Daily, weekly and monthly data showing seasonally adjusted and non-seasonally adjusted UK spending using debit and credit cards. These are official statistics in development. Source: CHAPS, Bank of England.

About the Competition

• American Express and HackerEarth present “AmExpert 2021 CODELAB – Machine Learning Hackathon”, an amazing opportunity to showcase your analytical abilities and talent!
• Get a chance to be interviewed with American Express for analytical and machine learning roles and other exciting prizes!

Tasks

Credit card default risk is the chance that companies or Individuals will not be able to return the money lent on time.

You are given relevant information about the customers of a company.

You are required to build a machine learning model that can predict if there will be credit card default.

Dataset description

The dataset folder contains the following files:

• train.csv: 45528 x 19
• test.csv: 11383 x 18
• sample_submission.csv: 5 x 2

The columns provided in the dataset are as follows:

Content

Column name	Description
customer_id	Represents the unique identification of a customer
name	Represents the name of a customer
age	Represents the age of a customer ( in years )
gender	Represents the gender of a customer( F means Female and M means Male )
owns_car	Represents whether a customer owns a car ( Y means Yes and N means No )
owns_house	Represents whether a customer owns a house ( Y means Yes and N means No )
no_of_children	Represents the number of children of a customer
net_yearly_income	Represents the net yearly income of a customer ( in USD )
no_of_days_employed	Represents the no of days employed
occupation_type	Represents the occupation type of a customer ( IT staff, Managers, Accountants, Cooking staff, etc )
total_family_members	Represents the number of family members of a customer
migrant_worker	Represents whether a customer is a migrant worker( 1 means Yes and 0 means No )
yearly_debt_payments	Represents the yearly debt payments of a customer ( in USD )
credit_limit	Represents the credit limit of a customer ( in USD )
credit_limit_used(%)	Represents the percentage of credit limit used by a customer
credit_score	Represents the credit score of a customer
prev_defaults	Represents the number of previous defaults
default_in_last_6months	Represents whether a customer has defaulted in the last 6 months ( 1 means Yes and 0 means No )
credit_card_default	Represents whether there will be credit card default ( 1 means Yes and 0 means No )

Evaluation metric

score = 100*(metrics.f1_score(actual, predicted, average= "macro" ))

Result submission guidelines

• The index is "customer_id" and the target is the "credit_card_default" column.
• The submission file must be submitted in .csv format only.
• The size of this submission file must be 11383 x 2.

Note: Ensure that your submission file contains the following:

• Correct index values as per the test file
• Correct names of columns as provided in the sample_submission.csv file

Rules:

• Entries submitted after the contest is closed, will not be considered.
• You are expected to solve the problem on your own.
• Multiple IDs of user leads to disqualification from the contest.
• Use of external data is not allowed.
• Participant must update their profile details and upload their latest CV.
• Decision on the winners and runners-up made by American Express will be final and binding.
• Throughout the hackathon, you are expected to respect fellow hackers and act with high integrity.
• HackerEarth and American Express hold the right to disqualify any participant at any stage of the competition if the participant(s) are deemed to be acting fraudulently.
• Existing American Express employees are not allowed to participate in the competition.
• It is an individual participation Hackathon and not a team event.
• Prizes will be shipped to India ...