01 | Problem
An auto insurance provider for approximately 40% of the United States wanted to expand their market reach by incorporating internet aggregators into their lead purchasing strategy. However, the auto insurance provider’s target market is very niche and unique, making it difficult to correlate the aggregator leads with conversion of a policy. Due to the use of multiple aggregators, the quality of the lead lists was difficult to determine.
02 | Solution
The auto insurance provider hired Dialog Direct to develop a custom lead purchasing strategy that would incorporate predictive analytics to target a specific niche market through internet aggregators. Dialog Direct was selected because of their experience in selling insurance policies through the use of their custom technologies and sales-oriented culture.
To begin the process, Dialog Direct developed a predictive scoring criterion for leads based on an analysis of historical performance and third-party data matching of more than 240 consumer attributes. This process developed a picture of the “ideal” buyer to use for future purchasing decisions.
Dialog Direct used a “ping/post” model to purchase leads. Demographic attributes were grouped into clusters by matching ZIP codes to third-party information, such as average income levels, age and gender. Each cluster was assigned a value based on historical data to determine the profitability of the lead and the maximum bid or offer to submit.
The predictive platform automatically rejected lead lists that did not meet the purchasing criteria and bought those predicted to be profitable. Dialog Direct’s platform also has the intelligence to reject leads with fake names, phone numbers or ZIP codes. For example, a lead with the same name as a cartoon character would be rejected regardless of the other matching attributes.
After leads are purchased, they were prioritized by probability to purchase a policy. The leads matching the most attributes of a converted lead based off historical data were highest priority to call first. Each lead was routed to the best agent to handle the call by matching the pattern of attributes of the lead with the sales team that performs the best with that attribute cluster. Dialog Direct’s call center agents then nurtured leads to build interest until the sale was closed.
The predictive platform analyzed lead conversion and dispositions to report what demographics were purchasing policies. That information went back into the predictive model to further enhance the intelligence of the model. Through the process, Dialog Direct identified specific locations outperforming the majority and instantaneously adjusted the purchasing strategy to buy more leads from the locations with high sales rates.
03 | Results
Dialog Direct increased sales and generated additional revenue by utilizing predictive analytics to determine which leads were most likely to convert. In addition, the average premium value increased by more than 70% when the predictive platform operated at optimal performance. During the first six months using predictive analytics, the auto insurance provider increased monthly sales by nearly 20%, which resulted in an increase of more than 55% in additional monthly premiums.