South East Asia-based insurance provider catering to small and medium businesses.
The sales and marketing groups were facing four critical business issues: High cost of acquiring and training agents, high attrition rates, inconsistent performance of agents, and time-consuming agent selection process.
SG Analytics deployed a four-step process to address this business problem:
SG Analytics first built an agent database using parameters such as written premium, a tenure of service, conversion rates for high-value customers and persistence index.
Based on the data, our data scientists created three clusters of agent performance using the centroid-based method and hierarchical clustering at both portfolio and regional level.
The team then used statistical techniques like ANOVA, chi-squared test of independence and various other descriptive statistical techniques to identify characteristics for reporting.
Finally, we developed a model using supervised learning techniques such as Random Forest, SVM, Neural Nets and Discriminant Analysis.
85% accuracy on unseen data.
Improved the effectiveness of the agent selection process.
Increased the overall hit ratio by 17% and revenue by 12% on a sequential basis.