← Back to all Predictive Models
PREDICTIVEThis model is designed to predict the probability that a customer will convert from registered-only status to making their first purchase/deposit.
Welcome Campaign Optimization
Personalize onboarding offers based on conversion likelihood
Acquisition Strategy Enhancement
Enable strategic customer targeting to:
- Allocate promotional budgets optimally based on conversion probability
- Identify high-potential prospects for premium welcome incentives
- Optimize acquisition channels by analyzing converted customer patterns
- Population Lifecycle Stages: Customers in "registered-only" or "non-deposited" lifecycle stages
- Target Lifecycle Stages: Customers in live lifecycle stages
- Training: Runs every iteration (unless data drift/changes require retraining)
- Inference: Runs daily in the daily process
The following outputs are stored in the customer profiles (as internal fields):
- Conversion Probability Score: Probability of this customer to convert within the next 2 iterations
-
Percentile rank in Conversion Probability:
Percentile rank among all not-converted customers by Conversion Probability Score.
On a scale of 1 (lowest) to 100 (highest) -
Permille rank in Conversion Probability:
Permille rank among all not-converted customers by Conversion Probability Score.
On a scale of 1 (lowest) to 1000 (highest), providing higher-resolution segmentation than the percentile ranking
- Training Window: default = 20 iterations
- Prediction Horizon: default = 2 iterations
- Catboost Classifier, which is the state-of-the-art model for tabular data
- Individual models per lifecycle stage for optimal accuracy
- Hyperparameters tuning in the first model training for optimal model parameters
Data Cleaning & Imputation: Handles missing values, removes constant features, and groups rare categorical values
Feature Engineering & Encoding: Converts categorical variables to numerical format using target-based encoding and applies scaling transformations
Feature Selection & Optimization: Removes low-variance and highly correlated features, selecting the most predictive variables
- Historical customer profiles (customer activity data, demographic data, campaign history, etc.)
- Minimum 3 iterations of historical data required for training (1 iteration for feature generation and 2 iterations for target definition, given the 2-iteration prediction horizon)
- Minimum number of 500 customers per lifecycle stage required for training
- Minimum number of 50 customers that converted to live lifecycle stage per lifecycle stage required for training