Applied AI & AI in business /

Save your NPS with operational AI

June 23/10 min read
  • Isak Hassbring
    Isak Hassbring

Hi there! My name is Isak and I work for Peltarion in Stockholm, Sweden. In this post we’ll demonstrate how you can act upon negative customer experiences and try to save your NPS score with operational AI and automation, using the Peltarion Platform and Zapier - an automation tool requiring no code at all, that we’ve supplied with a Peltarion connector. 

02/ Intro

What you will learn to build with this post.

The purpose of this post is to enable and inspire you to use our operational AI platform. If you’re used to e.g. Tensorflow or Pytorch you’ll be surprised how fast and easy it is to use our GUI (Graphical User Interface). If you’re not familiar with programming at all, you’ll probably be excited to hear that you can follow this demo without writing a single line of code.

There’s a 12 minute demo video for you to watch at the end of this article, however we’ll briefly introduce you to the project in written form below if you don’t have time to check out the demo video right away.

03/ Summary of the project

We’ll use a dataset of Amazon Kindle Reviews from Kaggle / Datafinity

We’ll train, test/evaluate and deploy a model with the data on the Peltarion platform. Given free-text product reviews, we’ll predict if customers would recommend the product or not.

We’ll build an automation flow in Zapier as follows:

  • Trigger: The automation flow is triggered to run every time a new customer review record is added into a “database” (we use Google Sheets for simplicity - many alternatives such as Postgres, MongoDB etc are available).
  • Action: The free-text review in the new database entry is sent to the Peltarion deep learning model deployment API we built, and shortly after, we’ll receive a response from the Peltarion API.
  • Logic gate: Based on the response (the outcome of predicting whether the customer would recommend the product or not), we’ll decide whether or not we want to reach out to the customers and try to prevent them from becoming detractors. 
  • Action: The above can be done in multiple ways, for simplicity in the demo we’ll connect to Gmail and send them a promo code over email. The email can be customized to perfectly fit the customer, if we have such requirements.

Note that..
..many other solutions can be implemented - e.g. one could automatically reach and to and listen to the customers and understand what could be done better, hence solving the core problem on a long term notice. Finding the very best action to take is outside the scope of this demo and is better discussed within the context of the actual use case. However if you want suggestions we’ll be happy to help and look closer into the business case that you want to solve. Simply sign up on the Platform and reach out in the chat! 

04/ NPS

For anyone who hasn't heard of NPS (net promoter score) before, it is an important KPI (key performance indicator) when it comes to customer satisfaction and is simply calculated as the share of customers considered being promoters minus the share of customers considered being detractors. NPS scores vary a lot between industries. To evaluate a product’s or company’s performance related to NPS is it preferable to compare with direct competitors. So why care about NPS? Because it tends to tell a lot about the overall customer experience. It’s said to be about 5-6 times more expensive to attract new customers than to keep existing ones, so you would want to keep your NPS score as high as possible. And to keep existing customers, it is usually good to take action and respond fast when they’re not satisfied. 

05/ The project

The good news is that Peltarion provides an easy solution for letting machines (instead of humans) read, understand and decide how to act upon receiving customer feedback. This could make life easier for lots of people. Meanwhile it does of course require some amount of manual setup, which is what we’re going to look at during the next couple of minutes. 

I’ll start out introducing what we’ll build in this demo, then we’ll build it, and finally we’ll wrap up and tell you how to get started. 

We will build a simple app that, given free-text customer reviews, uses deep learning to predict whether or not the customer would recommend a given article. Based on prediction results, the app will connect with potentially dissatisfied customers and try to win them back as fast as possible, by sending them a message with a promo code. Now oftentimes it is not that simple, this flow is mainly for simplicity and it is a good start. If you’d like to make a more complex automation flow, everything is possible, it will just take a bit longer to build. When we’re done building, everything will be running autonomously using Google Sheets Peltarion and Zapier. Note that we will not actually predict or calculate NPS scores, but act on caught detractors in order to push the NPS score up.

Before we start the project we need to clarify three things. First, the dataset we’re going to use. Then, the problem type in terms of machine learning, and finally based on that, decide what model we could use to attack the problem. 

We’ll use a dataset found on Kaggle / the Datafiniti API. The dataset consists of Amazon Kindle Reviews. It has a free text review label, and a DoRecommend-label that tells if the customer would/would not recommend a given product. In other words, it fits our project very well. Here's the dataset.

Regarding the problem type, classifying text reviews and mapping them to a binary value (recommendation or not) is what one would call a binary text classification problem.

We’re going to classify a binary value based on free text. Fortunately there’s a perfectly suitable deep learning model pre-implemented on the Peltarion platform - the English Bert.

Now that we have what we need (dataset, problem type, model), let's go ahead and build our project. First we’ll build, train, evaluate and deploy the model with the Peltarion Platform. Then we’ll connect the model to Zapier and set up our simple automation flow with Google Sheets, Peltarion and Gmail. 

Whenever you’re ready - feel free to start the 12 min video. Good luck!

  • Isak Hassbring

    Isak Hassbring

    Isak joined Peltarion in May 2021. He is pursuing a MSc degree at KTH Royal Institute of Technology in Stockholm, Sweden. 

02/ More on Business & Applied AI