2.032	.383
Within Groups	2502.487	2	1251.244
Total	71139.239	29

Table 6

The table 6 above, the analysis of variance results show that there p-values calculated are generally larger than the significant level used in the test. In anova test, if the p-value is less than the level of significance, then the decision is always that the null hypothesis is rejected and the alternative is not rejected. The reverse is also true. In regard to this test rule, since it has been found in this test that the p-values are more than .05, then the decision rule is that the null hypothesis is rejected and the alternative is accepted. This therefore indicates that there is no significant difference in gross profit across the 12 months of the year.

To establish whether there was a relationship between sales and rainfall, a Pearson correlation test was used to establish the same. A Pearson correlation coefficient usually span from -1 to 1. -1 means a negative perfect correlation while 1 means a positive perfect positive correlation.

The test results for the correlation are as shown in the table below,

Correlations
	SALES	RAINFALL
SALES	Pearson Correlation	1	.057
Sig. (2-tailed)		.273
N	366	366
RAINFALL	Pearson Correlation	.057	1
Sig. (2-tailed)	.273
N	366	366

Table 7

Table 7 above shows the results for relationship between rainfall and sales. The correlation coefficient between the two variables is .06. This shows that there is a weak but positive relationship between rainfall and sales.

To establish whether there was a relationship between sales and net profit, a Pearson correlation test was used to establish the same. A Pearson correlation coefficient usually span from -1 to 1. -1 means a negative perfect correlation while 1 means a positive perfect positive correlation.

The test results for the correlation are as shown in the table below,

Correlations
	SALES	Net profit
SALES	Pearson Correlation	1	.017
Sig. (2-tailed)		.745
N	366	366
Net profit	Pearson Correlation	.017	1
Sig. (2-tailed)	.745
N	366	1034

Table 7

Table 7 above shows the results for relationship between rainfall and sales. The correlation coefficient between the two variables is .02. This shows that there is a weak but positive relationship between net profit and sales.

The research report found that there was no relationship between rainfall and sales. It was also found that the gross profit the company fetched from sales every month showed not much improvement. The report therefore recommends to the management of Harvest Kitchen that since it deals in agricultural products, it will be very dangerous to rainfall to do any forecast of their sales at any month of the year. This is because the two have been found not to have any strong relationship. The report also recommends that there should be a lot of sales and marketing done by the company if at all profit margins are to be widened. This is because the current trend shows little improvement in gross profits from one month to the other.

Kotler , P. (2012). Marketing Management: Analysis, Planning, Implementation and Control,. Englewood Cliffs, NJ.: Prentice-Hall.

March, R. (2009). Tourism marketing myopia”, Tourism Management. (Vol. 15).

Mowlana, H., & Smith, G. (2003). Marketing in a global context: the case of frequent traveler programs. Journal of Travel Research, 33, 20-27.

Romano, C. (2009). Research strategies for small business: a case study. International Small Business Journal, 7, 35-43.l Business Journal, 7, 35-43.