#Set the working directory and load the data file.

## Read Input data from raw-data and validation_data

data_raw = read.csv("raw-data.csv", header = TRUE)
data_validation = read.csv("validation_data.csv", header = TRUE)

## View column names

names(data_raw)
names(data_validation)
[1] "Num" "Default...1"
[3] "Total.assets" "Net.worth"
[5] "Total.income" "Change.in.stock"
[7] "Total.expenses" "Profit.after.tax"
[9] "PBDITA" "PBT"
[11] "Cash.profit"
"PBDITA.as...of.total.income"
[13] "PBT.as...of.total.income"
"PAT.as...of.total.income"
[15] "Cash.profit.as...of.total.income" "PAT.as...of.net.worth"
[17] "Sales"
"Income.from.financial.services"
[19] "Other.income" "Total.capital"
[21] "Reserves.and.funds"
"Deposits..accepted.by.commercial.banks."
[23] "Borrowings"
"Current.liabilities...provisions"
[25] "Deferred.tax.liability" "Shareholders.funds"
[27] "Cumulative.retained.profits" "Capital.employed"
[29] "TOL.TNW"
"Total.term.liabilities...tangible.net.worth"
[31] "Contingent.liabilities...Net.worth...." "Contingent.liabilities"
[33] "Net.fixed.assets" "Investments"
[35] "Current.assets" "Net.working.capital"
[37] "Quick.ratio..times." "Current.ratio..times."
[39] "Debt.to.equity.ratio..times."
"Cash.to.current.liabilities..times."
[41] "Cash.to.average.cost.of.sales.per.day" "Creditors.turnover"
[43] "Debtors.turnover"
"Finished.goods.turnover"
[45] "WIP.turnover" "Raw.material.turnover"
[47] "Shares.outstanding" "Equity.face.value"
[49] "EPS" "Adjusted.EPS"
[51] "Total.liabilities" "PE.on.BSE"

## View Structure of Input data

str(data_raw)
str(data_validation)
'data.frame': 3541 obs. of 52 variables:
$ Num : int 1 2 3 4 5 6 7 8 9
10 ...
 $ Networth.Next.Year : num 8890.6 394.3 92.2 2.7
109 ...
$ Total.assets : num 17512.3 941 232.8 2.7
478.5 ...
$ Net.worth : num 7093.2 351.5 100.6 2.7
107.6 ...
$ Total.income : num 24965 1527 477 NA 1580
...
$ Change.in.stock : num 235.8 42.7 -5.2 NA -17
...
$ Total.expenses : num 23658 1455 479 NA 1558
...
$ Profit.after.tax : num 1543.2 115.2 -6.6 NA
5.5 ...
$ PBDITA : num 2860.2 283 5.8 NA
31 ...
$ PBT : num 2417.2 188.4 -6.6 NA
6.3 ...
$ Cash.profit : num 1872.8 158.6 0.3 NA
11.9 ...
$ PBDITA.as...of.total.income : num 11.46 18.53 1.22 0
1.96 ...
$ PBT.as...of.total.income : num 9.68 12.33 -1.38 0 0.4
...
$ PAT.as...of.total.income : num 6.18 7.54 -1.38 0 0.35
2.81 0 0.72 8.29 -2.88 ...
$ Cash.profit.as...of.total.income : num 7.5 10.38 0.06 0
0.75 ...
$ PAT.as...of.net.worth : num 23.78 38.08 -6.35 0
5.25 ...
$ Sales : num 24458 1504 476 NA 1575
...
$ Income.from.financial.services : num 158 4 1.5 NA 3.9 6.4
NA NA 7.3 NA ...
$ Other.income : num 297.2 15.9 0.2 NA
0.9 ...
$ Total.capital : num 423.8 115.5 81.4 0.5
6.2 ...
$ Reserves.and.funds : num 6822.8 257.8 19.2 2.2
161.8 ...
$ Deposits..accepted.by.commercial.banks. : logi NA NA NA NA NA NA ...
$ Borrowings : num 14.9 272.5 35.4 NA
193.1 ...
$ Current.liabilities...provisions : num 9965.9 210 96.8 NA
112.8 ...
$ Deferred.tax.liability : num 284.9 85.2 NA NA
4.6 ...
$ Shareholders.funds : num 7093.2 351.5 100.6 2.7
107.6 ...
$ Cumulative.retained.profits : num 6263.3 247.4 32.4 2.2
82.7 ...
$ Capital.employed : num 7108.1 624 136 2.7
300.7 ...
$ TOL.TNW : num 1.33 1.23 1.44 0 2.83
1.8 0.03 5.17 1.05 3.25 ...
$ Total.term.liabilities...tangible.net.worth: num 0 0.34 0.29 0 1.59
0.37 0.03 0.94 0.3 0.54 ...
$ Contingent.liabilities...Net.worth.... : num 14.8 19.2 45.8 0
34.9 ...
$ Contingent.liabilities : num 1049.7 67.6 46.1 NA
37.6 ...
 $ Net.fixed.assets : num 1900.2 286.4 38.7 2.5
94.8 ...
$ Investments : num 1069.6 2.2 4.3 NA
7.4 ...
$ Current.assets : num 13277.5 563.9 167.5
0.2 349.7 ...
$ Net.working.capital : num 3588.5 203.5 59.6 0.2
215.8 ...
$ Quick.ratio..times. : num 1.18 0.95 1.11 NA 1.41
0.48 NA 0.54 0.59 0.39 ...
$ Current.ratio..times. : num 1.37 1.56 1.55 NA 2.54
1.27 NA 1.15 1.58 0.5 ...
$ Debt.to.equity.ratio..times. : num 0 0.78 0.35 0 1.79
1.09 0.32 2.31 0.94 3.13 ...
$ Cash.to.current.liabilities..times. : num 0.43 0.06 0.21 NA 0
0.11 NA 0.04 0.19 0 ...
$ Cash.to.average.cost.of.sales.per.day : num 68.21 5.96 17.07 NA
0 ...
$ Creditors.turnover : num 3.62 9.8 5.28 0 13 ...
$ Debtors.turnover : num 3.85 5.7 5.07 0
9.46 ...
$ Finished.goods.turnover : num 200.55 14.21 9.24 NA
12.68 ...
$ WIP.turnover : num 21.78 7.49 0.23 NA 7.9
...
$ Raw.material.turnover : num 7.71 11.46 NA 0
17.03 ...
$ Shares.outstanding : num 42381675 11550000
8149090 52404 619635 ...
$ Equity.face.value : num 10 10 10 10 10 10 10
NA 10 10 ...
$ EPS : num 35.52 9.97 -0.5 0 7.91
...
$ Adjusted.EPS : num 7.1 9.97 -0.5 0
7.91 ...
$ Total.liabilities : num 17512.3 941 232.8 2.7
478.5 ...
$ PE.on.BSE : num 27.31 8.17 -5.76 NA NA
...

## View Summary of Input data

summary(data_raw)
summary(data_validation)
data_training = data_raw[ !(data_raw$Num %in% data_validation$Num), ]
dim(data_validation)
dim(data_training)

## Add a column of Default based on the value of NetWorthNextYear.

# 0 if NetWorthNextYear is positive,
#1 if NetWorthNextYear is negative.
 #Then remove the NetWorthNextYear column

data_training$Default <- ifelse(data_training$`Networth Next Year`>=0 ,0,1)

data_training = data_training[,c(1,3,4:53)]

## Reordering the columns so making the details easy to find

data_training = data_training[,order(names(data_training))]
data_validation = data_validation[,order(names(data_validation))]
data_training = data_training[,c(29,1:28,30:52)] data_validation =
data_validation[,c(29,1:28,30:52)] attach(data_training)

##Default Rate for the data set

default_rate = (sum(data_training$Default)/(nrow(data_training)))*100
paste("Default Rate for the dataset is ", default_rate, "%")

## For finding the missing values:

missing_values = lapply(data_training,function(x)
sum(is.na(x))) missing_values
missmap(data_training, main = "Missing values vs
observed")
Output:
> missing_values
$`Networth Next
Year` [1] 0

$`Adjusted
EPS` [1] 0

$Borrowings
[1] 301

$`Capital
employed` [1] 0

$`Cash profit`
[1] 108

$`Cash profit as % of total

income` [1] 57

$`Cash to average cost of sales per

day` [1] 70

$`Cash to current liabilities

(times)` [1] 8
[1] 366

$`Contingent liabilities` [1] 974

$`Contingent liabilities / Net worth (%)` [1] 0

$`Creditors turnover` [1] 38

$`Cumulative retained profits` [1] 31

$`Current assets` [1] 52

$`Current liabilities & provisions` [1] 82

$`Current ratio (times)` [1] 81

$`Debt to equity ratio (times)` [1] 0

$`Debtors turnover` [1] 34

$Default
[1] 0

$`Deferred tax liability` [1] 911

$`Deposits (accepted by commercial banks)` [1] 2826

$EPS
[1] 0

$`Equity face value` [1] 0

$`Finished goods turnover` [1] 369

$`Income from financial services` [1] 759

$Investments
[1] 1155

$`Net fixed assets` [1] 104

$`Net working capital` [1] 27

#Remove columns for both test and training data for which more than
50% is missing i.e. ones which have more 1416 missing
data_training <-subset(data_training,-c(data_training$`PE on
BSE`,data_training$`Deposits (accepted by commercial
banks)`,data_training$Investments))
data_validation <- subset(data_validation, select =
-c(data_validation$`PE on BSE`,data_validation$`Deposits (accepted by
commercial banks)`,data_validation$Investments))

## Now replacing the NA by the mean value for the given attribute:
mean_values = array()

##Replace the rest of missing NAs with mean values in TRAINING data.
for (i in 1:length(data_training)) {
mean_values[i] = mean(data_training[,i],na.rm=T)
data_training[,i][is.na(data_training[,i])] <-
mean_values[i]
}
#Replace the rest of missing NAs with mean values for given
training & validation data.
data_validation_non_missing = data_validation
for (i in 1:length(data_validation_non_missing)) {
data_validation_non_missing[,i]
[is.na(data_validation_non_missing[,i])] <-
mean(data_validation_non_missing[,i],na.rm=T)
}
#Code for the capping for 99% & 1% values to reduce
the number of outliers:
## Remove Outliers
data_summary = summary(data_training)
data_summary
col_length = ncol(data_summary)

View(data_training)

data_training_pruned
=data_training
View(data_training_pru
ned)
#Remove anything above 99% and Remove anything below 1%
for (i in 2:col_length) {
# for (i in 2:18) {
if (colnames(data_training_pruned)[i] != "Default") {
topmost = quantile(data_training[,i], 0.99)
bottommost = quantile(data_training[,i], 0.01)
data_training_pruned = training_pruned[data_training_pruned[,i] <
topmost,]
#Logistic Regression

library(ISLR)
library(dplyr)
library(ggvis)
library(boot)
library(rJava)
str(data)
## 'data.frame': 3541 obs. of 52 variables:
## $ X...Num : int 12345 6789
10 ...
## $ Default : int 11111 1111
0 ...
## $ Total.assets : int 17512 941 233 3
479 2434 327 80 574 89 ...
## $ Net.worth : int 7093 352 101 3 108
676 245 13 239 20 ...
## $ Total.income : int 24965 1527 477 0
1581 2649 0 154 583 83 ...
## $ Change.in.stock : int 236 43 -5 0 -17 62

