How to Identify High-Potential Customers With Customer Lifetime Value

Use Cases & Projects, Dataiku Product Benoit Rojare

Three people enter a wine shop at the same time — one of them comes in every week to buy a bottle, another one has never been there before, and the third comes very rarely but usually ends up buying several crates of wine bottles. Question: Which customer should the sales clerk go help first? This is not a riddle meant to give you a headache, but a situation that any retailer must know how to handle.

customer in wine store

No decision can be made wisely without a minimum amount of customer data. If the three people who enter a shop are unidentifiable, there won’t be any way of deciding on a priority. So step one would be to identify the people already in the customer base. Step two is straightforward: Spend time with the people that are already customers! According to Forbes, acquiring new customers costs five times more than retaining existing ones.

If we want to go all the way in knowing which customer to target first, a good approach is to calculate the Customer Lifetime Value (CLV). The simple objective behind it is to identify who the most valuable customers are, what their potential future spendings amounts to, and how to engage with them. Bain & Company states that CLV-supported strategies enable retailers to deliver up to a +30% lift in sales. Dataiku just released a new solution that helps kickstart your implementation of CLV in your marketing strategy, so let’s look at that more closely.

Customer Lifetime Value Enriched With RFM

Dataiku’s approach to CLV takes advantage of the RFM technique based on the three following elements that make up the acronym: Recency, Frequency, Monetary Value. Since when did the customer last purchase something? What is the usual pace at which purchases are made? How much does the customer usually spend? These metrics help build a balanced segmentation model.

Additionally, the purchase history of the customer is poured into the calculation of the CLV score. Then, the score can be used in many different valuable ways: For instance, a marketing analyst could use it to know which customers to invest into by pushing promotional offers. A CRM analyst could want to optimize the CRM budget and strategy by delivering personalized offers to certain customer segments. 

Let’s look at what you might find in this solution exactly, but first a reminder of what an Industry Solution actually is.

How Can Dataiku's Industry Solutions Help You Reach Full Potential?

Industry Solutions are Dataiku add-ons accelerating the journey to realize advanced or foundational industry-specific use cases within your organization. They are an operational shortcut to achieve real-world business value. Taking advantage of Dataiku’s core features, they are built to be fully customizable and entirely editable.

They come with:

  • A user-friendly interface that enables fine tuning to match specific business requirements
  • Ready-to-use dashboards that can be customized
  • Documentation and training materials

Dataiku industry specialists develop solutions for every vertical, among which:

As a result, business professionals experience a boost in AI productivity and can rationalize their resources.

How Does It Work in Practice?

The RFM-Enriched Customer Lifetime Value solution provides a reusable project wireframe to accelerate the development of analytics tailored to your data and business structure.

Learn more about Dataiku's RFM-Based Customer Lifetime Value solution in the video above.

With this solution, marketing analysts, CRM specialists, acquisition managers, or marketing directors can access:

  • A full end-to-end pipeline
  • Probabilistic & machine learning models to predict the projected CLV
  • Ready-to-use dashboards to consume insights

From a user perspective, the solution is made of the following easy-to-use components: 

1. Ingest Data Sources and Compute CLV Scores:

In this flow zone, we pre-process the data source (transaction history) and then calculate the current CLV of existing customers.

2. Compute RFM Scores:

At this step, scores are computed for each customer. Then, a sum of three scores is made to compute a final RFM score.

RFM score distribution

3. Segment Customers According to Their Marketing Recency and Frequency

10 segments are built according to customers’ Marketing Recency and Frequency using a visual matrix.

customer segments visual matrix

4. Tier Customers Based on Their Future CLV: High, Medium, and Low

Customers are classified according to their CLV score.

CLV score

5. Predict Customers' Future CLV Across Different Dimensions

This step focuses on predicting customers' CLV with different approaches. It is possible to compare all approaches and select the one that best matches your needs.

customer SLV prediction

6. Find the Most Bought Products With the Highest Predicted CLV

With the help of more data on the items sold, this step allows users to combine the most frequently bought products with the highest predicted CLV.

highest predicted CLV

Start implementing your CLV system enriched with RFM, with these simple requirements:

  • Historic data on the past transactions
  • Dataiku version: 9.0 or later

You May Also Like

Alteryx to Dataiku: Working With Datasets

Read More

Demystifying Multimodal LLMs

Read More

I Have AWS, Why Do I Need Dataiku?

Read More

Why Data Quality Matters in the Age of Generative AI

Read More