Carson Group's AI/ML Adoption for Enhanced Lead Scoring and Customer Acquisition
- Analytics & Modeling - Machine Learning
- Application Infrastructure & Middleware - Event-Driven Application
- Education
- Equipment & Machinery
- Product Research & Development
- Sales & Marketing
- Predictive Maintenance
- Virtual Training
- Data Science Services
- Training
Carson Group Holdings LLC, a comprehensive ecosystem for advisors, was seeking ways to enhance their marketing efforts to help their investment advisor clients acquire new customers more effectively. They decided to adopt AI/ML, starting with a machine learning model for scoring leads received from Salesforce. The goal was to narrow down their leads, focusing on customers with the highest likelihood of investing, thereby reducing time spent filtering leads that are less likely to convert. This would optimize costs and drive growth for their clients more efficiently. Carson Group had the right data for training ML models and saw the potential to streamline the entire process of evaluating and scoring leads by their sales and marketing teams. They aimed to replace their existing predictive system, which relied on complex rules and heuristics, with a self-training machine learning solution for higher accuracy and efficiency in lead scoring.
Carson Group Holdings LLC is a comprehensive ecosystem for advisors, designed to help them better serve their clients and unleash their firm’s full potential to drive business growth. Carson Group offers a wide range of services, including advisor coaching programs, process optimization development and investment strategies, and discovery of lead and customer acquisition opportunities. With Carson, advisors receive industry-leading support for marketing, technology, compliance, investments, succession planning, and mergers and acquisition, enabling their firms to secure better positions on the market.
Provectus, an AWS Premier Consulting Partner with competencies in Machine Learning, and Data & Analytics, partnered with Carson Group to develop the ML model. The project began with the discovery and evaluation of Carson’s data, including labeled lead records and various reports on impressions, clicks, lead conversion cost, spend, and more. The ML model was designed and built from scratch, including EDA and modeling work, development of an end-to-end model training pipeline, and implementation of an inference pipeline. The model was enhanced and fine-tuned to reach an accuracy of 96% (chance of conversion), with actual conversions predicted from new data hitting the eight-out-of-10 mark (recall of 88%, precision of 67%). The ML lead scoring model was designed to seamlessly access new data from various sources, including Salesforce, and then deliver the results to the respective teams.