0 -9 31 -7 ...
## $ Total.expenses : int 23658 1455 479 0
1558 2636 0 144 565 79 ...
## $ Profit.after.tax : int 1543 115 -7 0 6 75
0 1 48 -2 ...
## $ PBDITA : int 2860 283 6 0 31
200 0 10 110 0 ...
## $ PBT : int 2417 188 -7 0 6 75
0 2 69 -14 ...
## $ Cash.profit : int 1873 159 0 0 12
147 0 4 83 -11 ...
## $ PBDITA.as...of.total.income : int 11 19 1 0 2 8 0 6
19 0 ...
## $ PBT.as...of.total.income : int 10 12 -1 0 0 3 0 1
12 -17 ...
## $ PAT.as...of.total.income : int 6 8 -1 0 0 3 0 1 8
-3 ...
## $ Cash.profit.as...of.total.income : int 8 10 0 0 1 6 0 3
14 -13 ...
## $ PAT.as...of.net.worth : int 24 38 -6 0 5 22 0
10 22 -12 ...
## $ Sales : int 24458 1504 476 1
1575 2640 1 153 574 83 ...
## $ Income.from.financial.services : int 158 4 2 0 4 6 0 0
7 0 ...
## $ Other.income : int 297 16 0 0 1 0 0 0
1 0 ...
## $ Total.capital : int 424 116 81 1 6 34
78 10 58 50 ...
## $ Reserves.and.funds : int 6823 258 19 2 162
972 241 -2 201 -30 ...
## $ Deposits..accepted.by.commercial.banks. : logi NA NA NA NA NA NA
...
## $ Borrowings : int 15 273 35 0 193
717 8 29 204 61 ...
## $ Current.liabilities...provisions: int 9966 210 97 0 113
556 0 37 75 2 ...
## $ Deferred.tax.liability : int 285 85 0 0 5 54 0
1 36 5 ...
## $ Shareholders.funds : int 7093 352 101 3 108
698 315 13 259 20 ...
## $ Cumulative.retained.profits : int 6263 247 32 2 83
318 -4 -2 174 -30 ...
## $ Capital.employed : int 7108 624 136 3 301
1415 323 42 463 81 ...
## $ TOL.TNW : int 1 1 1 0 3 2 0 5 1
3 ...
## $ Total.term.liabilities...tangible.net.worth: int 0 0 0 0 2 0 0 1 0

1 ...
## $ Contingent.liabilities...Net.worth.... : int 15 19 46 0 35
36 0
0 40 0 ...
## $ Contingent.liabilities : int 1050 68 46 0 38
245 0 0 95 0 ...
## $ Net.fixed.assets : int 1900 286 39 3 95
865 0 10 207 24 ...
## $ Investments : int 1070 2 4 0 7 23
298 0 0 7 ...
## $ Current.assets : int 13278 564 168 0
350 1296 21 62 328 27 ...
## $ Net.working.capital : int 3589 204 60 0 216
279 21 8 120 -26 ...
## $ Quick.ratio..times. : int 111010011
0 ...
## $ Current.ratio..times. : int 122031012
1 ...
## $ Debt.to.equity.ratio..times. : int 010021021
3 ...
## $ Cash.to.current.liabilities..times.: int 000000000
0 ...
## $ Cash.to.average.cost.of.sales.per.day : int 68 6 17 0 0 16
05
29 1 ...
## $ Creditors.turnover : int 4 10 5 0 13 7 0 3
13 0 ...
## $ Debtors.turnover : int 4 6 5 0 9 21 0 6 7
3 ...
## $ Finished.goods.turnover : int 201 14 9 1 13 10 1
15 6 43 ...
## $ WIP.turnover : int 22 7 0 0 8 8 0 11
5 6 ...
## $ Raw.material.turnover : int 8 11 0 0 17 5 0 6
4 5 ...
## $ Shares.outstanding : int 42381675 11550000
8149090 52404 619635 1141718 50070 359249712 3807100 5000000 ...
## $ Equity.face.value : int 10 10 10 10 10 10
10 1000 10 10 ...
## $ EPS : int 36 10 -1 0 8 31 0
0 13 0 ...
## $ Adjusted.EPS : int 7 10 -1 0 8 15 0 0
1 0 ...
## $ Total.liabilities : int 17512 941 233 3
479 2434 327 80 574 89 ...
## $ PE.on.BSE : int 27 8 -6 363 363
363 363 363 12 -2 ...
head(data)
## X...Num Default Total.assets Net.worth Total.income Change.in.stock
## 1 1 1 17512 7093 24965 236

## 2 2 1 941 352 1527 43

## 3 3 1 233 101 477 -5
## 4 4 1 3 3 0 0
## 5 5 1 479 108 1581 -17
## 6 6 1 2434 676 2649 62
## Total.expenses Profit.after.tax PBDITA PBT Cash.profit
## 1 23658 1543 2860 2417 1873
## 2 1455 115 283 188 159
## 3 479 -7 6 -7 0
## 4 0 0 0 0 0
## 5 1558 6 31 6 12
## 6 2636 75 200 75 147
## PBDITA.as...of.total.income PBT.as...of.total.income
## 1 11 10
## 2 19 12
## 3 1 -1
## 4 0 0
## 5 2 0
## 6 8 3
## PAT.as...of.total.income Cash.profit.as...of.total.income

## 1 6 8
## 2 8 10
## 3 -1 0
## 4 0 0
## 5 0 1
## 6 3 6
## PAT.as...of.net.worth Sales Income.from.financial.services

Other.income
## 1
297 24 24458 158
## 2 38 1504 4
16
## 3 -6 476 2
0
## 4 0 1 0
0
## 5 5 1575 4
1
## 6 22 2640 6
0
## Total.capital Reserves.and.funds
Deposits..accepted.by.commercial.banks.
## 1 424 6823
NA
## 2 116 258

NA
## 3 81 19
NA
## 4 1 2
NA
## 5 6 162
NA
## 6 34 972
NA
## Borrowings Current.liabilities...provisions Deferred.tax.liability
## 1 15 9966 285
## 2 273 210 85
## 3 35 97 0
## 4 0 0 0
## 5 193 113 5
## 6 717 556 54
## Shareholders.funds Cumulative.retained.profits
Capital.employed
TOL.TNW
## 1 7093 6263 7108
1
## 2 352 247 624
1
## 3 101 32 136
1
## 4 3 2 3
0
## 5 108 83 301
3
## 6 698 318 1415
2
## Total.term.liabilities...tangible.net.worth

## 1 0
## 2 0
## 3 0
## 4 0
## 5 2
## 6 0
## Contingent.liabilities...Net.worth.... Contingent.liabilities
## 1 15 1050
## 2 19 68
## 3 46 46
## 4 0 0
## 5 35 38
## 6 36 245
## Net.fixed.assets Investments Current.assets
Net.working.capital
## 1 1900 1070 13278 3589

## 2 286 2 564 204

## 3 39 4 168 60
## 4 3 0 0 0
## 5 95 7 350 216
## 6 865 23 1296 279
## Quick.ratio..times. Current.ratio..times.
Debt.to.equity.ratio..times.
## 1 1 1
0
## 2 1 2
1
## 3 1 2
0
## 4 0 0
0
## 5 1 3
2
## 6 0 1
1
## Cash.to.current.liabilities..times.
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## Cash.to.average.cost.of.sales.per.day Creditors.turnover
## 1 68 4
## 2 6 10
## 3 17 5
## 4 0 0
## 5 0 13
## 6 16 7
## Debtors.turnover Finished.goods.turnover WIP.turnover
## 1 4 201 22
## 2 6 14 7
## 3 5 9 0
## 4 0 1 0
## 5 9 13 8
## 6 21 10 8
## Raw.material.turnover Shares.outstanding Equity.face.value EPS
## 1 8 42381675 10 36
## 2 11 11550000 10 10
## 3 0 8149090 10 -1
## 4 0 52404 10 0

## 5 17 619635 10 8
## 6 5 1141718 10 31
## Adjusted.EPS Total.liabilities PE.on.BSE
## 1 7 17512 27
## 2 10 941 8
## 3 -1 233 -6
## 4 0 3 363
## 5 8 479 363
## 6 15 2434 363
summary(data)
## X...Num Default Total.assets Net.worth
## Min. : 1 Min. :0.0000 Min. : 2 Min. :
0.0
## 1st Qu.: 886 1st Qu.:1.0000 1st Qu.: 91 1st Qu.:
31.0
## Median :1771 Median :1.0000 Median : 310 Median : 102.0
## Mean :1771 Mean :0.9339 Mean : 2051 Mean : 754.1
## 3rd Qu.:2656 3rd Qu.:1.0000 3rd Qu.: 1099 3rd Qu.: 377.0
## Max. :3541 Max. :1.0000 Max. :51659 Max. :20921.0
## Total.income Change.in.stock Total.expenses Profit.after.tax
## Min. : 0 Min. :-283.00 Min. : 0 Min. :-
192.0
## 1st Qu.: 76 1st Qu.: -1.00 1st Qu.: 75 1st Qu.:
0.0
## Median : 371 Median : 1.00 Median : 361 Median : 8.0
## Mean : 2028 Mean : 19.54 Mean : 1905 Mean : 128.8
## 3rd Qu.: 1340 3rd Qu.: 13.00 3rd Qu.: 1285 3rd Qu.: 48.0
## Max. :43481 Max. : 676.00 Max. :38581 Max.
:4345.0
## PBDITA PBT Cash.profit
## Min. : -25.0 Min. :-202.0 Min. :-117.0
## 1st Qu.: 5.0 1st Qu.: 0.0 1st Qu.: 2.0
## Median : 32.0 Median : 11.0 Median : 17.0
## Mean : 285.4 Mean : 175.6 Mean : 189.9
## 3rd Qu.: 139.0 3rd Qu.: 68.0 3rd Qu.: 87.0
## Max. :7498.0 Max. :5803.0 Max. :5818.0
## PBDITA.as...of.total.income PBT.as...of.total.income
## Min. :-67.00 Min. :-260.0000
## 1st Qu.: 5.00 1st Qu.: 0.0000
## Median : 9.00 Median : 3.0000
## Mean : 11.03 Mean : 0.2883
## 3rd Qu.: 16.00 3rd Qu.: 9.0000
## Max. : 81.00 Max. : 52.0000
## PAT.as...of.total.income Cash.profit.as...of.total.income ## Min. :-
238.0000 Min. :-136.000
## 1st Qu.: 0.0000 1st Qu.: 2.000
## Median : 2.0000 Median : 5.000
## Mean : -0.8763 Mean : 4.862
## 3rd Qu.: 6.0000 3rd Qu.: 11.000

