Store 24(A)
Parv Patni
December 18, 2017
getwd()## [1] "C:/Users/parvp/Desktop/data analytics internship"store <- read.csv(paste("Store24.csv", sep=""))
head(store)## store Sales Profit MTenure CTenure Pop Comp Visibility
## 1 1 1060294 265014 0.00000 24.804930 7535 2.797888 3
## 2 2 1619874 424007 86.22219 6.636550 8630 4.235555 4
## 3 3 1099921 222735 23.88854 5.026694 9695 4.494666 3
## 4 4 1053860 210122 0.00000 5.371663 2797 4.253946 4
## 5 5 1227841 300480 3.87737 6.866530 20335 1.651364 2
## 6 6 1703140 469050 149.93590 11.351130 16926 3.184613 3
## PedCount Res Hours24 CrewSkill MgrSkill ServQual
## 1 3 1 1 3.56 3.150000 86.84327
## 2 3 1 1 3.20 3.556667 94.73510
## 3 3 1 1 3.80 4.116667 78.94776
## 4 2 1 1 2.06 4.100000 100.00000
## 5 5 0 1 3.65 3.588889 68.42164
## 6 4 1 0 3.58 4.605556 94.73510summary(store)## store Sales Profit MTenure
## Min. : 1.0 Min. : 699306 Min. :122180 Min. : 0.00
## 1st Qu.:19.5 1st Qu.: 984579 1st Qu.:211004 1st Qu.: 6.67
## Median :38.0 Median :1127332 Median :265014 Median : 24.12
## Mean :38.0 Mean :1205413 Mean :276314 Mean : 45.30
## 3rd Qu.:56.5 3rd Qu.:1362388 3rd Qu.:331314 3rd Qu.: 50.92
## Max. :75.0 Max. :2113089 Max. :518998 Max. :277.99
## CTenure Pop Comp Visibility
## Min. : 0.8871 Min. : 1046 Min. : 1.651 Min. :2.00
## 1st Qu.: 4.3943 1st Qu.: 5616 1st Qu.: 3.151 1st Qu.:3.00
## Median : 7.2115 Median : 8896 Median : 3.629 Median :3.00
## Mean : 13.9315 Mean : 9826 Mean : 3.788 Mean :3.08
## 3rd Qu.: 17.2156 3rd Qu.:14104 3rd Qu.: 4.230 3rd Qu.:4.00
## Max. :114.1519 Max. :26519 Max. :11.128 Max. :5.00
## PedCount Res Hours24 CrewSkill
## Min. :1.00 Min. :0.00 Min. :0.00 Min. :2.060
## 1st Qu.:2.00 1st Qu.:1.00 1st Qu.:1.00 1st Qu.:3.225
## Median :3.00 Median :1.00 Median :1.00 Median :3.500
## Mean :2.96 Mean :0.96 Mean :0.84 Mean :3.457
## 3rd Qu.:4.00 3rd Qu.:1.00 3rd Qu.:1.00 3rd Qu.:3.655
## Max. :5.00 Max. :1.00 Max. :1.00 Max. :4.640
## MgrSkill ServQual
## Min. :2.957 Min. : 57.90
## 1st Qu.:3.344 1st Qu.: 78.95
## Median :3.589 Median : 89.47
## Mean :3.638 Mean : 87.15
## 3rd Qu.:3.925 3rd Qu.: 99.90
## Max. :4.622 Max. :100.00mean and standards deviations of Profit
mean(store$Profit)## [1] 276313.6sd(store$Profit)## [1] 89404.08mean and standard deviation of MTenure.
mean(store$MTenure)## [1] 45.29644sd(store$MTenure)## [1] 57.67155mean and standard deviation of CTenure.
mean(store$CTenure)## [1] 13.9315sd(store$CTenure)## [1] 17.69752Top 10 most profitable stores.
attach(store)## The following object is masked _by_ .GlobalEnv:
##
## storeexhib1 <- store[order(-Profit),]
exhib1[1:10,1:5]## store Sales Profit MTenure CTenure
## 74 74 1782957 518998 171.09720 29.519510
## 7 7 1809256 476355 62.53080 7.326488
## 9 9 2113089 474725 108.99350 6.061602
## 6 6 1703140 469050 149.93590 11.351130
## 44 44 1807740 439781 182.23640 114.151900
## 2 2 1619874 424007 86.22219 6.636550
## 45 45 1602362 410149 47.64565 9.166325
## 18 18 1704826 394039 239.96980 33.774130
## 11 11 1583446 389886 44.81977 2.036961
## 47 47 1665657 387853 12.84790 6.636550Top 10 least profitable stores
exhib1 <- store[order(Profit),]
exhib1[1:10,1:5]## store Sales Profit MTenure CTenure
## 57 57 699306 122180 24.3485700 2.956879
## 66 66 879581 146058 115.2039000 3.876797
## 41 41 744211 147327 14.9180200 11.926080
## 55 55 925744 147672 6.6703910 18.365500
## 32 32 828918 149033 36.0792600 6.636550
## 13 13 857843 152513 0.6571813 1.577002
## 54 54 811190 159792 6.6703910 3.876797
## 52 52 1073008 169201 24.1185600 3.416838
## 61 61 716589 177046 21.8184200 13.305950
## 37 37 1202917 187765 23.1985000 1.347023Plot of Profit vs MTenure
plot(MTenure,Profit)
Plot of Profit vs CTenure
plot(CTenure,Profit)
library(corrplot)## Warning: package 'corrplot' was built under R version 3.4.3## corrplot 0.84 loadedcorrplot(corr=cor(store[ , c(1:14)], use="complete.obs"),
method ="ellipse")
MTenure
cor(store$Profit,store$MTenure)## [1] 0.4388692Correlation between Profit and CTenure
cor(store$Profit,store$CTenure)## [1] 0.2576789Corrgram of all the variables
library(corrgram)## Warning: package 'corrgram' was built under R version 3.4.3corrgram(store, order=TRUE,
main="Corrgram of all the Variables",
lower.panel=panel.shade, upper.panel=panel.pie,
diag.panel=panel.minmax, text.panel=panel.txt) 
The p - Value is 8.193e-05.
