SignOn CRM transforms customer rating through remodelling CRM workflow, applying Machine learning to address problems before they manifest.

#SignOnCRM #Insurance #MachineLearning

About Client

This Insurance company engages in the provision of a range of property insurance, life insurance, retirement products, and other financial services to commercial and individual customers. It operates through the following segments: General Insurance, Life and Retirement, Other Operations, and Legacy Portfolio.

Problem statement

On account of the multitude of products the complexity of queries and grievances of customers was compounded with the severity & constant enhancements to the processes .

1. The customer service transaction volume in the customer service department , the agent’s knowledge had a direct correlation to the NPS ( Net promoter score) .


2. The call & email volumes were unpredictable & dependent on the seasonality , issues faced.


3. Customers were not quick to adopt self serve & hence would reach the 1800 number for solution.


4. Customer complaints were not prioritised on account of the increasing complexity

Solutions

The need was to create an automated, self serve & deflect customer service volumes to self serve . Also model an enhanced workflow which would predict if any customers were in distress where they could have helped prevent the issue.

• Proactively address customer complaints using a machine learning model which would determine the incoming issues & usage of self serve.


• For each customer , the system would trigger a probably score rating the issue , prioritising the queue .


• The scoring mechanism would also determine if the customer would complain on social media


• Implemented an Integrated Net Promoter Score (NPS) can measure customer engagement.


• Right Escalation management: Automate routing of issues to specific queues in order to filter issues that require escalation management into a unique queue where executives with that particular specialisation can work upon it.


• Prioritising cases using ML considering case history, complaint opportunity, severity & resolution path

Configuration and Deployment timeline - 2 Months Study, 3 Months Deployment, 1 Months Transition Time to Go Live- 5 Months from Contract

Results

• 42% increase in positive feedback by customers