Jul 15, 2022
No image
Completed
Improving Cold Calling Success Rate for the Property and Car Insurance Company
$10,000+
4-6 months
United States
2-5
Service categories
Service Lines
Artificial Intelligence
Big Data
Cloud Consulting
IT Services
Domain focus
Banking & Financial Services
Challenge
Within our long-term collaboration with the insurtech company, our partner contacted us to help them research and solve the problem of the low cold calling success rate. We proposed a data science approach to test the hypothesis of underperforming cold calls caused by the customer’s phone numbers being flagged as spam.
Within our long-term collaboration with the insurtech company, our partner contacted us to help them research and solve the problem of the low cold calling success rate. We proposed a data science approach to test the hypothesis of underperforming cold calls caused by the customer’s phone numbers being flagged as spam.
Solution
Intelliarts completed the general phone call analysis to see how the amount of successful cold calls grew over time and whether there was any correlation between effective vs all calls generally at the moment the numbers were flagged as spam. Also, we did a number migration analysis to track the performance of cold calls over time. The conclusions were similar — no strong correlation between the number being flagged as spam and the low cold calling success rate. The underperformance vs. spam analysis didn’t show any correlation either. Further research revealed other factors affecting the cold call performance, such as the agent who was calling, the demographics of the lead, the timing of the original and follow-up calls, and the strategy of how the cold calls were managed
Intelliarts completed the general phone call analysis to see how the amount of successful cold calls grew over time and whether there was any correlation between effective vs all calls generally at the moment the numbers were flagged as spam. Also, we did a number migration analysis to track the performance of cold calls over time. The conclusions were similar — no strong correlation between the number being flagged as spam and the low cold calling success rate. The underperformance vs. spam analysis didn’t show any correlation either. Further research revealed other factors affecting the cold call performance, such as the agent who was calling, the demographics of the lead, the timing of the original and follow-up calls, and the strategy of how the cold calls were managed
Results
We delivered these business insights to the customer and built the MVP that could detect the underperformance of phone numbers, help the insurer understand the underlying factors, and avoid such patterns in the future. After the MVP is tested and feedback is collected from agents, we'll proceed with developing the full-scale ML solution for number management.
We delivered these business insights to the customer and built the MVP that could detect the underperformance of phone numbers, help the insurer understand the underlying factors, and avoid such patterns in the future. After the MVP is tested and feedback is collected from agents, we'll proceed with developing the full-scale ML solution for number management.