Skip to main content

Insights

Beta Feature

Building credit risk models is a complex and demanding task. In addition, it requires a significant volume of data.

Palenca insights offer a list of pre-calculated variables that will help risk and data science teams make decisions with a higher degree of certainty.

Employment Insights

You can access this information by making a GET request to /accounts/:account_id/insights.

DataDescriptionTypeExample
work_durationMedian seniority of the last 3 jobs (in months).float2.45
salary_progressionMedian percentage of salary increase for the last 3 jobs (value between 0 and 100).float10.0
periods_moonlightingList with the periods in which the employee had 2 or more employers at the same time and the months that each of these periods lasted.objects[{'start_date': '2022-08-01', 'end_date': '2022-08-19', 'employers': ['COMPANY A', 'COMPANY B']}]
periods_unemployedList with the periods in which the worker was unemployed for more than 1 monthobjects[{'start_date': '2021-05-11', 'end_date': '2022-11-16', 'month_duration': 17.1}, {'start_date': '2022-11-16', 'end_date': '2023-04-26', 'month_duration': 4.2}]

GigInsights

You can access this information by making a GET request to /accounts/:account_id/insights-gig. The response from this route returns a dictionary with the attributes worker_information, payment_capacity, other_gig_accounts, work_history.

Below we show tables for the most relevant attributes.

payment_capacity

DataDescriptionTypeExample
median_weekly_incomeMedian weekly income of the workerfloat4699.55
average_days_worked_per_weekAverage number of days worked per weekfloat1.0
income_percentilePercentile in which the employee's income is found with respect to other workers. Value between 0 and 100, the higher the better.float72.63
income_volatilityConsistency of worker income (below_average, average, above_average)stringabove_average

other_gig_accounts

If applicable, the route will return a list with the accounts of other platforms that the worker has connected.