## Max. : 44.0000 Max. : 57.000

## PAT.as...of.net.worth Sales Income.from.financial.services
## Min. :-141.000 Min. : 1 Min. : 0.0
## 1st Qu.: 0.000 1st Qu.: 71 1st Qu.: 0.0
## Median : 8.000 Median : 358 Median : 1.0
## Mean : 8.935 Mean : 1969 Mean : 25.2
## 3rd Qu.: 20.000 3rd Qu.: 1315 3rd Qu.: 5.0
## Max. : 97.000 Max. :42041 Max. :1037.0
## Other.income Total.capital Reserves.and.funds
## Min. : 0.000 Min. : 1.0 Min. : -235.0
## 1st Qu.: 0.000 1st Qu.: 13.0 1st Qu.: 3.0
## Median : 0.000 Median : 42.0 Median : 50.0
## Mean : 9.661 Mean : 149.8 Mean : 609.8
## 3rd Qu.: 3.000 3rd Qu.: 100.0 3rd Qu.: 263.0
## Max. :368.000 Max. :2939.0 Max. :17698.0
## Deposits..accepted.by.commercial.banks. Borrowings
## Mode:logical Min. : 0.0
## NA's:35411st Qu.: 11.0
## Median : 75.0
## Mean : 616.6
## 3rd Qu.: 296.0
## Max. :17534.0 ## Current.liabilities...provisions Deferred.tax.liability ##
Min. : 0.0 Min. : 0.00
## 1st Qu.: 15.0 1st Qu.: 0.00
## Median : 65.0 Median : 4.00
## Mean : 475.6 Mean : 83.79
## 3rd Qu.: 249.0 3rd Qu.: 27.00
## Max. :11525.0 Max. :3537.00
## Shareholders.funds Cumulative.retained.profits Capital.employed ## Min.
: 0.0 Min. : -501.0 Min. : 1
## 1st Qu.: 32.0 1st Qu.: 1.0 1st Qu.: 61
## Median : 106.0 Median : 36.0 Median : 215
## Mean : 769.6 Mean : 444.6 Mean : 1402
## 3rd Qu.: 393.0 3rd Qu.: 199.0 3rd Qu.: 767
## Max. :20921.0 Max. :13090.0 Max. :34915
## TOL.TNW Total.term.liabilities...tangible.net.worth
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 1.000 1st Qu.: 0.000
## Median : 1.000 Median : 0.000
## Mean : 3.202 Mean : 1.202
## 3rd Qu.: 3.000 3rd Qu.: 1.000
## Max. :56.000 Max. :29.000
## Contingent.liabilities...Net.worth.... Contingent.liabilities
## Min. : 0.00 Min. : 0.0
## 1st Qu.: 0.00 1st Qu.: 0.0
## Median : 5.00 Median : 6.0
## Mean : 36.07 Mean : 281.5
## 3rd Qu.: 31.00 3rd Qu.: 84.0
## Max. :774.00 Max. :12158.0
## Net.fixed.assets Investments Current.assets
Net.working.capital
## Min. : 0.0 Min. : 0.0 Min. : 0.0 Min. :-
1771.0
## 1st Qu.: 22.0 1st Qu.: 0.0 1st Qu.: 32.0 1st Qu.:
-1.0
## Median : 87.0 Median : 0.0 Median :
138.0 Median : 16.0
## Mean : 648.6 Mean : 228.7 Mean : 780.6 Mean :
106.9
## 3rd Qu.: 329.0 3rd Qu.: 16.0 3rd Qu.: 486.0 3rd Qu.:
82.0
## Max. :17183.0 Max. :17183.0 Max. :17836.0 Max. :
3689.0
## Quick.ratio..times. Current.ratio..times. Debt.to.equity.ratio..times.
## Min. : 0.000 Min. : 0.0 Min. : 0.000
## 1st Qu.: 0.000 1st Qu.: 1.0 1st Qu.: 0.000
## Median : 1.000 Median : 1.0 Median : 1.000
## Mean : 1.056 Mean : 1.7 Mean : 1.939
## 3rd Qu.: 1.000 3rd Qu.: 2.0 3rd Qu.: 2.000
## Max. :15.000 Max. :19.0 Max. :37.000
## Cash.to.current.liabilities..times.

Cash.to.average.cost.of.sales.per.day
##
## Min. :0.0000
1st Qu.:0.0000 Min. :
1st Qu.: 0.00
3.00
## Median :0.0000 Median : 8.00
## Mean :0.2203 Mean : 47.24
## 3rd Qu.:0.0000 3rd Qu.: 21.00
## Max. :6.0000 Max. :1278.00
## Creditors.turnover Debtors.turnover Finished.goods.turnover
## Min. : 0.00 Min. : 0.00 Min. : 1
## 1st Qu.: 4.00 1st Qu.: 4.00 1st Qu.: 6
## Median : 7.00 Median : 7.00 Median :
16
## Mean : 21.97 Mean : 28.62 Mean : 136

##
##
## 3rd Qu.: 15.00
Max. :135.00
WIP.turnover 3rd Qu.: 15.00 3rd Qu.: 49
Max. :202.00 Max. :1123
Raw.material.turnover Shares.outstanding
## Min. : 0.00 Min. : 0.00 Min. : 14121
## 1st Qu.: 4.00 1st Qu.: 3.00 1st Qu.: 2209860
## Median : 9.00 Median : 7.00 Median :
6297477
## Mean : 39.05 Mean : 17.69 Mean : 84573778
## 3rd Qu.: 24.00 3rd Qu.: 15.00 3rd Qu.: 57890000
## Max. :269.00 Max. :102.00 Max. :359249712
## Equity.face.value EPS Adjusted.EPS Total.liabilities
## Min. : 1.0 Min. :-65.00 Min. :-65.00 Min. :
2
## 1st Qu.: 10.0 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.:
91
## Median : 10.0 Median : 1.00 Median :
1.00 Median : 310
## Mean : 218.9 Mean : 25.87 Mean : 24.69 Mean :
2051
## 3rd Qu.: 100.0 3rd Qu.: 10.00 3rd Qu.: 7.00 3rd Qu.:
1099
## Max. :1000.0 Max. :896.00 Max. :896.00 Max.
:51659
## PE.on.BSE
## Min. :-163.0
## 1st Qu.: 13.0
## Median : 363.0
## Mean : 228.7
## 3rd Qu.: 363.0
## Max. : 363.0
dim(data)
## [1] 3541 52
train <- data[,2:52]
val <- val[,2:52] str(train)
## 'data.frame': 3541 obs. of 51 variables:
## $ Default : int 111 111111
0 ...
## $ Total.assets : int 17512 941 233 3
479 2434 327 80 574 89 ...
## $ Net.worth : int 7093 352 101 3 108
676 245 13 239 20 ...
## $ Total.income : int 24965 1527 477 0
1581 2649 0 154 583 83 ...
## $ Change.in.stock : int 236 43 -5 0 -17 62
0 -9 31 -7 ...
## $ Total.expenses : int 23658 1455 479 0
1558 2636 0 144 565 79 ...
## $ Profit.after.tax : int 1543 115 -7 0 6 75
0 1 48 -2 ...
## $ PBDITA : int 2860 283 6 0 31
200 0 10 110 0 ...
## $ PBT : int 2417 188 -7 0 6 75

0 2 69 -14 ...
## $ Cash.profit : int 1873 159 0 0 12
147 0 4 83 -11 ...
## $ PBDITA.as...of.total.income : int 11 19 1 0 2 8 0 6
19 0 ...
## $ PBT.as...of.total.income : int 10 12 -1 0 0 3 0 1
12 -17 ...
## $ PAT.as...of.total.income : int 6 8 -1 0 0 3 0 1 8
-3 ...
## $ Cash.profit.as...of.total.income : int 8 10 0 0 1 6 0 3
14 -13 ...
## $ PAT.as...of.net.worth : int 24 38 -6 0 5 22 0
10 22 -12 ...
## $ Sales : int 24458 1504 476 1
1575 2640 1 153 574 83 ...
## $ Income.from.financial.services : int 158 4 2 0 4 6 0 0
7 0 ...
## $ Other.income : int 297 16 0 0 1 0 0 0
1 0 ...
## $ Total.capital : int 424 116 81 1 6 34
78 10 58 50 ...
## $ Reserves.and.funds : int 6823 258 19 2 162
972 241 -2 201 -30 ...
## $ Deposits..accepted.by.commercial.banks. : logi NA NA NA NA NA NA
...
## $ Borrowings : int 15 273 35 0 193
717 8 29 204 61 ...
## $ Current.liabilities...provisions: int 9966 210 97 0 113
556 0 37 75 2 ...
## $ Deferred.tax.liability : int 285 85 0 0 5 54 0
1 36 5 ...
## $ Shareholders.funds : int 7093 352 101 3 108
698 315 13 259 20 ...
## $ Cumulative.retained.profits : int 6263 247 32 2 83
318 -4 -2 174 -30 ...
## $ Capital.employed : int 7108 624 136 3 301
1415 323 42 463 81 ...
## $ TOL.TNW : int 1 1 1 0 3 2 0 5 1
3 ...
## $ Total.term.liabilities...tangible.net.worth: int 0 0 0 0 2 0 0 1 0
1 ...
## $ Contingent.liabilities...Net.worth.... : int 15 19 46 0 35 36 0
0 40 0 ...
## $ Contingent.liabilities : int 1050 68 46 0 38
245 0 0 95 0 ...
## $ Net.fixed.assets : int 1900 286 39 3 95
865 0 10 207 24 ...
## $ Investments : int 1070 2 4 0 7 23

298 0 0 7 ...
## $ Current.assets : int 13278 564 168 0
350 1296 21 62 328 27 ...
## $ Net.working.capital : int 3589 204 60 0 216
279 21 8 120 -26 ...
## $ Quick.ratio..times. : int 111010011
0 ...
## $ Current.ratio..times. : int 122031012
1 ...
## $ Debt.to.equity.ratio..times. : int 010021021
3 ...
## $ Cash.to.current.liabilities..times.: int 000000000
0 ...
## $ Cash.to.average.cost.of.sales.per.day : int 68 6 17 0 0 16
05
29 1 ...
## $ Creditors.turnover : int 4 10 5 0 13 7 0 3
13 0 ...
## $ Debtors.turnover : int 4 6 5 0 9 21 0 6 7
3 ...
## $ Finished.goods.turnover : int 201 14 9 1 13 10 1
15 6 43 ...
## $ WIP.turnover : int 22 7 0 0 8 8 0 11
5 6 ...
## $ Raw.material.turnover : int 8 11 0 0 17 5 0 6
4 5 ...
## $ Shares.outstanding : int 42381675 11550000
8149090 52404 619635 1141718 50070 359249712 3807100 5000000 ...
## $ Equity.face.value : int 10 10 10 10 10 10
10 1000 10 10 ...
## $ EPS : int 36 10 -1 0 8 31 0
0 13 0 ...
## $ Adjusted.EPS : int 7 10 -1 0 8 15 0 0
1 0 ...
## $ Total.liabilities : int 17512 941 233 3
479 2434 327 80 574 89 ...
## $ PE.on.BSE : int 27 8 -6 363 363
363 363 363 12 -2 ...
View(train)
## Warning: running command ''/usr/bin/otool' -L '/Library/Frameworks/ ##
R.framework/Resources/modules/R_de.so'' had status 1
dim(train)
## [1] 3541 51
str(train)
## 'data.frame': 3541 obs. of 51 variables:
## $ Default : int 1 1 1 1 1 1 1 1 1
0 ...
## $ Total.assets : int 17512 941 233 3
479 2434 327 80 574 89 ...

