Welcome
User Guide
Preconfigured Reference Models
MaxAI Workbench provides reference models for use with products like Unica Campaign, Unica Journey, HCL CDP, etc.
Buying Propensity Model
A product propensity model predicts the likelihood that a customer, existing or new, will adopt or purchase a specific product in the near future. Predicting which product, a customer is likely to take next.

HCL MaxAI Workbench Documentation
Release Notes
Installation Guide
Developer Guide
MLAC User Guide
User Guide
- Introduction
  MaxAI Workbench is an AI life cycle management platform for applying machine learning to real-world problems. MaxAI Workbench encompasses the complete pipeline from raw data ingestion to a deployable machine learning model with a less-code/no-code approach.
- Model Management
- Model Training
- Model Prediction
  Model prediction predicts the input data based on the pattern of training data.
- Trusted AI
  This feature is available for classification and regression problem types.
- Model Monitoring
  This feature is available for classification and regression problem types.
- Utility
  For Data Generator and BYOM (Bring Your Own Model), select the Utility tab.
- Preconfigured Reference Models
  MaxAI Workbench provides reference models for use with products like Unica Campaign, Unica Journey, HCL CDP, etc.
  - Next Best Channel (NBC) Model
    The Next Best Channel (NBC) model identifies the most effective communication channel for each customer based on demographics, banking behavior, device preferences, and previous marketing interactions. It helps optimize customer engagement and improve conversion rates across channels like WhatsApp, Email, SMS, IVR, Push Notifications, and more.
  - Send Time Optimization (STO) Model
    The Send Time Optimization (STO) Model enhances customer engagement and boost conversion rates by predicting the optimal time and channel to send marketing communications for each customer. By analyzing customer demographics, behaviors, device preferences, and historical engagement patterns, the model personalizes marketing strategies for improving open rates, click-through rates, conversions, and marketing ROI.
  - Churn Prediction Model
    A churn prediction model identifies the likelihood that a customer will stop using a company's products or services within a given period. The objective is to proactively detect customers at high risk of churn so that timely retention actions can be taken.
  - Buying Propensity Model
    A product propensity model predicts the likelihood that a customer, existing or new, will adopt or purchase a specific product in the near future. Predicting which product, a customer is likely to take next.

Buying Propensity Model

A product propensity model predicts the likelihood that a customer, existing or new, will adopt or purchase a specific product in the near future. Predicting which product, a customer is likely to take next.

This model leverages customer demographics, product holdings, behavioural data, and historical campaign interactions. The target variable (target) is binary:

1 indicates conversion/engagement.

0 indicates no conversion.

The Product Propensity Model aims to predict the likelihood of an existing or prospective customer purchasing or adopting a specific banking or financial product (for example, credit card, personal loan, savings account upgrade, insurance). This helps prioritize offers, personalize campaigns, and optimize sales channel efficiency.

Example: If a bank wants to offer the perfect product to each customer, using a propensity model, it can predict who is most likely to respond, ensuring every campaign reaches the right person. This not only boosts conversions but also creates a personalized experience for every customer.

Features

Customer Profile (Demographics and Static Attributes): Demographics and profile attributes often influence product adoption behaviour. For example, younger customers may prefer digital products, while older customers may prefer traditional loans. Geography and device can also affect accessibility and channel effectiveness.
Product Ownership / Portfolio: Existing product portfolio is highly predictive of future product adoption. Cross-sell/up-sell opportunities depend on what the customer already holds or has closed in the past (for example, customers with savings accounts are more likely to adopt credit cards).
Engagement and Campaign Exposure: Measures historical exposure and responsiveness to marketing campaigns. Customers with higher campaign exposure and recent interactions are more likely to show interest in new offers.
Channel Engagement and Response Behaviour: Captures channel-level effectiveness and customer preferences. For example, customers with high WhatsApp accept rate are strong candidates for future WhatsApp-driven offers. Balancing open and accept rates helps identify not just engagement but also intent.