OK then, let us move to the practical part: applying the lm() function to our data. Let us choose an explanatory variable and see what happens. Just recall the variables we have:

colnames(clean_casted_stored_data_validated_complete)

 [1] "corporation"
 [2] "subsidiary"
 [3] "previous_default"
 [4] "customer_agreement"
 [5] "multiple_country"
 [6] "default_numeric"
 [7] "default_flag"
 [8] "customer_code"
 [9] "cost_income"
 [10] "ROE"
 [11] "employees"
 [12] "economic_sector"
 [13] "company_revenues"
 [14] "ROS"
 [15] "commercial_portfolio"
 [16] "business_unit"

What would you go for?