## $ Net.worth
676 245 13 239 20 ... : int 7093 352 101 3 108
## $ Total.income : int 24965 1527 477 0
1581 2649 0 154 583 83 ...
## $ Change.in.stock : int 236 43 -5 0 -17 62
0 -9 31 -7 ...
## $ Total.expenses : int 23658 1455 479 0
1558 2636 0 144 565 79 ...
## $ Profit.after.tax : int 1543 115 -7 0 6 75
0 1 48 -2 ...
## $ PBDITA : int 2860 283 6 0 31
200 0 10 110 0 ...
## $ PBT : int 2417 188 -7 0 6 75
0 2 69 -14 ...
## $ Cash.profit : int 1873 159 0 0 12
147 0 4 83 -11 ...
## $ PBDITA.as...of.total.income
: int 11 19 1 0 2 8 0 6
19 0 ...
## $ PBT.as...of.total.income
: int 10 12 -1 0 0 3 0 1
12 -17 ...
## $ PAT.as...of.total.income
: int 6 8 -1 0 0 3 0 1 8
-3 ...
## $ Cash.profit.as...of.total.income
: int 8 10 0 0 1 6 0 3
14 -13 ...
## $ PAT.as...of.net.worth
: int 24 38 -6 0 5 22 0
10 22 -12 ...
## $ Sales : int 24458 1504 476 1
1575 2640 1 153 574 83 ...
## $ Income.from.financial.services : int 158 4 2 0 4 6 0 0
7 0 ...
## $ Other.income : int 297 16 0 0 1 0 0 0
1 0 ...
## $ Total.capital : int 424 116 81 1 6 34
78 10 58 50 ...
## $ Reserves.and.funds : int 6823 258 19 2 162
972 241 -2 201 -30 ...
## $ Deposits..accepted.by.commercial.banks. : logi NA NA
NA NA NA NA
...
## $ Borrowings : int 15 273 35 0 193
717 8 29 204 61 ...
## $ Current.liabilities...provisions : int 9966 210 97 0 113
556 0 37 75 2 ...
## $ Deferred.tax.liability : int 285 85 0 0 5 54 0
1 36 5 ...
## $ Shareholders.funds : int 7093 352 101 3 108
698 315 13 259 20 ...
## $ Cumulative.retained.profits : int 6263 247 32 2 83
318 -4 -2 174 -30 ...

## $ Capital.employed
1415 323 42 463 81 ... : int 7108 624 136 3 301
## $ TOL.TNW : int 1110 32 0 51
3 ...
## $ Total.term.liabilities...tangible.net.worth: int
0000 20 0 10
1 ...
## $ Contingent.liabilities...Net.worth.... : int 15 19 46 0
35 36 0
0 40 0 ...
## $ Contingent.liabilities : int 1050 68 46 0 38
245 0 0 95 0 ...
## $ Net.fixed.assets : int 1900 286 39 3 95
865 0 10 207 24 ...
## $ Investments : int 1070 2 4 0 7 23
298 0 0 7 ...
## $ Current.assets : int 13278 564 168 0
350 1296 21 62 328 27 ...
## $ Net.working.capital : int 3589 204 60 0
216
279 21 8 120 -26 ...
## $ Quick.ratio..times. : int 1110 10 0 11
0 ...
## $ Current.ratio..times. : int 1220 31 0 1
2
1 ...
## $ Debt.to.equity.ratio..times. : int 0100 21 0
21
3 ...
## $ Cash.to.current.liabilities..times.: int 0000 00 0
00
0 ...
## $ Cash.to.average.cost.of.sales.per.day : int 68 6 17 0
0 16 05
29 1 ...
## $ Creditors.turnover : int 4 10 5 0 13 7 03
13 0 ...
## $ Debtors.turnover : int 4650 9 21 0 6 7
3 ...
## $ Finished.goods.turnover : int 201 14 9 1 13
10 1
15 6 43 ...
## $ WIP.turnover : int 22 7 0 0 8 80 11
5 6 ...
## $ Raw.material.turnover : int 8 11 0 0 17 5 0
6
4 5 ...
## $ Shares.outstanding : int 42381675 11550000
8149090 52404 619635 1141718 50070 359249712 3807100 5000000 ...

## $ Equity.face.value : int 10 10 10 10 10 10
10 1000 10 10 ...
## $ EPS : int 36 10 -1 0 8 31 0
0 13 0 ...
## $ Adjusted.EPS : int 7 10 -1 0 8 15 00
1 0 ...
## $ Total.liabilities : int 17512 941 233 3
479 2434 327 80 574 89 ...

## $ PE.on.BSE : int 27 8 -6 363 363

363 363 363 12 -2 ...

#Let's remove the blank variable from the file

## $ Borrowings : int 15 273 35 0 193
717 8 29 204 61 ...
## $ Current.liabilities...provisions: int 9966 210 97 0 113
556 0 37 75 2 ...
## $ Deferred.tax.liability : int 285 85 0 0 5 54 0
1 36 5 ...
## $ Shareholders.funds : int 7093 352 101 3 108
698 315 13 259 20 ...
## $ Cumulative.retained.profits : int 6263 247 32 2 83
318 -4 -2 174 -30 ...
## $ Capital.employed : int 7108 624 136 3 301
1415 323 42 463 81 ...
## $ TOL.TNW : int 1 1 1 0 3 2 0 5 1
3 ...
## $ Total.term.liabilities...tangible.net.worth: int 0 0 0 0 2 0 0 1 0
1 ...
## $ Contingent.liabilities...Net.worth.... : int 15 19 46 0 35 36 0
0 40 0 ...
## $ Contingent.liabilities : int 1050 68 46 0 38
245 0 0 95 0 ...
## $ Net.fixed.assets : int 1900 286 39 3 95
865 0 10 207 24 ...
## $ Investments : int 1070 2 4 0 7 23
298 0 0 7 ...
## $ Current.assets : int 13278 564 168 0
350 1296 21 62 328 27 ...
## $ Net.working.capital : int 3589 204 60 0 216
279 21 8 120 -26 ...
## $ Quick.ratio..times. : int 1 1 1 0 1 0 0 1 1
0 ...
## $ Current.ratio..times. : int 1 2 2 0 3 1 0 1 2
1 ...
## $ Debt.to.equity.ratio..times. : int 0 1 0 0 2 1 0 2 1
3 ...
## $ Cash.to.current.liabilities..times. : int 0 0 0 0 0 0 0 0 0
0 ...
## $ Cash.to.average.cost.of.sales.per.day : int 68 6 17 0 0 16 0 5
29 1 ...
## $ Creditors.turnover : int 4 10 5 0 13 7 0 3
13 0 ...
## $ Debtors.turnover : int 4 6 5 0 9 21 0 6 7
3 ...
## $ Finished.goods.turnover : int 201 14 9 1 13 10 1
15 6 43 ...
## $ WIP.turnover : int 22 7 0 0 8 8 0 11
5 6 ...
## $ Raw.material.turnover : int 8 11 0 0 17 5 0 6
4 5 ...

## $ Shares.outstanding
8149090 52404 619635 1141718 50070 359249712 : int 42381675
11550000
3807100 5000000 ...
## $ Equity.face.value : int 10 10 10 10 10 10
10 1000 10 10 ...
## $ EPS : int 36 10 -1 0 8 31 0
0 13 0 ...
## $ Adjusted.EPS : int 7 10 -1 0 8 15 0
1 0 ...
## $ Total.liabilities : int 17512 941 233 3
479 2434 327 80 574 89 ...
## $ PE.on.BSE : int 27 8 -6 363 363
363 363 363 12 -2 ...

#Let's run first iteration

my_logit <- glm(Default~., family = "binomial", data = train)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
my_logit
##
## Call: glm(formula = Default ~ ., family = "binomial", data = train) ##
## Coefficients:
## (Intercept)
## 2.480e+00
## Total.assets
## -4.837e-03
## Net.worth
## 1.927e-03
## Total.income
## -3.294e-02
## Change.in.stock
## -9.628e-03
## Total.expenses
## 2.805e-03
## Profit.after.tax
## -3.300e-03
## PBDITA
## 3.423e-02
## PBT
## 1.544e-03
## Cash.profit
## 8.677e-03
## PBDITA.as...of.total.income
## -3.056e-03
## PBT.as...of.total.income
## 9.450e-03
## PAT.as...of.total.income

## -1.122e-02
## Cash.profit.as...of.total.income
## 7.606e-03
## PAT.as...of.net.worth
## 2.186e-02
## Sales
## 2.976e-02
## Income.from.financial.services
## 4.540e-02
## Other.income
## 2.707e-02
## Total.capital
## 2.973e-03
## Reserves.and.funds
## 5.914e-03
## Borrowings
## 1.305e-03
## Current.liabilities...provisions
## 5.379e-03
## Deferred.tax.liability
## 3.635e-03
## Shareholders.funds
## 1.107e-03
## Cumulative.retained.profits
## 1.859e-03
## Capital.employed
## 3.352e-03
## TOL.TNW
## -4.281e-02
## Total.term.liabilities...tangible.net.worth
## 5.996e-02
## Contingent.liabilities...Net.worth....
## -1.386e-03
## Contingent.liabilities
## 2.916e-03
## Net.fixed.assets
## -1.190e-03
## Investments
## -1.891e-03
## Current.assets
## -1.590e-03
## Net.working.capital
## 1.027e-03
## Quick.ratio..times.

