Pilot project for transcribing calls to the Estonian Unemployment Insurance Fund

Feelingstream has created an AI application for the analysis of customer communication in several different languages, including Estonian and Russian. The Unemployment Insurance Fund and Feelingstream worked together to create a pilot to find the root causes of customer inquiries and thereby reduce the number of calls.


The application developed by Feelingstream provides an opportunity to get both a statistical overview and a detailed understanding of customers' concerns across several customer communication channels - calls, emails and chat bots. Analysis of customer communications’ is the fastest and most immediate way to find out which parts of the services the customer is having troubles with and in turn that can be changed quickly. The analysis creates insights for managerial decision-making, which in turn leads to better and more efficient public services.


As part of the pilot, the Feelingstream application for the Unemployment Insurance Fund transcribed calls from April to August 2019 (5 months). In addition, Unemployment Insurance Fund employees participated in workshops organized by Feelingstream. Initially, the focus was on all calls, but during analysis it was decided to focus on calls that concerned a certain subsidy. The entire process from the client's side was looked at in order to find out to what causes the client to be confused and call customer support.


The main reason for calling with the chosen type of subsidy was related to the receipt of grants. It is understandable to humans why issues related to the receipt of subsidy money arise and the volume of calls is therefore significantly higher at the beginning of the month. Following the pilot project, work was carried out to improve e-environments and there were other findings to improve the customer experience that were taken into account.