Glovo

Automated calls to remind Glovo couriers of debt

Glovo uses a voicebot to send automated voice notifications to remind couriers of their debt while using the platform. If customers paid a courier in cash for orders and then a courier didn't deposit that money back, the platform can’t intermediate in the process of reaching that money to other users (businesses) and the courier would automatically receive a call.

Voximplant Kit interface allows us to create the voicebot faster than other services. Moreover, the Voximplant team offered to create all of the scenarios themselves. We improved and finalized it during testing, and the Voximplant experts have always done their utmost to make a difference. When starting a new business process, it is very important to have a partner who will provide comprehensive support and top-notch recommendations. We replaced our existing provider with Voximplant, because the previous provider wouldn’t help with the scenario development, and continuing to use internal resources wasn't an option for us. Also, the previous provider only used DTMF but A/B tests in several countries showed that the conversion rate from ASR was 10% higher than DTMF.

Antonio García-Bragado Casellas
Global Cash Manager at Glovo

Problem

A courier can stop delivering while still having cash to deposit

According to the Glovo’s terms and conditions, the courier can stop using the app at his or her own request without further explanation. In addition, the company operates in many regions where cash payments are widespread, therefore, customers pay for the order directly to the courier.  So there are situations when a courier stops delivering while still having cash to deposit.

 

As soon as the company realized that certain amounts of cash had not been refunded by couriers, in order to intermediate in the process of reaching that money to other users (businesses), the need for collections became obvious. And given that the company has lots of active couriers that use the app every month, it is not possible to manually keep track of everyone's account and have people make calls manually. Before working with Voximplant, the company used other tools for this, but the refund conversion rate was extremely low.

Solution

Automated calls to remind Glovo couriers of debt

Using Voximplant Kit’s no-code drag and drop visual builder, two scenarios for calls to couriers were set up. 

 

Scenario # 1: Calling a courier who has not used the app in the last 14 days and has a debt. When the voicebot calls, it introduces itself as a Glovo voice assistant, addresses the courier by name and says that the company has noticed a lack of activity on his or her account. The robot then asks if the courier plans to continue using Glovo. If the answer is affirmative, the robot reminds the courier that for using Glovo he/her needs to book delivery slots in the app. If not, the robot says that Glovo will always be pleased to get him/her back. Additionally, regardless of the answer, a request is made to refund the cash received from customers.

 

An additional personality validation mechanism triggers in case a courier claims that they are not the person the company is looking for. If triggered, the scenario plays first name and last name of the respective courier and repeats the question. If a courier continues to insist, the script marks this call for later analysis and finishes the conversation.

 

Scenario # 2: Calling a courier who has a debt and whose account has been deactivated due to a violation of the terms of service. During the call, the voicebot introduces itself, greets the courier by name, notifies that the account is blocked, and specifies the amount of outstanding funds that must be refunded by a certain deadline.


Speech synthesis and recognition technologies are used in the communication between a voicebot and a person. Immediately after the call ends, couriers receive additional information as well as a payment link via SMS and email. The voicebot uses data from Glovo’s CRM to dynamically personalize voice messages as well as texts for SMS and email (e.g. courier's name, debt sum, currency).

 

The project currently operates in seven languages: Spanish, Portuguese, Russian, Romanian, Ukrainian, Georgian, and Italian.

How it Works

Speech-To-Text

Speech recognition and natural language processing

Text-To-Speech

Synthesis of a unique voice for speaking to customers

HTTP API

Script integration with any application

Voice Recording

Call recording for quality assurance

Result

30-40% of couriers return the debt after the call

With the introduction of automated voice calls using the voicebot, the company can contact every courier who has not deposited cash. Depending on the region, 30-40% of couriers return the debt after the call. At the same time, 40% of couriers who did not deliver orders within 2 weeks confirm that they want to continue using Glovo. Additionally, 68% of couriers whose account was deactivated listen to the voicebot's message completely and do not hang up.


Thanks to the integration, Glovo is able to reclaim more and re-engage inactive couriers to start using the app again. Glovo also intends to expand this into new markets because of its quantitative positive impact on results.

Automated calls to remind Glovo couriers of debt

Glovo is a Barcelona-based startup and a fast-growing technology company whose main activity is the development and management of a technology platform through which certain local stores in a number of territories can offer their products and/or services by means of a mobile or web application on the platform.

Employee count

1,900

Project start date

2020

Location

Europe, Western Asia and Africa

Automation area

Delivery, Courier operations, Cash debt collection