Articles in this section

Second Purchase Propensity

This classification model scores all active customers in the population on their likelihood to make a second purchase at the time of their first purchase. This model gives you insight into who is most likely to return to your business, and the ability to segment your audience accordingly. In addition to modeling for the likelihood of a second purchase, the model is also able to take in any incremental purchase; that is, if a customer who just made their third purchase will return for a fourth.

 

How does it work?

MessageGears' default value for the window of prediction (known as the PREDICTION_WINDOW) is 90 days. This means that the model predicts the probability that an individual will make their next purchase in the next 90 days. If necessary, we can assign a custom PREDICTION_WINDOW that fits your unique sales cycle. We transform each customer’s unique data into a custom feature set, with automated training and tuning to deliver the most performant model possible.

The HISTORICAL_WINDOW determines who is eligible to be scored. For the Next Purchase model, the default HISTORICAL_WINDOW criteria is that a customer must have made their first purchase within the last 14 days.

After training and tuning, the model is ready to score the active population.

 

Results

The model’s output is a normalized SCORE that ranks customers from 100 (most likely) to 1 (least likely) to make their second (or incremental) purchase. It then assigns the customer into a percentile, creating a (mostly) even distribution that ranks customers against each other. A customer with a score of 99 is considered more likely to make a purchase than a customer with a score of 75, who in turn more likely to make a purchase than a customer with a score of 25. You can then use the score in segmentation or personalization for a wide variety of marketing use cases.

 

Requirements

 

Schema

MG Field Name Type Range Description
RecipientId VARCHAR   Unique customer identifier.
ML-NextPurchaseScore INT 0-100 normalized output of scoring Likelihood to make a second purchase at the time of their first purchase
ML-NextPurchaseLow BOOL 0 or 1 Predefined segments.
Our recommended audience definitions today break out high/medium/low where the top quintile = high; mid three quintiles = medium; bottom quintile = low. However, we can customize this during implementation.
ML-NextPurchaseMedium BOOL 0 or 1
ML-NextPurchaseHigh BOOL 0 or 1
Was this article helpful?
0 out of 0 found this helpful

Comments

0 comments

Please sign in to leave a comment.