Correlation test between Profit and CTenure
cor.test(store$Profit,store$CTenure)##
## Pearson's product-moment correlation
##
## data: store$Profit and store$CTenure
## t = 2.2786, df = 73, p-value = 0.02562
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03262507 0.45786339
## sample estimates:
## cor
## 0.2576789The p - Value is 0.02562.
Regression of Profit on {MTenure, CTenure, Comp, Pop, PedCount, Res, Hours24, Visibility}
regr <- lm(Profit ~ MTenure + CTenure + Comp + Pop + PedCount + Res + Hours24 + Visibility, data = store)
summary(regr)##
## Call:
## lm(formula = Profit ~ MTenure + CTenure + Comp + Pop + PedCount +
## Res + Hours24 + Visibility, data = store)
##
## Residuals:
## Min 1Q Median 3Q Max
## -105789 -35946 -7069 33780 112390
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7610.041 66821.994 0.114 0.909674
## MTenure 760.993 127.086 5.988 9.72e-08 ***
## CTenure 944.978 421.687 2.241 0.028400 *
## Comp -25286.887 5491.937 -4.604 1.94e-05 ***
## Pop 3.667 1.466 2.501 0.014890 *
## PedCount 34087.359 9073.196 3.757 0.000366 ***
## Res 91584.675 39231.283 2.334 0.022623 *
## Hours24 63233.307 19641.114 3.219 0.001994 **
## Visibility 12625.447 9087.620 1.389 0.169411
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 56970 on 66 degrees of freedom
## Multiple R-squared: 0.6379, Adjusted R-squared: 0.594
## F-statistic: 14.53 on 8 and 66 DF, p-value: 5.382e-12regr$coefficients## (Intercept) MTenure CTenure Comp Pop
## 7610.041452 760.992734 944.978026 -25286.886662 3.666606
## PedCount Res Hours24 Visibility
## 34087.358789 91584.675234 63233.307162 12625.447050residuals(regr)## 1 2 3 4 5
## -17870.5566 112390.4448 -24652.2001 21254.9195 -8292.9911
## 6 7 8 9 10
## 89270.7785 84050.0803 -10870.2458 31488.0240 -21849.6437
## 11 12 13 14 15
## -528.7222 -91759.0426 -57806.5916 -7068.7877 -75345.2520
## 16 17 18 19 20
## -6104.0234 -86950.2209 -61254.3355 5413.3764 -5853.2921
## 21 22 23 24 25
## 5094.0156 95869.5511 -31589.1824 53013.4120 36072.8170
## 26 27 28 29 30
## -7386.9737 -28735.7167 -7662.9590 53111.6789 73572.1725
## 31 32 33 34 35
## 14802.3715 -42214.3885 85510.4023 11712.8399 3995.3758
## 36 37 38 39 40
## -13036.0714 -52665.8054 4157.3337 -39500.8957 49125.8347
## 41 42 43 44 45
## -90438.9845 -13683.5771 -38699.0221 -35704.8151 59928.2412
## 46 47 48 49 50
## 36388.7486 -11664.7868 75418.5740 -20696.9041 -56799.7045
## 51 52 53 54 55
## -45563.7849 -42912.6649 112306.9000 -36187.6388 -67002.3454
## 56 57 58 59 60
## 22171.0985 -105788.7112 9050.7093 38001.1613 24195.2780
## 61 62 63 64 65
## -15038.1182 -16284.7396 509.1427 -97461.0600 8243.7616
## 66 67 68 69 70
## -72921.5481 100520.7352 -4625.3831 95310.5717 -27907.3903
## 71 72 73 74 75
## -7364.0084 -65662.7214 9331.0473 106126.6026 43997.8062Summary
1.Profit has the strongest correlation with crew tenure and with manager tenure.
2.Crew skill is directly dependent on the crew tenure, meaning crew retention will lead to increase in skills, which inturn leads to higher profits.
3.The most profitable store is with ID:74 and the least profitable store is :57
4.Profit also has a significantly strong relationship with population served by the store, pedestrian traffic rate and crew skill.It also has a negative correlation with competition and resedential area.
5.stores located in industrial areas generally have a high employee retention and skill rate. Hence, any employee retention programme must primarily be focused in stores located in resedential areas.
6.Coming to the regression part,the p-value of the model is statistically significant.It means it is a good fit model.
7.R square value is:0.6379.It means that 63.79% of variations in the dependent variable is explained by the independent variable.
8.Adjusted R square value is 0.594.It means 59.4% variation in the dependent variable is explained by the independent variable.This values decreases as we add no of independent variables.
9.Variables MTenure, Comp, PedCount, Hours24, CTenure, Pop, Res are Statistically significant with p<0.05.
10.Variable Visibility is statistically insignificant with p>0.05.