Real-time Propensity Scoring

Configuring Scores for Automated Personalization.

In Statistical Analysis, Behavior Scoring (Propensity Scoring) is a technique that is useful in predicting or estimating an outcome. This is done by applying scores to co-variates (independent variable) which may be of direct interest or it may be an interacting variable.

In the context of Plumb5, this model is applied to enable real-time engagement automation by using scores set by marketers to estimate/predict customer behavior. These predictions can, in turn, trigger personalized engagements. The marketer can also predict behavior at different stages of the customer lifecycle. Here, the term ‘behavior’ applies to all user parameters spanning interactions, responses, sentiments and transactions.

Listed are some of the preset attributes that can be configured by marketers to detect intent and trigger relevant communication based on intent. Click here to view sample documentation on how you can use scoring for your customer interactions.

1. Assigning scores to Sources
Assigning scores to source URLs helps in segmenting visitors coming from particular campaigns. You can even add scores to all interaction points and create custom attribution models, which help in identifying even the smallest contributing source.

2. Assigning scores to pages
Assigning different weights based on page type will help you understand the intent behind each visit. If your goal pages include 'add to cart' pages or 'wish list' pages, you would want to give them higher scores, so that you can easily segment visitors with high intent and assign conversion workflows based on scores.

3 Assigning scores to Time-spent
Scoring duration, based on time spent also contributes in analyzing the intention.

4. Assigning scores to PageDepth
Scoring Page Depth is crucial. Page depth scores help you in quickly identifying an opportunity and can be easily targeted using personalization work-flows

5. Assigning scores to Frequency
Frequency scores, along with page depth scores, reveal urgency and intent associated with user engagement.

6. Assigning scores to recency
Assigning scores to Recency also helps in identifying drifting visitors. You can set negative scores for drifting visitors,, so that you can be notified of negative scores

7. Assigning scores to events
Assigning scores to events helps in measuring intent. You can add high scores for key interactions like 'add to cart' or 'add to wish list' button.

8. Assigning scores to groups
You can also assign scores to fresh contact lists with a base score and assign a lead generation workflow to enable automation