At Rappi, like more and more leading tech companies, decisions are now taken based on data. Experimentation is the gold standard of impact evaluation and, as such, it allows making correct decisions throughout the product development process.
David Zarruk, head of data science for Rappi Bank in Latin America, discusses how experimentation serves as the backbone for decision-making at Rappi, a marketplace connecting customers, stores, merchants, and couriers in Latin America.
Rappi, with over 3,000 employees across Latin America and over 11 million active customers monthly and operations in nine countries, faces various challenges across its business lines, such as customer segmentation, delivery optimization, recommendation systems, and fraud detection. Rappi supports various lines of business including grocery, pharmacy, restaurant deliveries, and fintech services.
Zarruk explains how Rappi employs experimentation, particularly A/B testing, to measure the impact of new features and algorithms, ensuring informed decision-making. He highlights the importance of experimentation in evaluating online metrics accurately and discusses the ease and low cost of experimentation in a data-driven company like Rappi.
Zarruk also illustrates a specific example of experimentation in restaurant recommendations, emphasizing the trade-off between exploration and exploitation. He concludes by discussing the challenges of implementing a culture of experimentation, including potential slowdowns in product development and the need for team members with statistical expertise. Utilizing Split for experimentation, was easy due to simple integration and configuration.
Switch It On With Split
The Split Feature Data Platform™ gives you the confidence to move fast without breaking things. Set up feature flags and safely deploy to production, controlling who sees which features and when. Connect every flag to contextual data, so you can know if your features are making things better or worse and act without hesitation. Effortlessly conduct feature experiments like A/B tests without slowing down. Whether you’re looking to increase your releases, to decrease your MTTR, or to ignite your dev team without burning them out–Split is both a feature management platform and partnership to revolutionize the way the work gets done. Schedule a demo or explore our feature flag solution at your own pace to learn more.