Propensity Modeling for Retail Marketing: Model Adjustments Based on Consumer Life Changes.

Question

I built a predictive model using logistic regression for direct marking creatives. I built a “children’s” model which predicts buying behavior for those that purchase boys, girls and baby apparel. But one may have a high propensity right now to buy baby clothes but in 12 months, when ones kid is a toddler, their propensity drops for baby and increases for Girls/Boys. I’ve been trying to brainstorm ways to take into account that scenario. My question is, can anyone suggest options for adjustments to the model to based on that additional criteria?

Answer 1

If you have the purchase data for all these customers, this could be one way to approach the problem:

You could either cluster the customers into natural groups based on their most recent purchases or find association rules (the likelihood of the customer purchasing in a particular category based on their most recent purchases).

I'm not sure how well this approach is going to work for you, but it worked for me in my scenario of propensity scoring. So, if it makes sense, try to relate your data to mine.

I had a list of customers and their purchase behaviors. From those purchase behaviors I deduced association rules to determine which customer is likely to purchase in what product category (based on their previous purchases- associated with the previous purchases of the group).

You can also include recency and frequency of the product purchases into the model to decide whether or not to recommend a particular product/offer to the customer for a specific time.

Based on the confidence, support and lift metrics of those rules for each customer, I mapped them to highly likely to purchase in this category with confidence being their propensity score.

Let me know if this works with your data.