Existing customers spend 67% more than new customers, and acquiring a new customer is between 5x and 25x more expensive than retaining a customer. The implications are clear: Optimizing your existing customer lifetime value (LTV) is critical to growing your business.
The problem is, most businesses don’t spend much time optimizing their LTV. The focus is too often on acquiring new customers, and not enough time retaining and growing the value of their customers once they’re in your pipeline.
Akkio's models can analyze a company’s customer data to predict how much they’re likely to spend in the future, and will help you optimize your marketing spend and customer acquisition strategy.
Akkio simplifies the process of building an LTV model with a clear visual interface that lets you build a complete model in just a few minutes. In addition to providing lifetime value models, Akkio enables machine learning use-cases from predictive churn to lead scoring.
To get started, sign up to Akkio for free. As with any machine learning task, the first step is getting historical data and picking a column to predict.
We’ll use a dataset of vehicle insurance customers from Kaggle, titled IBM Watson Marketing Customer Value Data. This dataset includes nearly 10,000 rows of customer data, including information like the customer’s income, location, insurance plan, premium, and even vehicle size.
Crucially, the file includes our desired target variable, called Customer Lifetime Value. We can use machine learning to estimate the lifetime value for any new lead or customer, and then prioritize business resources accordingly.
Predicting LTV for insurance customers is a bit tricky. For one, a customer’s income can have a big influence on how much they spend on car insurance. In addition, some customers might have chosen a plan with a low deductible to minimize their costs right out of the gate. However, this will likely change over time as these customers get more familiar with their insurance plan and become more comfortable with their options.
A customer's location is also predictive of their future spending - customers in expensive areas like New York City are more likely to spend more on car insurance than customers in less expensive locations like Pittsburgh. With that said, calculating the importance of each of the 23 predictive columns in our dataset is quite a challenge.
Luckily, we don’t have to solve this by ourselves. Akkio makes it easy to build models that automatically take into account the entire dataset. We’ll simply download the dataset as a CSV, and then upload it to Akkio. You'll get a preview of the dataset, including modifiable data types, columns, and row count.
Now, we can click on the second step in the AI flow, which is “Predict.” Under “predict fields” you can select the column to predict, named “Customer Lifetime Value.”
You can add or remove as many columns as you’d like, and we'll build a model based on the selected columns. Then just hit “Create Predictive Model,” and you’re done.
You can also select a longer training time—from 1 to 5 minutes—for potentially more accurate models. Keep in mind that longer training times will not always necessarily perform better.
Also note that you don’t pay for model training time, unlike with many typical automated machine learning tools, so feel free to build as many models as you’d like.
After a model is created, you get a simple overview, which highlights the top fields, model prediction quality, sample predictions, and more. We’ll also see customer segments, showing, for instance, customer profiles with the lowest and highest values of lifetime value.
This indicates certain segments may be profitable for us to sell more to. For example, the highest lifetime value customer is a luxury car or luxury SUV driver with two policies. This means we can focus our marketing efforts on this customer segment and potentially increase profits.
On the flip side, the lowest lifetime value customer is someone with a single, basic policy. This means we should be careful about selling them additional products, as it may not make sense for us to invest in marketing for a low-value customer.
Armed with these insights, we can now prioritize our marketing efforts. For example, we could target the SUV customer segment with a more expensive offer for an annual policy, or focus on increasing engagement and retention among the highest value customers.
There’s also the option to “See Model Report,” which lets us easily collaborate with others and share these model details with anyone, even if they don’t have an Akkio account.
In short, we’ve discovered that it’s very easy to build a highly accurate model to predict customer LTV.
Now that we’ve built a model, it’s time to deploy it in the real world.
With Akkio, it becomes trivial to deploy complex machine learning models. Deployment via web app is an easy way to instantly serve predictions. It’s also possible to deploy through Salesforce, Google Sheets, Snowflake, and the Akkio API, with many more methods coming soon.
Further, you could deploy the model in practically any setting with Zapier, a no-code automation tool that connects tools with “Zaps.” Zapier allows you to link up thousands of different tools, so no matter where your data is coming from, it’s easy to connect it to Akkio to get a prediction, even if you don’t have any technical expertise.
If you’re looking for more technical power, you can also use Akkio’s API, which is formatted as a Curl command, allowing you to send a GET request that contains your flow key, API key, and input data, and get a prediction back.
We’ve explored how lifetime value is a crucial KPI, but it’s challenging to calculate. Akkio’s platform makes it easy for everyone - from marketing teams to product developers - to build AI models without any code or specialized skills.
You can use our visual interface to quickly define the inputs you want your model to use, as well as the target value you want it to predict. Our machine learning engine will analyze your data and return a probability of how much each customer might spend in the future.