Lead Analytics
For a Real Estate Advisory Firm
CLIENT & PROBLEM STATEMENT
- The client is a large Real Estate Advisory firm who works in a broking model.
- They provide potential property buyers with appropriate Properties & Developers.
- Client wanted to be the first in the space to use smart analytics to identify appropriate customers for the desirable properties.
- Identifying the customers from their large Digital marketing lead base who are high potential buyers.
APPROACH
- Based on project properties, different groups of lookalike projects were made through a popular clustering technique and on each cluster a data science model was created.
- The data science models created on this data reclassify future projects into clusters that have similar properties and assign a propensity of buying to customers, after months of rigorous updating of various Data Science models, testing them and validating them by prioritizing a set of customers.
- Machine learning models like Decision trees, Random forest, XGBoost.
SOLUTION & OUTPUT
- Customers are prioritized or de-prioritized based on the Data Science models at various sales process stages.
- A higher conversion rate of 6-7% was observed from the past, which led to a marked increase in revenue and at the same time efficiency.
- G-Square’s productified solution Clientrator is now implemented and is being used to track the ‘high propensity to convert’ customers.