## 2.479e-01
## Current.ratio..times.
## 1.323e-03
## Debt.to.equity.ratio..times.
## -7.344e-02
## Cash.to.current.liabilities..times.
## -3.563e-01
## Cash.to.average.cost.of.sales.per.day
## -8.885e-04
## Creditors.turnover
## 5.455e-03
## Debtors.turnover
## -3.261e-03
## Finished.goods.turnover
## -1.757e-03
## WIP.turnover
## 5.073e-03
## Raw.material.turnover
## -4.918e-03
## Shares.outstanding
## -5.119e-10
## Equity.face.value
## 8.851e-06
## EPS
## -2.357e-02
## Adjusted.EPS
## 2.418e-02
## Total.liabilities
## NA
## PE.on.BSE
## 9.813e-04
##
## Degrees of Freedom: 3540 Total (i.e. Null); 3492 Residual ## Null
Deviance: 1724
## Residual Deviance: 875.7 AIC: 973.7

anova(my_logit, test = "Chisq")

## Analysis of Deviance Table
##
## Model: binomial, link: logit
##
## Response: Default
##
## Terms added sequentially (first to last)

## ## ## ## NULL Df Deviance Resid. Df

3540
## Total.assets 1 7.2 3539
## Net.worth 1 80.0 3538
## Total.income 1 65.3 3537
## Change.in.stock 1 0.2 3536
## Total.expenses 1 59.3 3535
## Profit.after.tax 1 48.2 3534
## PBDITA 1 58.6 3533
## PBT 1 16.3 3532
## Cash.profit 1 114.4 3531
## PBDITA.as...of.total.income
1 25.0 3530
## PBT.as...of.total.income
1 9.2 3529
## PAT.as...of.total.income
1 0.3 3528
## Cash.profit.as...of.total.income
1 3.9 3527
## PAT.as...of.net.worth
1 145.4 3526
## Sales 1 17.4 3525
## Income.from.financial.services 1 12.6 3524
## Other.income 1 0.0 3523
## Total.capital 1 1.1 3522
## Reserves.and.funds 1 32.4 3521
## Borrowings 1 1.4 3520
## Current.liabilities...provisions 1 13.2 3519
## Deferred.tax.liability 1 1.8 3518
## Shareholders.funds 1 1.0 3517
## Cumulative.retained.profits 1 4.2 3516
## Capital.employed 1 3.3 3515
## TOL.TNW 1 64.9 3514
## Total.term.liabilities...tangible.net.worth
1 0.5 3513
## Contingent.liabilities...Net.worth.... 1 0.0 3512
## Contingent.liabilities 1 10.9 3511
## Net.fixed.assets 1 2.4 3510
## Investments 1 0.0 3509
## Current.assets 1 0.0 3508
## Net.working.capital 1 0.0 3507
## Quick.ratio..times. 1 576.7 3506
## Current.ratio..times. 1 0.0 3505
## Debt.to.equity.ratio..times. 1 0.0 3504
## Cash.to.current.liabilities..times. 1 3316.0 3503
## Cash.to.average.cost.of.sales.per.day 1 0.0 3502
## Creditors.turnover 1 0.0 3501
## Debtors.turnover 1 3099.8 3500

## Finished.goods.turnover 1 0.0 3499

## WIP.turnover 1 0.0 3498
## Raw.material.turnover 1 4181.1 3497
## Shares.outstanding 1 2667.2 3496
## Equity.face.value 1 0.0 3495
## EPS 1 0.0 3494
## Adjusted.EPS 1 0.0 3493
## Total.liabilities 0 0.0 3493
## PE.on.BSE 1 14478.9 3492
## Resid. Dev Pr(>Chi)
## NULL 1723.7
## Total.assets 1716.5 0.0072743 **
## Net.worth 1636.5 < 2.2e-16 ***
## Total.income 1571.2 6.528e-16 ***
## Change.in.stock 1571.0 0.6269971
## Total.expenses 1511.7 1.338e-14 ***
## Profit.after.tax 1463.4 3.781e-12 ***
## PBDITA 1404.9 1.980e-14 ***
## PBT 1388.6 5.539e-05 ***
## Cash.profit 1274.2 < 2.2e-16 ***
## PBDITA.as...of.total.income
1249.2 5.655e-07 ***
## PBT.as...of.total.income
1240.1 0.0024808 **
## PAT.as...of.total.income
1239.8 0.5984652
## Cash.profit.as...of.total.income
1235.8 0.0469348 *
## PAT.as...of.net.worth
1090.4 < 2.2e-16 ***
## Sales 1073.0 3.036e-05 ***
## Income.from.financial.services 1060.4 0.0003876 ***
## Other.income 1060.4 0.9578082
## Total.capital 1059.3 0.2932411
## Reserves.and.funds 1026.9 1.257e-08 ***
## Borrowings 1025.4 0.2285386
## Current.liabilities...provisions 1012.2 0.0002760 ***
## Deferred.tax.liability 1010.4 0.1780105
## Shareholders.funds 1009.4 0.3186585
## Cumulative.retained.profits 1005.2 0.0410643 *
## Capital.employed 1002.0 0.0707777 .
## TOL.TNW 937.0 7.683e-16 ***
## Total.term.liabilities...tangible.net.worth
936.6 0.4989419
## Contingent.liabilities...Net.worth.... 936.6 0.9063633
## Contingent.liabilities 925.6 0.0009474 ***
## Net.fixed.assets 923.2 0.1227011
## Investments 12975.7 1.0000000
## Current.assets 13264.1 1.0000000
## Net.working.capital 13696.6 1.0000000
## Quick.ratio..times. 13119.9 < 2.2e-16 ***
## Current.ratio..times. 13119.9 1.0000000
## Debt.to.equity.ratio..times. 15787.1 1.0000000
## Cash.to.current.liabilities..times. 12471.1 < 2.2e-16 ***
## Cash.to.average.cost.of.sales.per.day 15787.1 1.0000000
## Creditors.turnover 15859.2 1.0000000
## Debtors.turnover 12759.5 < 2.2e-16 ***
## Finished.goods.turnover 13912.9 1.0000000
## WIP.turnover 19103.1 1.0000000
## Raw.material.turnover 14922.1 < 2.2e-16 ***
## Shares.outstanding 12254.8 < 2.2e-16 ***
## Equity.face.value 13119.9 1.0000000
## EPS 13840.8 1.0000000
## Adjusted.EPS 15354.6 1.0000000
## Total.liabilities 15354.6
## PE.on.BSE 875.7 < 2.2e-16 ***

## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(my_logit)
##
## Call:
## glm(formula = Default ~ ., family = "binomial", data = train)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.5474 0.0013 0.1066 0.2671 3.3697
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error z
value
## (Intercept)2.480e+00 2.333e-01
10.629
## Total.assets -4.837e-03 1.818e-03
-2.660
## Net.worth 1.927e-03 2.753e-03
0.700
## Total.income -3.294e-02 7.676e-03
-4.291
## Change.in.stock -9.628e-03 6.273e-03
-1.535
## Total.expenses 2.805e-03 3.931e-03
0.714
## Profit.after.tax -3.300e-03 1.517e-02
-0.218
## PBDITA 3.423e-02 6.620e-03

## PBT 1.544e-03 1.453e-02

0.106
## Cash.profit 8.677e-03 5.072e-03
1.711
## PBDITA.as...of.total.income
-3.056e-03 6.015e-03
-0.508
## PBT.as...of.total.income
9.450e-03 1.692e-02
0.559
## PAT.as...of.total.income
-1.122e-02 1.811e-02
-0.620
## Cash.profit.as...of.total.income
7.606e-03 6.603e-03
1.152
## PAT.as...of.net.worth
2.186e-02 3.106e-03
7.039
## Sales 2.976e-02 6.485e-03
4.589
## Income.from.financial.services 4.540e-02 2.195e-02
2.068
## Other.income 2.707e-02 1.925e-02
1.406
## Total.capital 2.973e-03 1.850e-03
1.608
## Reserves.and.funds 5.914e-03 2.122e-03
2.787
## Borrowings 1.305e-03 6.581e-03
0.198
## Current.liabilities...provisions 5.379e-03 2.063e-03
2.608
## Deferred.tax.liability 3.635e-03 4.063e-03
0.895
## Shareholders.funds 1.107e-03 6.023e-03
0.184
## Cumulative.retained.profits 1.859e-03 2.218e-03
0.838
## Capital.employed 3.352e-03 6.968e-03
0.481
## TOL.TNW -4.281e-02 1.886e-02
-2.269
## Total.term.liabilities...tangible.net.worth
5.996e-02 4.377e-02
1.370
## Contingent.liabilities...Net.worth.... -1.386e-03 8.976e-04
-1.544
## Contingent.liabilities 2.916e-03 1.174e-03
2.485
## Net.fixed.assets -1.190e-03 7.400e-04
-1.608
## Investments -1.891e-03 1.653e-03
-1.144

## Current.assets -1.590e-03 1.704e-03

-0.933
## Net.working.capital 1.027e-03 1.855e-03
0.554
## Quick.ratio..times. 2.479e-01 1.231e-01
2.014
## Current.ratio..times. 1.323e-03 6.617e-02
0.020
## Debt.to.equity.ratio..times. -7.344e-02 3.420e-02
-2.148
## Cash.to.current.liabilities..times. -3.563e-01 2.011e-01
-1.772
## Cash.to.average.cost.of.sales.per.day -8.885e-04 3.968e-04
-2.239
## Creditors.turnover 5.455e-03 6.255e-03
0.872
## Debtors.turnover -3.261e-03 3.206e-03
-1.017
## Finished.goods.turnover -1.757e-03 6.833e-04
-2.572
## WIP.turnover 5.073e-03 3.530e-03
1.437
## Raw.material.turnover -4.918e-03 6.989e-03
-0.704
## Shares.outstanding -5.119e-10 2.858e-09
-0.179
## Equity.face.value 8.851e-06 1.043e-03
0.008
## EPS -2.357e-02 2.344e-02
-1.006
## Adjusted.EPS 2.418e-02 2.358e-02
1.025
## Total.liabilities NA NA
NA
## PE.on.BSE 9.813e-04 6.564e-04
1.495
## Pr(>|z|)
## (Intercept)< 2e-16 ***
## Total.assets 0.00781 **
## Net.worth 0.48398
## Total.income 1.78e-05 ***
## Change.in.stock 0.12485
## Total.expenses 0.47550
## Profit.after.tax 0.82777
## PBDITA 2.33e-07 ***
## PBT 0.91537
## Cash.profit 0.08714 .

