Insurance companies play an important role in providing financial support to the insured in the event of unforeseen events like critical illness, hospitalization, accidents or death. 
Insurers face the challenge of determining the amount of premium to be paid by the insured. 
To accurately estimate this, extensive background checks are required to be done by the insurer. The most important is to determine the “***level of criticality***” or the probability of a critical illness occurring in a prospective insurance customer. 
Adding to the challenge is that background checks are done by humans and human error/ bias cannot be ruled out. If background checks are not done at all or not reported correctly, this can result in an extraordinary liability for the insurer. 
In the event of an unfortunate eventuality of the insured, the insurance company is liable to pay a hefty amount in excess of the premium collected.
In view of this it is important that the probable criticalities be predicted by a machine learning model accurately. This will enable the turnaround time of insurance approval and disbursal of claims to get crashed leading to higher efficiency in operations.
Before issuing the insurance policy bond, insurers record multiple data points related to family background, medical history, economic strata and other related data. These are processed manually to estimate the criticality score of the insured. 
For this competition the data is in an excel file. The objective is to predict the criticality level or score of the potential prospect for insurance (the last variable in the training set). The variables are anonymized for security reasons.