Bank Marketing

Bank Marketing

Predicting client's subscription depending on background

Instances: 4521

Attributes: 17

Tasks: Classification

Downloads: 2574

Year Published: 2012

Missing Values: No

Attribute Details:
Name Type Description
age integer Age of client: numerical value
job string Type of job: admin., blue-collar, entrepreneur, housemaid, management, retired, self-employed, services, student, technician, unemployed, unknown
marital string Marital status: divorced, married, single, unknown
education string Level of education: primary, secondary, tertiary, unknown
default string Has credit in default: no, yes, unknown
balance integer Average yearly balance in Euro: numerical value
housing string Has housing loan: no, yes, unknown
loan string Has personal loan: no, yes, unknown
contact string Communication type: unknown, telephone, cellular
day integer Day of the month: numerical value between 1 and 31
month string Month of the year: jan, feb, mar, apr, may, jun, jul, aug, sep, oct, nov, dec
duration float Last contact duration: numerical value in seconds
campaign integer Number of contacts made: numerical value
pdays float Number of days passed since client was last contacted from a previous campaign: numerical value, -1 indicates client was not previously contacted
y string Predictor class: yes, no

Showing 15 out of 17 attributes. Download attribute CSV for full details


Choose Library

Replace Missing Values?

Include Header Row?



age job marital education default balance housing loan contact day month duration campaign pdays y
30 unemployed married primary no 1787 no no cellular 19 oct 79.0 1 -1.0 no
33 services married secondary no 4789 yes yes cellular 11 may 220.0 1 339.0 no
35 management single tertiary no 1350 yes no cellular 16 apr 185.0 1 330.0 no
30 management married tertiary no 1476 yes yes unknown 3 jun 199.0 4 -1.0 no

Showing 15 out of 17 attributes. Download attribute CSV for full details



The data is related with direct marketing campaigns (phone calls) of a Portuguese banking institution. The classification goal is to predict if the client will subscribe a term deposit (variable y).

X Decoder Tables

Column Name One Hot Val Decoded Val
job 1,0,0,0,0,0,0,0,0,0,0,0 admin.
job 0,0,0,0,0,1,0,0,0,0,0,0 retired
job 0,0,0,0,0,0,0,0,1,0,0,0 student
job 0,0,0,0,0,0,0,0,0,0,0,1 unknown
job 0,0,0,0,0,0,0,1,0,0,0,0 services
job 0,0,0,1,0,0,0,0,0,0,0,0 housemaid
job 0,0,0,0,1,0,0,0,0,0,0,0 management
job 0,0,0,0,0,0,0,0,0,1,0,0 technician
job 0,0,0,0,0,0,0,0,0,0,1,0 unemployed
job 0,1,0,0,0,0,0,0,0,0,0,0 blue-collar
job 0,0,1,0,0,0,0,0,0,0,0,0 entrepreneur
job 0,0,0,0,0,0,1,0,0,0,0,0 self-employed
marital 0,0,1 single
marital 0,1,0 married
marital 1,0,0 divorced
education 1,0,0,0 primary
education 0,0,0,1 unknown
education 0,0,1,0 tertiary
education 0,1,0,0 secondary
default 1,0 no
default 0,1 yes
housing 1,0 no
housing 0,1 yes
loan 1,0 no
loan 0,1 yes
contact 0,0,1 unknown
contact 1,0,0 cellular
contact 0,1,0 telephone
month 1,0,0,0,0,0,0,0,0,0,0,0 apr
month 0,1,0,0,0,0,0,0,0,0,0,0 aug
month 0,0,1,0,0,0,0,0,0,0,0,0 dec
month 0,0,0,1,0,0,0,0,0,0,0,0 feb
month 0,0,0,0,1,0,0,0,0,0,0,0 jan
month 0,0,0,0,0,1,0,0,0,0,0,0 jul
month 0,0,0,0,0,0,1,0,0,0,0,0 jun
month 0,0,0,0,0,0,0,1,0,0,0,0 mar
month 0,0,0,0,0,0,0,0,1,0,0,0 may
month 0,0,0,0,0,0,0,0,0,1,0,0 nov
month 0,0,0,0,0,0,0,0,0,0,1,0 oct
month 0,0,0,0,0,0,0,0,0,0,0,1 sep
poutcome 0,1,0,0 other
poutcome 1,0,0,0 failure
poutcome 0,0,1,0 success
poutcome 0,0,0,1 unknown
Column Name Label Val Decoded Val
job 0 admin.
job 1 blue-collar
job 2 entrepreneur
job 3 housemaid
job 4 management
job 5 retired
job 6 self-employed
job 7 services
job 8 student
job 9 technician
job 10 unemployed
job 11 unknown
marital 0 divorced
marital 1 married
marital 2 single
education 0 primary
education 1 secondary
education 2 tertiary
education 3 unknown
default 0 no
default 1 yes
housing 0 no
housing 1 yes
loan 0 no
loan 1 yes
contact 0 cellular
contact 1 telephone
contact 2 unknown
month 0 apr
month 1 aug
month 2 dec
month 3 feb
month 4 jan
month 5 jul
month 6 jun
month 7 mar
month 8 may
month 9 nov
month 10 oct
month 11 sep
poutcome 0 failure
poutcome 1 other
poutcome 2 success
poutcome 3 unknown

Y Decoder Tables

One Hot Val Decoded Val
1,0 no
0,1 yes

Label Val Decoded Val
0 no
1 yes


Moro et al., 2011] S. Moro, R. Laureano and P. Cortez. Using Data Mining for Bank Direct Marketing: An Application of the CRISP-DM Methodology.
In P. Novais et al. (Eds.), Proceedings of the European Simulation and Modelling Conference - ESM'2011, pp. 117-121, Guimarães, Portugal, October, 2011. EUROSIS.