## PBDITA.as...of.total.income ## PBT.as...of.total.income
## PAT.as...of.total.income
## Cash.profit.as...of.total.income
0.61145 0.57638 0.53557 0.24933
## PAT.as...of.net.worth
1.93e-12 ***
## Sales 4.46e-06 ***
## Income.from.financial.services 0.03863 *
## Other.income 0.15963
## Total.capital 0.10792
## Reserves.and.funds 0.00532 **
## Borrowings 0.84280
## Current.liabilities...provisions 0.00912 **
## Deferred.tax.liability 0.37094
## Shareholders.funds 0.85422
## Cumulative.retained.profits 0.40191
## Capital.employed 0.63049
## TOL.TNW 0.02325 *
## Total.term.liabilities...tangible.net.worth
0.17072
## Contingent.liabilities...Net.worth.... 0.12266
## Contingent.liabilities 0.01297 *
## Net.fixed.assets 0.10789
## Investments 0.25255
## Current.assets 0.35097
## Net.working.capital 0.57971
## Quick.ratio..times. 0.04398 *
## Current.ratio..times. 0.98405
## Debt.to.equity.ratio..times. 0.03173 *
## Cash.to.current.liabilities..times. 0.07640 .
## Cash.to.average.cost.of.sales.per.day 0.02516 *
## Creditors.turnover 0.38317
## Debtors.turnover 0.30911
## Finished.goods.turnover 0.01011 *
## WIP.turnover 0.15071
## Raw.material.turnover 0.48165
## Shares.outstanding 0.85788
## Equity.face.value 0.99323
## EPS 0.31453
## Adjusted.EPS 0.30522
## Total.liabilities NA
## PE.on.BSE 0.13492

## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 ##
## (Dispersion parameter for binomial family taken to be 1)

##
## Null deviance: 1723.67 on 3540 degrees of freedom
## Residual deviance: 875.68 on 3492 degrees of freedom ## AIC: 973.68
##
## Number of Fisher Scoring iterations: 14

#Now is the time to implement and check the performance of boruta

package. The syntax of boruta is almost similar to regression (lm)
method.
# install.packages("Boruta")
library(Boruta)
## Warning: package 'Boruta' was built under R version 3.4.4 ## Loading
required package: ranger
set.seed(123)
boruta.train <- Boruta(Default~., data = train, doTrace = 2)

boruta.train$ImpHistory[is.finite(boruta.train$ImpHistory[,i]),i]) names(lz) <-

colnames(boruta.train$ImpHistory)
Labels <- sort(sapply(lz,median))
axis(side = 1,las=2,labels = names(Labels), at =
1:ncol(boruta.train$ImpHistory), cex.axis = 0.7)

final.boruta <- TentativeRoughFix(boruta.train) print(final.boruta)

## Boruta performed 99 iterations in 6.128146 mins.
## Tentatives roughfixed over the last 99 iterations.
## 42 attributes confirmed important: Adjusted.EPS, Borrowings,
Capital.employed, Cash.profit, Cash.profit.as...of.total.income and 37
more;
## 7 attributes confirmed unimportant:
## Cash.to.average.cost.of.sales.per.day,
## Cash.to.current.liabilities..times., Creditors.turnover,
## Current.ratio..times., Equity.face.value and 2 more;
train <- train[,getSelectedAttributes(final.boruta, withTentative = F)]
train <- cbind(data[2],train) dim(train)
## [1] 3541 43
View(train)
colnames(train[1]) = "Default"

boruta.df <- attStats(final.boruta) class(boruta.df)

## [1] "data.frame"
print(boruta.df)
## meanImp medianImp
## Total.assets 5.6848550 5.4741921
## Net.worth 10.1874958 10.2583608
## Total.income 5.7116518 5.6530456
## Change.in.stock 7.6687597 7.6367323
## Total.expenses 6.0135622 5.9888636
## Profit.after.tax 11.2455511 11.3079792
## PBDITA 8.1337785 8.2247391
## PBT 12.1360119 12.1463871
## Cash.profit 11.2626284 11.2452606
## PBDITA.as...of.total.income 7.9302617 7.9647158
## PBT.as...of.total.income 10.5030411 10.4486280
## PAT.as...of.total.income 9.7589165 9.8462562
## Cash.profit.as...of.total.income 11.8367538 11.9593037
## PAT.as...of.net.worth 16.0474512 16.1155187
## Sales 5.7853502 5.7269845
## Income.from.financial.services 3.6098586 3.5708939
## Other.income 4.6264741 4.6391333
## Total.capital 5.6958011 5.6444980
## Reserves.and.funds 7.8528069 7.6862604
## Borrowings 6.8840979 6.9319835
## Current.liabilities...provisions 6.7433888 6.8067864
## Deferred.tax.liability 4.8057418 4.8025729
## Shareholders.funds 9.7960840 9.7826295
## Cumulative.retained.profits 9.2598965 9.2850155
## Capital.employed 7.5643983 7.4892053
## TOL.TNW 19.8694788 19.8687016
## Total.term.liabilities...tangible.net.worth 13.4156150 13.4252889
## Contingent.liabilities...Net.worth.... 6.4054664 6.4414674
## Contingent.liabilities 5.3286876 5.4567158
## Net.fixed.assets 7.0360965 6.9920044
## Investments 2.0726629 2.1512085
## Current.assets 5.7225924 5.7868951
## Net.working.capital 6.9316837 6.9061285
## Quick.ratio..times. -0.2011067 -0.2369274
## Current.ratio..times. 1.2389497 1.4154778
## Debt.to.equity.ratio..times. 17.5078508 17.5173415

## Cash.to.current.liabilities..times. -0.5556410 -0.4214221

## Cash.to.average.cost.of.sales.per.day 1.2994065 1.4139290
## Creditors.turnover 3.2275236 3.1830241
## Debtors.turnover 4.2788961 4.3319679
## Finished.goods.turnover 3.1429970 3.1617051
## WIP.turnover 4.0050806 4.0382613
## Raw.material.turnover 4.6093714 4.6663572
## Shares.outstanding 2.6656452 2.6975405
## Equity.face.value 1.4750935 1.4800973
## EPS 9.6019601 9.6210269
## Adjusted.EPS 9.8221389 9.7737227
## Total.liabilities 5.6116307 5.5571793
## PE.on.BSE 6.7680547 6.6058002
## minImp maxImp
## Total.assets 3.62169491 7.7741503
## Net.worth 8.53325506 12.0444190
## Total.income 4.25531086 7.5366142
## Change.in.stock 5.35626655 9.3832366
## Total.expenses 4.18795358 7.3671490
## Profit.after.tax 9.29290291 13.3686461
## PBDITA 6.27044306 9.8091873
## PBT 9.36656365 14.7254457
## Cash.profit 9.10122253 13.6766093
## PBDITA.as...of.total.income
6.53077833 8.8221845
## PBT.as...of.total.income
9.21219159 12.1472935
## PAT.as...of.total.income
8.56497301 11.1001274
## Cash.profit.as...of.total.income
8.83198590 13.4750057
## PAT.as...of.net.worth
14.20364693 18.2428335
## Sales 4.32173965 7.2940169
## Income.from.financial.services 1.85487730 5.3457087
## Other.income 2.16619312 6.1257440
## Total.capital 3.95317186 7.5334725
## Reserves.and.funds 5.28518158 10.2431069
## Borrowings 5.21914925 8.2493878
## Current.liabilities...provisions 4.97984341 8.6195315
## Deferred.tax.liability 3.42353937 6.3229262
## Shareholders.funds 8.26480869 11.2969482
## Cumulative.retained.profits 7.66885623 11.2864544
## Capital.employed 6.06110345 9.6531699
## TOL.TNW 18.06039769 21.7118099
## Total.term.liabilities...tangible.net.worth
11.86162704 15.2825980
## Contingent.liabilities...Net.worth.... 3.96629386 8.5538660
## Contingent.liabilities 3.57293041 6.8769645
## Net.fixed.assets 5.13385839 9.0263262

## Investments -0.18075665 4.3997736

## Current.assets 4.39201239 7.3043050
## Net.working.capital 5.27815754 9.4319129
## Quick.ratio..times. -2.33315892 2.2648527
## Current.ratio..times. 0.07273932 2.1790623
## Debt.to.equity.ratio..times. 15.26488058 19.1569294
## Cash.to.current.liabilities..times. -1.97738673 0.7096837
## Cash.to.average.cost.of.sales.per.day -0.59722669 3.6906851
## Creditors.turnover 1.50721188 4.8597755
## Debtors.turnover 1.28315109 5.9750329
## Finished.goods.turnover 0.57756594 4.7961857
## WIP.turnover 2.50435679 5.5606877
## Raw.material.turnover 2.45495657 6.4346714
## Shares.outstanding 0.08664660 4.5428689
## Equity.face.value 0.54803752 2.6758926
## EPS 7.91904021 11.1822860
## Adjusted.EPS 7.43819171 11.8957807
## Total.liabilities 3.81336097 8.2587030
## PE.on.BSE 5.27353957 9.1391080
## normHits decision
## Total.assets 0.97979798 Confirmed
## Net.worth 1.00000000 Confirmed
## Total.income 0.98989899 Confirmed
## Change.in.stock 1.00000000 Confirmed
## Total.expenses 0.98989899 Confirmed
## Profit.after.tax 1.00000000 Confirmed
## PBDITA 1.00000000 Confirmed
## PBT 1.00000000 Confirmed
## Cash.profit 1.00000000 Confirmed
## PBDITA.as...of.total.income 1.00000000 Confirmed
## PBT.as...of.total.income 1.00000000 Confirmed
## PAT.as...of.total.income 1.00000000 Confirmed
## Cash.profit.as...of.total.income 1.00000000 Confirmed
## PAT.as...of.net.worth 1.00000000 Confirmed
## Sales 1.00000000 Confirmed
## Income.from.financial.services 0.73737374 Confirmed
## Other.income 0.91919192 Confirmed
## Total.capital 1.00000000 Confirmed
## Reserves.and.funds 1.00000000 Confirmed
## Borrowings 1.00000000 Confirmed
## Current.liabilities...provisions 1.00000000 Confirmed
## Deferred.tax.liability 0.95959596 Confirmed
## Shareholders.funds 1.00000000 Confirmed
## Cumulative.retained.profits 1.00000000 Confirmed

## Capital.employed 1.00000000 Confirmed

## TOL.TNW 1.00000000 Confirmed
## Total.term.liabilities...tangible.net.worth 1.00000000 Confirmed
## Contingent.liabilities...Net.worth.... 1.00000000 Confirmed
## Contingent.liabilities 0.97979798 Confirmed
## Net.fixed.assets 1.00000000 Confirmed
## Investments 0.22222222 Rejected
## Current.assets 0.98989899 Confirmed
## Net.working.capital 1.00000000 Confirmed
## Quick.ratio..times. 0.00000000 Rejected
## Current.ratio..times. 0.00000000 Rejected
## Debt.to.equity.ratio..times. 1.00000000 Confirmed
## Cash.to.current.liabilities..times. 0.00000000 Rejected
## Cash.to.average.cost.of.sales.per.day 0.01010101 Rejected
## Creditors.turnover 0.60606061 Rejected
## Debtors.turnover 0.83838384 Confirmed
## Finished.goods.turnover 0.57575758 Confirmed
## WIP.turnover 0.82828283 Confirmed
## Raw.material.turnover 0.93939394 Confirmed
## Shares.outstanding 0.38383838 Confirmed
## Equity.face.value 0.01010101 Rejected
## EPS 1.00000000 Confirmed
## Adjusted.EPS 1.00000000 Confirmed
## Total.liabilities 0.96969697 Confirmed
## PE.on.BSE 1.00000000 Confirmed
my_logit1 <- glm(Default~., family = "binomial", data = train)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
my_logit1
##
## Call: glm(formula = Default ~ ., family = "binomial", data = train) ##
## Coefficients:
## (Intercept)
## 2.598e+00
## Total.assets
## -6.136e-03
## Net.worth
## 6.428e-04
## Total.income
## -3.264e-02
## Change.in.stock
## -9.556e-03
## Total.expenses
## 2.398e-03

