Covering Disruptive Technology Powering Business in The Digital Age

inDrive, the global ride-hailing service, revealed how artificial intelligence (AI) is increasingly integrated into every aspect of its ride-hailing app to enhance efficiency and accuracy, lower costs, improve safety, and elevate user experience. This integration is pivotal in a rapidly evolving market like Malaysia, where urbanisation and technological advancements are shaping the future of transportation, aligning with the Malaysian government’s initiative to actively promote AI through the National AI Framework and the Malaysia AI Blueprint, with the aim to position the country as a regional leader in AI technology. 

Improving user experience, from support to timing, supply and user feedback

Modern ride-hailing services now provide an estimated time for the driver’s arrival and the expected time of arrival at the destination, even in the presence of unforeseen events. Using pricing and matching models, inDrive can account for local conditions such as traffic surges, sporting events, and accidents, becoming more accurate in its predictions with more local data collected.

These conditions can also affect the number of drivers available and, in turn, customers’ ability to book rides. inDrive uses this information to create heat maps, guiding drivers to hotspots to increase supply where it is needed and better serve its users. 

AI is also improving customer service and support, which can be automated to enhance self-service options. For example, reducing the amount of boilerplate material a customer has to read and instead providing more focused, relevant information. This reduces customer waiting time, improves efficiency, and allows staff to prioritise and address more complex issues. 

When dealing with customer feedback, inDrive utilises AI to cluster and categorise this information into analytical data that allows them to spot trends and infer customer sentiment and tone of voice. This helps to highlight emerging issues and areas for improvement, so that the company can direct their efforts where they have the most impact.

Getting the price right

inDrive differs from many of its competitors in that it adopted a peer-to-peer negotiation model, allowing drivers and passengers to directly negotiate the price for a ride. The company uses machine learning in the pricing models to improve the accuracy of the recommended price when customers bid for rides, providing a starting point for negotiation that is fair to both customers and drivers. By using AI to automate manual pricing, inDrive can react more quickly to dynamic conditions, so that drivers can increase their earnings when demand is high, and passengers can successfully book at a price point that matches their expectations.

Streamlining processes and spotting fakes

“Internally, AI can be used to improve operational efficiency by streamlining processes, for example, during security checks. When a driver wants to register in the app, they must supply several documents, including Identification Card (IC) and driver’s licence. These are manually and digitally verified by a dedicated team of professionals using different filters, currently testing machine learning-based features to better identify fraudulent documents.”  Stephen Kruger, Chief Technology and Product Officer (CTPO) for inDrive shares. 

This process allows inDrive to spot fakes more reliably and quickly, thereby increasing the safety and security of its users and speeding up the verification process for legitimate drivers.

The company also works with artificial intelligence to strengthen its security ecosystem in other ways. For example, in some countries, inDrive uses a facial recognition tool to validate its users’ identities and machine learning to review users’ profile images and exclude sensitive, potentially dangerous, or commercial content.

The challenges

AI and machine learning can make a considerable difference to the quality and safety of ride-hailing services; however, they present several challenges. One such challenge is model drift, where models gradually become less relevant over time and thus require retraining. To address this, inDrive is working to improve learning capabilities to ensure the models remain up-to-date – essentially enabling them to self-train. Since inDrive operates in many countries, it adapts to the different laws and regulations, balancing technological advancement with privacy protection and societal well-being on a regional basis. 

It is imperative to ensure the protection of personal data when collecting it. This can be achieved in part by obfuscating data in a manner that preserves its contextual value while concealing the customer’s personally identifiable information (PII). The privacy and security of the collected data are ensured by restricting access to a strictly need-only basis. inDrive’s operations teams are prohibited from accessing data in bulk and may only use it for active support requests. In addition, customer-driver exchanges of PII are minimised and utilised solely to enable drivers and passengers to locate each other and to enhance the ride experience.

As in many other industries, AI and machine learning are enabling the ride-hailing sector to rapidly evolve in quality, safety, and efficiency, impacting every aspect of the business. The use of AI has transitioned from a futuristic concept to a fundamental component of the present, with its benefits being experienced each time a ride is hailed.

Mohamed Khalil, Regional Driver Acquisition & Activation Team Lead at inDrive Malaysia, says, “as we continue to integrate AI and machine learning to improve our services, inDrive remains committed to enhancing the ride-hailing experience in Malaysia by improving efficiency, safety, and customer satisfaction to benefit both drivers and passengers, and pave the way towards transforming the local ride-hailing scene. “

(0)(0)