Improving Cold Calling Success Rate for the Property and Car Insurance Company

Our partner is a midsize insurance business specializing in property and car insurance. This is also the company that Intelliarts has a long history of collaboration with. As cold calls comprise a considerable part of the customer’s sales strategy, the company reached out to us to solve their problem of the low cold calling success rate, which could have been related to their phone numbers being marked as spam. We’ve taken a data science approach in this project, which we saw as the most appropriate to address the customer’s challenge.

Solution

We performed a series of data researches that showed that the underperformance of customer cold calls had nothing to do with their phone numbers being marked as spam. During the project:

• We performed the general phone call analysis, which aimed at checking how the amount of successful cold calls grew over time and whether there was any correlation between effective cold calls and all calls generally at the moment when the numbers were flagged as spam. We didn’t establish any strong correlation between the numbers being flagged as spam and the low cold calling success rate.
• We noticed similar observations during the number migration analysis. While tracking the success rate of cold calls over time, it was expected the performance would drop after the number was flagged as spam. This did happen, but occasionally the performance grew again after a few more calls were made from the same number, which meant there was no tight correlation between the two events.
• We conducted the underperformance vs. spam analysis to contrast the low success rate of a particular number to spam detection. We discovered that while marking phone numbers as spam did provide extra management efforts related to phone number management, it didn't have any direct influence on the overall success rate of cold calls.

Although we didn’t find any evidence suggesting that the underperformance of cold calls was related to the company’s phone numbers being flagged as spam, we confirmed multiple other factors affecting the effectiveness of cold calls, such as the insurance agent who was calling and the way how the calls were managed. The timing of the original and follow-up calls, as well as the demographic state of the lead, also mattered.

Results

The Intelliarts team shared all these business insights with the customer and suggested building a machine learning system that could detect the underperformance of phone numbers, track the factors causing the low success rates of cold calls, and avoid such patterns in the future. We built the MVP for this solution, and now the customer is busy testing the MVP. As soon as we collect feedback from the insurance agents who are testing the solution in the fields, we'll proceed with developing the full-scale ML solution for phone numbers management.