## Profit.after.tax
## -5.557e-03
## PBDITA
## 3.323e-02
## PBT
## 4.607e-03
## Cash.profit
## 9.070e-03
## PBDITA.as...of.total.income
## -5.804e-03
## PBT.as...of.total.income
## 8.545e-03
## PAT.as...of.total.income
## -9.263e-03
## Cash.profit.as...of.total.income
## 7.531e-03
## PAT.as...of.net.worth
## 2.187e-02
## Sales
## 2.981e-02
## Income.from.financial.services
## 4.569e-02
## Other.income
## 2.607e-02
## Total.capital
## 3.800e-03
## Reserves.and.funds
## 6.725e-03
## Borrowings
## 4.076e-03
## Current.liabilities...provisions
## 6.221e-03
## Deferred.tax.liability
## 4.757e-03
## Shareholders.funds
## 4.020e-03
## Cumulative.retained.profits
## 1.920e-03
## Capital.employed
## 1.641e-03
## TOL.TNW
## -4.839e-02
## Total.term.liabilities...tangible.net.worth
## 7.314e-02

## Contingent.liabilities...Net.worth....
## -1.511e-03
## Contingent.liabilities
## 3.080e-03
## Net.fixed.assets
## -1.043e-03
## Current.assets
## -6.561e-04
## Net.working.capital
## 6.987e-04
## Debt.to.equity.ratio..times.
## -7.458e-02
## Debtors.turnover
## -3.324e-03
## Finished.goods.turnover
## -1.735e-03
## WIP.turnover
## 6.230e-03
## Raw.material.turnover
## -7.932e-04
## Shares.outstanding
## -6.817e-10
## EPS
## -2.328e-02
## Adjusted.EPS
## 2.396e-02
## Total.liabilities
## NA
## PE.on.BSE
## 1.021e-03
##
## Degrees of Freedom: 3540 Total (i.e. Null); 3499 Residual ## Null
Deviance: 1724
## Residual Deviance: 891.8 AIC: 975.8
anova(my_logit1, test = "Chisq")
## Analysis of Deviance Table
##
## Model: binomial, link: logit
##
## Response: Default
##
## Terms added sequentially (first to last)
##

##
## Df Deviance Resid. Df
## NULL 3540
## Total.assets 1 7.204 3539
## Net.worth 1 79.964 3538
## Total.income 1 65.271 3537
## Change.in.stock 1 0.236 3536
## Total.expenses 1 59.323 3535
## Profit.after.tax 1 48.235 3534
## PBDITA 1 58.552 3533
## PBT 1 16.254 3532
## Cash.profit 1 114.393 3531
## PBDITA.as...of.total.income
1 25.026 3530
## PBT.as...of.total.income
1 9.155 3529
## PAT.as...of.total.income
1 0.277 3528
## Cash.profit.as...of.total.income
1 3.948 3527
## PAT.as...of.net.worth
1 145.441 3526
## Sales 1 17.395 3525
## Income.from.financial.services 1 12.591 3524
## Other.income 1 0.003 3523
## Total.capital 1 1.105 3522
## Reserves.and.funds 1 32.396 3521
## Borrowings 1 1.450 3520
## Current.liabilities...provisions 1 13.226 3519
## Deferred.tax.liability 1 1.814 3518
## Shareholders.funds 1 0.994 3517
## Cumulative.retained.profits 1 4.173 3516
## Capital.employed 1 3.265 3515
## TOL.TNW 1 64.950 3514
## Total.term.liabilities...tangible.net.worth
1 0.457 3513
## Contingent.liabilities...Net.worth.... 1 0.014 3512
## Contingent.liabilities 1 10.928 3511
## Net.fixed.assets 1 2.382 3510
## Current.assets 1 0.395 3509
## Net.working.capital 1 0.585 3508
## Debt.to.equity.ratio..times. 1 5.927 3507
## Debtors.turnover 1 15.735 3506
## Finished.goods.turnover 1 1.669 3505
## WIP.turnover 1 3.826 3504
## Raw.material.turnover 1 0.046 3503
## Shares.outstanding 1 0.283 3502
## EPS 1 0.083 3501
## Adjusted.EPS 1 0.358 3500
## Total.liabilities 0 0.000 3500

## PE.on.BSE ## 1 2.491 3499

Resid. Dev Pr(>Chi)
## NULL 1723.67
## Total.assets 1716.46 0.0072743 **
## Net.worth 1636.50 < 2.2e-16 ***
## Total.income 1571.23 6.528e-16 ***
## Change.in.stock 1570.99 0.6269971
## Total.expenses 1511.67 1.338e-14 ***
## Profit.after.tax 1463.43 3.781e-12 ***
## PBDITA 1404.88 1.980e-14 ***
## PBT 1388.63 5.539e-05 ***
## Cash.profit 1274.23 < 2.2e-16 ***
## PBDITA.as...of.total.income
1249.21 5.655e-07 ***
## PBT.as...of.total.income
1240.05 0.0024808 **
## PAT.as...of.total.income
1239.78 0.5984652
## Cash.profit.as...of.total.income
1235.83 0.0469348 *
## PAT.as...of.net.worth
1090.39 < 2.2e-16 ***
## Sales 1072.99 3.036e-05 ***
## Income.from.financial.services 1060.40 0.0003876 ***
## Other.income 1060.40 0.9578082
## Total.capital 1059.29 0.2932411
## Reserves.and.funds 1026.90 1.257e-08 ***
## Borrowings 1025.45 0.2285386
## Current.liabilities...provisions 1012.22 0.0002760 ***
## Deferred.tax.liability 1010.41 0.1780105
## Shareholders.funds 1009.41 0.3186585
## Cumulative.retained.profits 1005.24 0.0410643 *
## Capital.employed 1001.97 0.0707777 .
## TOL.TNW 937.02 7.683e-16 ***
## Total.term.liabilities...tangible.net.worth
936.57 0.4989419
## Contingent.liabilities...Net.worth.... 936.55 0.9063633
## Contingent.liabilities 925.62 0.0009474 ***
## Net.fixed.assets 923.24 0.1227011
## Current.assets 922.85 0.5294395
## Net.working.capital 922.26 0.4442690
## Debt.to.equity.ratio..times. 916.34 0.0149143 *
## Debtors.turnover 900.60 7.287e-05 ***
## Finished.goods.turnover 898.93 0.1963453
## WIP.turnover 895.11 0.0504698 .
## Raw.material.turnover 895.06 0.8305061
## Shares.outstanding 894.78 0.5946070
## EPS 894.69 0.7734053
## Adjusted.EPS 894.33 0.5493831
## Total.liabilities 894.33

## PE.on.BSE 891.84 0.1144780

## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(my_logit1)
##
## Call:
## glm(formula = Default ~ ., family = "binomial", data = train) ##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.5816 0.0012 0.1121 0.2834 3.2747
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error z
value
## (Intercept)2.598e+00 2.177e-01
11.933
## Total.assets -6.136e-03 1.716e-03
-3.576
## Net.worth 6.428e-04 2.059e-03
0.312
## Total.income -3.264e-02 7.369e-03
-4.429
## Change.in.stock -9.556e-03 5.654e-03
-1.690
## Total.expenses 2.398e-03 3.314e-03
0.724
## Profit.after.tax -5.557e-03 1.512e-02
-0.368
## PBDITA 3.323e-02 6.395e-03
5.196
## PBT 4.607e-03 1.437e-02
0.321
## Cash.profit 9.070e-03 5.116e-03
1.773
## PBDITA.as...of.total.income
-5.804e-03 6.201e-03
-0.936
## PBT.as...of.total.income
8.545e-03 1.714e-02
0.499
## PAT.as...of.total.income
-9.263e-03 1.829e-02
-0.507
## Cash.profit.as...of.total.income
7.531e-03 6.697e-03
1.124
## PAT.as...of.net.worth
2.187e-02 3.093e-03
7.069
## Sales 2.981e-02 6.500e-03
4.586

## Income.from.financial.services 4.569e-02 2.147e-02

2.128
## Other.income 2.607e-02 1.973e-02
1.321
## Total.capital 3.800e-03 1.819e-03
2.089
## Reserves.and.funds 6.725e-03 2.124e-03
3.166
## Borrowings 4.076e-03 5.581e-03
0.730
## Current.liabilities...provisions 6.221e-03 2.086e-03
2.982
## Deferred.tax.liability 4.757e-03 4.696e-03
1.013
## Shareholders.funds 4.020e-03 4.840e-03
0.831
## Cumulative.retained.profits 1.920e-03 2.208e-03
0.869
## Capital.employed 1.641e-03 6.255e-03
0.262
## TOL.TNW -4.839e-02 1.925e-02
-2.514
## Total.term.liabilities...tangible.net.worth
7.314e-02 4.205e-02
1.739
## Contingent.liabilities...Net.worth.... -1.511e-03 9.145e-04
-1.652
## Contingent.liabilities 3.080e-03 1.336e-03
2.305
## Net.fixed.assets -1.043e-03 7.209e-04
-1.447
## Current.assets -6.561e-04 1.527e-03
-0.430
## Net.working.capital 6.987e-04 1.838e-03
0.380
## Debt.to.equity.ratio..times. -7.458e-02 3.340e-02
-2.233
## Debtors.turnover -3.324e-03 2.931e-03
-1.134
## Finished.goods.turnover -1.735e-03 6.844e-04
-2.535
## WIP.turnover 6.230e-03 3.498e-03
1.781
## Raw.material.turnover -7.932e-04 6.676e-03
-0.119
## Shares.outstanding -6.817e-10 6.246e-10
-1.091
## EPS -2.328e-02 2.216e-02
-1.050

