Sector: Marketing Services

Opportunity:To develop a model to predict the likelihood that a lead will convert to a sale. With this data, sales teams could then employ a more targeted and hence cost-effective approach to following-up on leads.The cost of using sales staff on phone or email to convert a lead is typically 10x more than the cost of self-service conversion mechanisms (transactions completed without the need to interact with sales staff). In addition, the cost of face-to-face sales interaction is typically 100x more than the cost of self-service conversion mechanisms. The online lead-generation company saw the opportunity to develop a model to predict the likelihood that a lead will convert to a sale. With this data, sales teams could then employ a more targeted and hence cost-effective approach to following-up on leads.

Approach:Our Data Scientist built predictive models to evaluate the probability that an online-generated lead will convert. The predictive model uses demographic data of the lead (age, gender, etc.) as well as behavioral data such as the search engine query that was typed by the user.

Results:Using predictive models, the client allocates higher-cost follow-up resources (e.g., agent phone call) for the leads that are most likely to convert, while it allocates lower-cost methods (e.g., emailing or redirecting the lead to online pages) for the leads that are determined to be less likely to convert.