You've successfully subscribed to Thematic
Great! Next, complete checkout for full access to Thematic
Welcome back! You've successfully signed in.
Success! Your account is fully activated, you now have access to all content.
Success! Your billing info is updated.
Billing info update failed.

How to use prescriptive analytics to improve your customer relationships

Following on from a previous blog post, a great example of prescriptive analytics, shared by Bain, is the one of DiDi. DiDi is a major Chinese ride-sharing company providing transportation services for more than 450 million users across over 400 cities in China (i.e. many times bigger than Uber, whose China operations DiDi acquired and absorbed in 2016).

As you know, the Net Promoter® Score (NPS) is used by thousands of companies worldwide to establish the likelihood of customers recommending a product to others. What if you don’t want to or for some reason aren’t able to send out a survey? Sometimes you don’t even need to ask your customers directly for feedback. Imagine leveraging the vast scale of data generated by all of DiDi’s customer transactions – this gives the a huge advantage. Knowledge is power, indeed.

Matching the data DiDi collects on every aspect of millions of rides with end-of-ride ratings from customers allows the company to create predictive models. They’ll know what sorts of experiences usually produce promoters and which ones create detractors.

Thereby, DiDi doesn’t need to ask all its customers for feedback. The models generate a rating score for rides that match what customers say in traditional NPS survey.

This means that DiDi’s model can generate real-time feedback to its drivers. For example, it immediately identifies situations where there’s a need to rectify the relationship or service. This then triggers an intervention, possibly even before the customer has completed the ride. If the algorithms identify a pickup that went wrong or a ride that took longer than it should have, DiDi can issue an apology or a credit. On the other hand, if the ride went swimmingly well, DiDi’s app can prompt the customer with ways to share with their friends about the service’s benefits.

Is this the future of customer feedback? Companies using predictive analytics to figure out whether customers are promoters or detractors, and then using prescriptive analytics to help close the loop and enable instant action.
Advanced analytics applied in the right ways can foster even deeper customer intimacy using enormous volumes of digital interaction data to “remember, interpret and enhance each customer’s experience at every point of contact, digital or personal” (Bain, 2017).

Image credit: Netflix/ CBS News

Download Thematic e-book 'Best practices for analyzing open-ended questions'

Start your free trial

Thematic is the easiest way to discover the best insights in feedback. Act on what matters to your customers and make an impact.

Keep reading
How to theme qualitative data using AI analysis software
How to theme qualitative data using AI analysis software

If you ever had to analyze customer feedback, you will know that the most difficult part is to create a perfect code frame. You need to understand the dataset, the stakeholders involved and the ideal outcomes of the analysis. You will have to iterate before settling on a solution, which

Alyona Medelyan PhD
Alyona Medelyan PhD
AI & NLP
Text Analytics Software – How to unlock the drivers behind your performance
Text Analytics Software – How to unlock the drivers behind your performance

Many organisations, large or small, gather customer feedback to improve their CX efforts and ultimately their bottom line. But gathering feedback alone can’t make much of a difference. We need to analyze our feedback to discover insights that inspire us to drive action at our organisations. Enter; Text

Melanie Disse
Melanie Disse
AI & NLP
Thematic Analysis Software: How It Works & Why You Need It
Thematic Analysis Software: How It Works & Why You Need It

Most likely, you landed in this blog because you have too much feedback to analyze. You sent out a survey or collected reviews or other form of free-text feedback. Now that you have this feedback in-hand, what do you do with it? How can you identify common themes in responses?

Alyona Medelyan PhD
Alyona Medelyan PhD
AI & NLP