Solving case allocation problems using Data science

Business Context

A major Healthcare SaaS product provider in US had several issues in servicing inbound cases from their clients, thereby leading to multiple business impacts

  • Compliance issues due to non-adherence to SLA
  • Lack of process to identify Competency level and productivity of associates, thereby leading to incorrect allocation of cases
  • Number of cases in queue continuously increasing leading to inefficiencies in backlog closures.

Kyyba Solution

Our data science experts solved this problem addressing 2 key root causes

  • We came up with a time series model to predict the incoming cases for the next 90 days
  • Enabled identification of the right ‘case-to-skill’ mapping; thereby ensuring right allocation and closure of cases.

 

Business outcomes

Average case completion duration was reduced to 13 from 23 hours.

Duration of cases waiting in the queue reduced to 3 hours from 13 hours.

100% cases resolved within SLA’S .