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

Consent(Required)
This field is for validation purposes and should be left unchanged.

Recommended Articles

Article
How to deal with the annoying implications of changing data sources

Let’s discuss a common scenario in AI consulting. The client provides access to data sources in formats such as CSVs or databases that aren’t in a production environment. Why? Usually, they’re exploring the value of the project, do not want to disclose too much data and want to prevent technical problems from happening at the […]

Read More
Article
Stop removing outliers just because!

Outliers are data points that stand out for being different from the remaining data distribution. An outlier can be: An odd value in a feature A data point distant from the centroid of the data A data point in a region of low density, but between areas of high density. Suppose you have been working […]

Read More
Article
Insights from UPTEC NON STOP

Last month, we participated in UPTEC NON-STOP, an event celebrating the 15th anniversary of UPTEC. UPTEC is the Science and Technology Park at the University of Porto, where businesses and academia meet to exchange ideas. During the event, local startups incubated at UPTEC (NILG.AI included), and French startups promoted by Accelerateur M pitched their business to […]

Read More