Default payment Management through Analytics in the new Post-Covid reality

Default Payment Analytics

Covid new reality

According to the latest estimates, more than 190 million jobs will be lost due to the Coronavirus, and for the first time after the 2008 crisis, the planet will enter a new recession. The drastic fall in family income will bring with it an irremediable crisis of default and liquidity that will fully impact on the cash flow forecasts of companies.

Enabling companies with analytical capabilities to anticipate possible cases of default, modelling the best actions to be taken by the team, can lead to a dramatic change in the success rates of recovery.

Experts point out that in Spain, each percentage point increase in unemployment increases bank default by 0.75%, understood as the resulting quotient between doubtful risks (unpaid loans) and total risks (total loans granted). After the 2008 crisis, banks have focused much of their efforts on reducing this ratio to below 5%. Currently the value is 4.83% (homogeneous values to those obtained in 1987). In the fourth quarter, the ratio is expected to reach between 8% and 10%, which will mean that the unemployment rate will rise from at least 13% at the end of 2019 to close to 20%.

Default Payment Analytics

This new crisis will destroy not only the jobs most historically affected in recessions, such as temporary jobs, or those associated with construction, but it will also cause people who under normal circumstances would never lose their jobs to end up falling into unemployment. This fact, together with the lack of liquidity of the families, will generate both a rise in default, and an increase in the drop of products and services that are not strictly necessary: the identification of customers with specific financial needs will become more important than ever, for this, providing financial departments with analytical tools can increase the opportunity of recovery by up to 70%.

Transformation to guarantee BAU

In this situation, companies are faced with different fundamental needs:

  1. To guarantee the continuity of the business, stabilizing the processes of current recoveries overloaded or not prepared for new needs. Having an external workforce available on a temporary basis, agile and flexible, to stabilize the business is critical. 
  2. Identify customers who are in default due to the crisis, but who can be expected to recover their ability to pay when the business returns to normal.
  3. Enable predictive models to anticipate default and prescriptive models to customize the most effective recovery actions for each customer, making the success rate of current processes more efficient. 
  4. Combine the previous points in processes developed on the basis of good practices to homogenize and make recovery actions more efficient.
Analytics Transformation Customer Shielding

Default payment analytics

To meet the needs 2 and 3, in everis, from our CoE of collection management, leveraged on technology, we have designed 14 analytical models throughout the life of the client in the company with the aim of

Customer Journey
Finance Analytics Approach

In addition, the end-to-end vision of the customer enables the reuse of statistical information and the search for synergies between cases of use (e.g., actions aimed at charging for the service before non-payment in advance).

The 14 use cases developed have been grouped into the four phases of the customer’s business cycle with different objectives:

Use cases are tested, validated and quantified by everis before they are incorporated into the client’s BAU in a short period of time of ~ 10 weeks. Where our clients are obtaining improvements in their recovery management ratios such as:

Funnel Finance

Funnel example of recovery actions generated by the algorithms.

In a demand shock like the one we are facing and with the huge default wave that is coming, successful companies will be the ones that get it:

Recommended Posts