Appendix: Embedding Domain Knowledge for Estimating Customer Lifetime Value

How we designed an interpretable neural network to predict Customer Lifetime Value (Appendix)

This is an appendix to the blog post Embedding Domain Knowledge for Estimating Customer Lifetime Value. We will describe some alternatives we considered for solving the proposed problem, but did not end up being implemented.

First, let’s assume we have a pre-trained model for estimating the probability of the target $yAlive_N$ and $yTaker$.

Estimating Lifetime Value using an optimization function

With a model containing client propensity of accepting the offer (yTaker), we can make a simple calculation for estimating CLTV:

Business Rules only approach

     \begin{eqnarray*} argmax & ( & \\ \text{X in Offer} & & (Propensity(User, X) \times PriceDest(X) \times 24 + \\ & & (1-Propensity(User, X)) \times PriceOrigin(User, X) * FP)\\ & ) & \\ \end{eqnarray*}

The first term of the equation is the expected revenue at the end of the fidelization period (FP), which is being renewed to 24 months. A second term is summed, comprised of the expected revenue in case the client does not accept the offer (and assuming no new offer is made in the remaining months – as such, he remains for “FP” months).

Business Rules + Propensity + Churn Model approach

Let’s now assume we have two models:

  • Propensity Model: we can calculate the probability of y_taker_N (i.e., of client accepting the offer)
  • Churn Model: we can predict the number of remaining months until the client churns

And that we also have some business rules embedded:

  • Survival Buyers: we can calculate global survival curves, for the complete customer base (Buyers), for clients which accept any new offer. These give us the average number of months until the client leaves the company, if he accepts an offer.

We can then create a slightly more complex optimization function.

     \begin{eqnarray*} argmax & ( & ( PriceDest(X) \times Buyers(FP) \times Propensity(User,X) + \\ \text{X in Offer} & & (1-Propensity(User, X)) \times PriceOrigin(User, X) \times \\ & & Churn(User) \\ & ) & \\ \end{eqnarray*}

Single-Task Machine Learning 

Although this is a solution that can be quickly calculated in case pre-trained models are available for churn and taker tasks (which is good for quick proofs of concept and baseline performance), we are not using much of the knowledge which can be extracted from customer interaction.

A possible approach for using this is including the probabilities of accepting the offer and churning as features, as follows:

CLTV :: Propensity x OriginOffer x DestinationOffer x ChurnProbability

However, this would require maintaining three models in production, and assessing their quality constantly: a regression model for estimating customer lifetime value, propensity model and churn model. Also, if we wanted to do a multiple output approach, this would require having as many pre-trained models as the number of outputs.

Like this story?

Subscribe to Our Newsletter

Special offers, latest news and quality content in your inbox once per month.

Signup single post

This field is for validation purposes and should be left unchanged.

Recommended Articles

Five Years Helping Entrepreneurs Embrace AI

We celebrate the 5th anniversary of NILG.AI with immense pride and gratitude. Over the years, we’ve embarked on a transformative journey, and today, as we commemorate this milestone, we want to take a moment to reflect on our accomplishments and share our exciting plans for the future. NILG.AI Fifth Anniversary: A Year of Remarkable Achievements […]

Read More
Classifying text using LLMs

  Text classification is one of the most common use cases in Natural Language Processing, with numerous practical applications – now easier to access with Large Language Models. Companies use text classification in multiple scenarios to become more efficient: Tagging large volumes of data: reducing manual labor with better filtering, automatically organizing large volumes of […]

Read More
NILG.AI will be at the Iqony Technology Days 2023

Innovation drives the future of the industry, and at NILG.AI, we’re committed to leading this charge. Therefore, we’re excited to announce our participation in the upcoming Iqony Technology Days 2023, scheduled for this September in Brühl, Cologne. Our enthusiasm is fueled by our recent victory in the Hands On Data (HOD) challenge earlier this year.  […]

Read More