Any company that deals with debt recovery needs to know in-depth the positions that make up the list of debtors and the recoverable values associated with it, in order to be able to set up strategies that allow it to achieve the pre-set objectives in the shortest possible time. and with the best possible result.
The debts differ from each other due to various parameters, such as the original value of the debt, or the amount recoverable from each of them. In a list of debt positions, we will find some that have very high amounts to be recovered and others whose debt are more modest amounts.
In a Phone Collection campaign, debtors are contacted randomly without taking into account the recoverable value associated with each of them. For example, in a segment of 10 debtors with a similar probability of recovery we could have six debts of € 3,000, with an expected recoverable amount of € 800 each, and four debts of € 2,000, with an expected recoverable value of € 1,800. The best way to manage these credits is to evaluate the expected value together with the probability of recovery, in order to prioritise the debt not only by the highest probability of recovery, but also by the greatest recoverable value.
Knowing in advance the recoverable value from each position therefore becomes fundamental in order to set up a recovery strategy that will reduce time, costs and maximize the total value recovered.
How is it possible to predict the recoverable values for each debt?
Thanks to Artificial Intelligence it is possible to develop value models that are able to predict the expected recoverable value of each position. In this way, debt recovery companies are able to predict the recoverable amount of each debtor, the total expected value of each debt portfolio and the time required to recover each debt; greatly expanding the range of possible data-driven strategies in order to choose the one that best suits the achievement of the company’s business objectives.