## Adjusted.EPS 1.073
## Total.liabilities NA
## PE.on.BSE
1.588
##
## (Intercept) ## Total.assets ## Net.worth
## Total.income
## Change.in.stock ## Total.expenses ## Profit.after.tax
## PBDITA
## PBT
## Cash.profit
## PBDITA.as...of.total.income
## PBT.as...of.total.income
## PAT.as...of.total.income
## Cash.profit.as...of.total.income
## PAT.as...of.net.worth
## Sales
## Income.from.financial.services
## Other.income ## Total.capital ## Reserves.and.funds
## Borrowings
## Current.liabilities...provisions
## Deferred.tax.liability
## Shareholders.funds
## Cumulative.retained.profits
## Capital.employed
## TOL.TNW
## Total.term.liabilities...tangible.net.worth ##
Contingent.liabilities...Net.worth....
## Contingent.liabilities
## Net.fixed.assets
## Current.assets
## Net.working.capital
## Debt.to.equity.ratio..times.
## Debtors.turnover
## Finished.goods.turnover
## WIP.turnover 2.396e-02
NA
1.021e-03
Pr(>|z|)
< 2e-16 ***
0.000348 ***
0.754895
9.48e-06 ***
0.090970 .
0.469292
0.713202
2.03e-07 ***
0.748487
0.076220 .
0.349315
0.618103
0.612450
0.260816
1.56e-12 ***
4.53e-06 ***
0.033310 *
0.186449
0.036706 *
0.001548 **
0.465168
0.002866 **
0.311092
0.406196
0.384686
0.793121
0.011952 *
0.081988 .
0.098474 .
0.021172 *
0.148006
0.667474
0.703895
0.025548 *
0.256839
0.011250 *
0.074904 . 2.233e-02
NA
6.428e-04

## Raw.material.turnover 0.905425
## Shares.outstanding 0.275059
## EPS 0.293590
## Adjusted.EPS 0.283333
## Total.liabilities NA
## PE.on.BSE 0.112368
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## (Dispersion parameter for binomial family taken to be 1)
## Null deviance: 1723.67 on 3540 degrees of freedom
## Residual deviance: 891.84 on 3499 degrees of freedom
## AIC: 975.84
## Number of Fisher Scoring iterations: 15
toselect.x <- summary(my_logit1)$coeff[-1,4] < 0.05
#EDIT: as subsequent posters have pointed out, the latter line should be
#to include all variables.
##
## Call: glm(formula = sig.formula, data = train)
##
## Coefficients:
## (Intercept) Total.assets
## 9.496e-01 7.235e-07
## Total.income PBDITA
## -2.750e-05 -4.759e-05
## PAT.as...of.net.worth
Sales

## 2.944e-03 3.332e-05
## Income.from.financial.services Total.capital
## 2.626e-05 -2.628e-06
## Reserves.and.funds Current.liabilities...provisions
## 1.084e-05 -9.504e-06
## TOL.TNW Contingent.liabilities
## -6.309e-03 1.606e-06
## Debt.to.equity.ratio..times. Finished.goods.turnover
## -8.543e-03 -4.220e-05
##
## Degrees of Freedom: 3540 Total (i.e. Null); 3527 Residual
## Null Deviance: 218.5
## Residual Deviance: 147.2 AIC: -1183
anova(my_logit2, test = "Chisq")
## Analysis of Deviance Table
##
## Model: gaussian, link: identity
##
## Response: Default
##
## Terms added sequentially (first to last)
##
##
## Df Deviance Resid. Df Resid. Dev
## NULL 3540 218.54
## Total.assets 1 0.303 3539 218.23
## Total.income 1 1.241 3538 216.99
## PBDITA 1 0.640 3537 216.35
## PAT.as...of.net.worth
1 45.225 3536 171.13
## Sales 1 0.255 3535 170.87
## Income.from.financial.services 1 0.138 3534 170.74
## Total.capital 1 0.004 3533 170.73
## Reserves.and.funds 1 1.142 3532 169.59
## Current.liabilities...provisions 1 0.129 3531 169.46
## TOL.TNW 1 20.403 3530 149.06
## Contingent.liabilities 1 0.005 3529 149.05
## Debt.to.equity.ratio..times. 1 1.237 3528 147.81
## Finished.goods.turnover 1 0.645 3527 147.17
## Pr(>Chi)
## NULL
## Total.assets 0.007064 **
## Total.income 4.939e-08 ***
## PBDITA 8.968e-05 ***
## PAT.as...of.net.worth
< 2.2e-16 ***

## Sales 0.013464 *
## Income.from.financial.services 0.069416 .
## Total.capital 0.749960
## Reserves.and.funds 1.689e-07 ***
## Current.liabilities...provisions 0.078935 . ## TOL.TNW < 2.2e-16 ***
## Contingent.liabilities 0.724730
## Debt.to.equity.ratio..times. 5.176e-08 ***
## Finished.goods.turnover 8.424e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(my_logit2)
##
## Call:
## glm(formula = sig.formula, data = train)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.04856 -0.00428 0.03888 0.06529 1.13657
##
## Coefficients: ## Estimate Std.Error t value Pr(>|t|)
## (Intercept)9.496e-01 4.614e-03 205.814 < 2e-16
## Total.assets 7.235e-07 2.255e-06 0.321 0.7483
## Total.income -2.750e-05 2.179e-05 -1.262 0.2071
## PBDITA -4.759e-05 1.469e-05 -3.240 0.0012
## PAT.as...of.net.worth
2.944e-03 1.272e-04 23.145 < 2e-16
## Sales 3.332e-05 2.122e-05 1.570 0.1165
## Income.from.financial.services 2.626e-05 6.339e-05 0.414 0.6787
## Total.capital -2.628e-06 1.304e-05 -0.202 0.8403
## Reserves.and.funds 1.084e-05 5.358e-06 2.022 0.0432
## Current.liabilities...provisions -9.505e-06 6.712e-06 -1.416 0.1568
## TOL.TNW -6.309e-03 1.037e-03 -6.083 1.30e-09
## Contingent.liabilities 1.605e-06 5.438e-06 0.295 0.7678
## Debt.to.equity.ratio..times. -8.543e-03 1.602e-03 -5.335 1.02e-07
## Finished.goods.turnover -4.220e-05 1.073e-05 -3.932 8.59e-05
##
## (Intercept)***
## Total.assets
## Total.income
## PBDITA **
## PAT.as...of.net.worth
***
## Sales
## Income.from.financial.services

## Total.capital
## Reserves.and.funds *
## Current.liabilities...provisions
## TOL.TNW ***
## Contingent.liabilities
## Debt.to.equity.ratio..times. ***
## Finished.goods.turnover ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 0.04172674)
##
## Null deviance: 218.54 on 3540 degrees of freedom
## Residual deviance: 147.17 on 3527 degrees of freedom
## AIC: -1183.5
##
## Number of Fisher Scoring iterations: 2 my_logit2_Val <-
glm(formula=sig.formula,data=val)
my_logit2_Val
##
## Call:
## glm(formula = sig.formula, data = val)
## Coefficients:
## (Intercept) Total.assets
## 9.664e-02 1.066e-06
## Total.income PBDITA
## 7.901e-06 8.637e-06
## PAT.as...of.net.worth
Sales
## -3.443e-03 -8.545e-06
## Income.from.financial.services Total.capital
## -1.020e-05 -1.370e-05
## Reserves.and.funds Current.liabilities...provisions
## -4.999e-06 2.686e-06
## TOL.TNW Contingent.liabilities
## 2.761e-03 -2.444e-06
## Debt.to.equity.ratio..times. Finished.goods.turnover
## -3.197e-03 -2.476e-05
##
## Degrees of Freedom: 396 Total (i.e. Null); 383 Residual ## (318
observations deleted due to missingness)
## Null Deviance: 15.36
## Residual Deviance: 10.85 AIC: -272.6
anova(my_logit2_Val, test = "Chisq")

## Analysis of Deviance Table

##
## Model: gaussian, link: identity
##
## Response: Default
##
## Terms added sequentially (first to last)
##
##
##
Pr(>Chi) Df Deviance Resid. Df Resid. Dev
## NULL 396 15.355
## Total.assets 1 0.0139 395 15.341
0.48353
## Total.income 1 0.0001 394 15.341
0.94292
## PBDITA 1 0.0073 393 15.334
0.61162
## PAT.as...of.net.worth
1 4.3077 392 11.026
2e-16
## Sales 1 0.0003 391 11.026
0.92056
## Income.from.financial.services 1 0.0041 390 11.022
0.70456
## Total.capital 1 0.0037 389 11.018
0.71598
## Reserves.and.funds 1 0.0152 388 11.003
0.46423
## Current.liabilities...provisions 1 0.0079 387 10.995
0.59735
## TOL.TNW 1 0.0223 386 10.973
0.37498
## Contingent.liabilities 1 0.0109 385 10.962
0.53547
## Debt.to.equity.ratio..times. 1 0.0958 384 10.866
0.06586
## Finished.goods.turnover 1 0.0208 383 10.845
0.39178
##
## NULL
## Total.assets ## Total.income ## PBDITA
## PAT.as...of.net.worth ***
## Sales

## Income.from.financial.services ## Total.capital
## Reserves.and.funds
## Current.liabilities...provisions
## TOL.TNW
## Contingent.liabilities
## Debt.to.equity.ratio..times. .
## Finished.goods.turnover
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(my_logit2_Val)
##
## Call:
## glm(formula = sig.formula, data = val)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.49273 -0.06993 -0.03881 0.00430 0.91737
##
## Coefficients: ## Estimate Std.Error t value Pr(>|t|)
## (Intercept)9.664e-02 1.027e-02 9.413 <2e-16
## Total.assets 1.066e-06 2.493e-06 0.427 0.6693
## Total.income 7.901e-06 2.883e-05 0.274 0.7842
## PBDITA 8.637e-06 7.841e-06 1.102 0.2714
## PAT.as...of.net.worth
-3.443e-03 2.820e-04 -12.210 <2e-16
## Sales -8.545e-06 3.026e-05 -0.282 0.7778
## Income.from.financial.services -1.020e-05 4.226e-05 -0.241 0.8093
## Total.capital -1.370e-05 1.290e-05 -1.062 0.2891
## Reserves.and.funds -4.999e-06 6.011e-06 -0.832 0.4061
## Current.liabilities...provisions 2.686e-06 6.102e-06 0.440 0.6600
## TOL.TNW 2.761e-03 1.412e-03 1.955 0.0513
## Contingent.liabilities -2.444e-06 3.802e-06 -0.643 0.5208
## Debt.to.equity.ratio..times. -3.197e-03 1.779e-03 -1.797 0.0731
## Finished.goods.turnover -2.476e-05 2.891e-05 -0.856 0.3923
##
## (Intercept)***
## Total.assets
## Total.income
## PBDITA
## PAT.as...of.net.worth
***
## Sales
## Income.from.financial.services
## Total.capital

## Reserves.and.funds
## Current.liabilities...provisions
## TOL.TNW .
## Contingent.liabilities
## Debt.to.equity.ratio..times. .
## Finished.goods.turnover
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 ##
## (Dispersion parameter for gaussian family taken to be 0.0283165) ##
## Null deviance: 15.355 on 396 degrees of freedom
## Residual deviance: 10.845 on 383 degrees of freedom
## (318 observations deleted due to missingness)
## AIC: -572.65
##
## Number of Fisher Scoring iterations: 2
The AIC Score on both Train and Test Dataset had a good match.