As Southeast Asia’s leading super app, Grab serves millions of users across multiple countries every day. Our services range from ride-hailing and food delivery to digital payments and much more. The backbone of our operations? Machine Learning (ML) models. They power our real-time decision-making capabilities, enabling us to provide a seamless and personalised experience to our users. Whether it’s determining the most efficient route for a ride, suggesting a food outlet based on a user’s preference, or detecting fraudulent transactions, ML models are at the forefront.

However, serving these ML models at Grab’s scale is no small feat. It requires a robust, efficient, and scalable model serving platform, which is where our ML model serving platform, Catwalk, comes in.

Catwalk has evolved over time, adapting to the growing needs of our business and the ever-changing tech landscape. It has been a journey of continuous learning and improvement, with each step bringing new challenges and opportunities.

In May 2023, Grab unveiled the Live Activity feature for iOS, which received positive feedback from users. Live Activity is a feature that enhances user experience by displaying a user interface (UI) outside of the app, delivering real-time updates and interactive content. At Grab, we leverage this feature to keep users informed about their order updates without requiring them to manually open the app.

While Live Activity is a native iOS feature provided by Apple, there is currently no official Android equivalent. However, we are determined to bring this immersive experience to Android users. Inspired by the success of Live Activity on iOS, we have embarked on design explorations and feasibility studies to ensure the seamless integration of Live Activity into the Android platform. Our ultimate goal is to provide Android users with the same level of convenience and real-time updates, elevating their Grab experience.

In our system, we use the term “treatment” to refer to the core unit of a full IFTTT data structure. A treatment is an amalgamation of three key elements - an event, conditions (which are optional), and actions. For example, consider a promotional campaign that offers “100 GrabPoints for completing a ride paid with GrabPay Credit”. This campaign can be transformed into a treatment in which the event is “ride completion”, the condition is “payment made using GrabPay Credit”, and the action is “awarding 100 GrabPoints”.

Data generated across various Kafka streams by multiple services within Grab forms the crux of events and conditions for a treatment. Trident processes these Kafka streams, treating each data object as an event for the treatments. It evaluates the set conditions against the data received from these events. If all conditions are met, Trident then executes the actions.

Key to innovation and improvement in machine learning (ML) models is the ability for rapid iteration. Our team, Chimera, part of the Artificial Intelligence (AI) Platform team, provides the essential compute infrastructure, ML pipeline components, and backend services. This support enables our ML engineers, data scientists, and data analysts to efficiently experiment and develop ML solutions at scale.

With a commitment to leveraging the latest Generative AI (GenAI) technologies, Grab is enhancing productivity tools for all Grabbers. Our Chimera Sandbox, a scalable Notebook platform, facilitates swift experimentation and development of ML solutions, offering deep integration with our AI Gateway. This enables easy access to various Large Language Models (LLMs) (both proprietary and open source), ensuring scalability, compliance, and access control are managed seamlessly.

Dive into our journey of improving in-app translation experience amidst a post-COVID tourism boom. Discover how we overcame language detection hurdles, crafted an in-house translation model, and…

通过启用PGO（Profile-guided Optimization），可以显著减少CPU和内存的使用。在实验中，启用PGO后，CPU使用率降低了至少10%，内存使用量减少了至少10GB（30%）。此外，通过实例TalariaDB的应用，启用PGO后，存储事件的卷使用量减少了至少7GB（38%）。然而，在Catwalk服务中，启用PGO所需的工作量可能不值得获得的改进。总的来说，启用PGO的适用性和效益因服务的特性、当前架构和支持机制而异。未来，随着更多服务对PGO的支持和改进，可能会实现更广泛的PGO应用，提供更快的响应时间、更低的资源消耗和更好的用户体验。

Discover how Grab assesses marketing effectiveness using advanced attribution models and strategic testing to improve campaign precision and impact.

Join us as we share our experience in developing and implementing a consistent upgrade routine. This process underscored the significance of adaptability, comprehensive preparation, efficient…

As the amount of data Grab handles grows, there is an increased need for quick detections for data anomalies (incompleteness or inaccuracy), while keeping it secure. Read this to learn how the Risk…

该文章介绍了Grab开发的实验工具包，用于在Grab平台上进行实验和因果分析。该工具包具有多种纠正技术，能够处理多个处理组、不均匀处理大小和异质处理效应。它在Grab内部广泛使用，并提供了GrabCausal Methodology Bank以共享因果方法的代码和指南。文章强调了持续更新和了解最新统计测试方法的重要性。总的来说，该工具包为Grab的数据科学家社区提供了自动化实验和产品决策的支持，进一步推动了Grab在东南亚地区的经济赋能使命。

With cross-platform monitoring, a common problem is the difficulty in getting comprehensive and in-depth views on metrics, making it tough to see the big picture. Read to find out how the Data Tech…

With the size of our app growing to include more features, Grab recognised it as a potential hurdle for new users with small storage capacities or restricted Internet bandwidth. Read to find out more…

In the domain of data processing, data analysts run their ad hoc queries on the data lake. The lake serves as an interface between our analytics and production environment, preventing downstream queries from impacting upstream data ingestion pipelines. To ensure efficient data processing in the data lake, choosing appropriate storage formats is crucial.

The Grab superapp offers a comprehensive array of services from ride-hailing and food delivery to financial services. This creates multifaceted user journeys, traversing homepages, product pages, checkouts, and interactions with diverse content, including advertisements and promo codes.

In this digital age, companies collect multitudes of data that enable the tracking of business metrics and performance. Over the years, data analytics tools for data storage and processing have evolved from the days of Excel sheets and macros to more advanced Map Reduce model tools like Spark, Hadoop, and Hive. This evolution has allowed companies, including Grab, to perform modern analytics on the data ingested into the Data Lake, empowering them to make better data-driven business decisions. This form of data will be referenced within this document as “Offline Data”.

With innovations in stream processing technology like Spark and Flink, there is now more interest in unlocking value from streaming data. This form of continuously-generated data in high volume will be referenced within this document as “Online Data”. In the context of Grab, the streaming data is usually materialised as Kafka topics (“Kafka Stream”) as the result of stream processing in its framework. This data is largely unexplored until they are eventually sunk into the Data Lake as Offline Data, part of the data journey (see Figure 1 below). This induces some data latency before the data can be used by data analysts to inform decisions.

Coban - Grab’s real-time data streaming platform - has been operating Kafka on Kubernetes with Strimzi in production for about two years. In a previous article (Zero trust with Kafka), we explained how we leveraged Strimzi to enhance the security of our data streaming offering.

In this article, we are going to describe how we improved the fault tolerance of our initial design, to the point where we no longer need to intervene if a Kafka broker is unexpectedly terminated.