A security guard provider had a configure-price-quote (CPQ) process that required manual verification of security guard wage rates in specific regional markets. In order to scale the business, they envisioned an AI-based solution that would combine real-time regional data, data extracted from active job listings, and their historic wage data into a system to generate a trustworthy AI-predicted wage rate.
As soon as a new quote for a security guard is created in the CRM system (Salesforce) it is pushed via webhook into the Contextual platform. A series of Contextual Flows augment the quote with 20 distinct variables including geographic information, cost of living data, crime statistics, and current wage data. The augmented data set is passed into a custom machine learning model that predicts the expected wage rate for a security guard in that specific location and confidence in the range of potential rates. The prediction and all supporting data are then pushed back into the CRM platform to initially support and eventually automate pricing decisions.
