Guiding You Door-to-Door via Our Superapp!

Summary

Grab addressed passenger navigation challenges at large Southeast Asian venues such as airports and shopping centers. Satellite signals weaken through concrete and steel, creating GPS inaccuracies that caused the rendezvous distance between passengers and drivers at large venues to exceed twice the average. While introducing Entrances previously mapped over 120,000 green dots to lower rendezvous distances, passengers still struggled to locate specific pickup spots indoors. The company launched Venues, an in-app feature delivering turn-by-turn text and photo directions to designated pickup points. To support this system, operations teams surveyed sites with cameras and scanners to capture landmarks, after which in-house teams masked faces and vehicle license plates.

Context

GPS satellite signals weaken when passing through concrete and steel, causing location inaccuracies inside large buildings or skyscraper districts where rendezvous distances between passengers and waiting cars were more than twice the platform average.

Approach / What changed

Grab introduced the Venues feature, which displays available pickup points in a menu and provides in-app turn-by-turn text and photo directions based on on-ground surveys using cameras, Wi-Fi, and Bluetooth scanners, accompanied by image masking of faces and license plates.

Takeaways

• Rendezvous distance between passengers and drivers at large venues was more than double the Grab average before targeted pickup point interventions.
• The earlier Entrances feature established over 120,000 mapped green dots representing distinct building pickup locations to reduce rendezvous distance.
• Creating the Venues feature required surveying 600 key venues to collect over 3,400 images across more than 1,900 pickup points, requiring over 3,000 man-hours and privacy masking of faces and number plates.

Related reading

• Grab · Aug 1, 2019

  Save Your Place with Grab!

  Grab introduced Saved Places across Southeast Asia to eliminate the friction of repeatedly typing addresses and prevent selection errors between similarly named locations. Data analysis across transport and food orders revealed that consumers consistently visit only five to seven unique locations and order food to one or two addresses. To streamline repeat bookings, cross-functional teams designed a feature allowing users to bookmark locations under custom labels such as Home and Work. Following usability testing and release, more than 14 million users stored nearly 45 million addresses across the platform. Platform metrics also showed that while office destinations clustered in central districts across major cities, residential distributions varied significantly between markets like Singapore and Jakarta.

  Summit Saurav

• Grab · Sep 11, 2018

  Journey of a Tourist via Grab

  Grab analyzed platform ride data from millions of tourist passengers representing over 150 countries visiting Singapore. Over 60% of these tourist riders originated from Southeast Asia, while non-regional visitors mainly came from China, the United States, and India. Seasonal demand revealed a trimodal distribution for tropical travelers aligning with holiday periods, contrasting with a September-to-January peak for visitors escaping winter in four-season climates. Airport trips showed that nearly 90% of tourist passengers headed directly to hotels, concentrated heavily in central areas like Orchard, Bugis, Downtown Core, and Kallang. Additional key destinations included major shopping districts, iconic dining locations like Newton Food Centre and Chijmes, and medical centers, which saw tourist ride volume grow over 500% between 2015 and 2017.

  Lara PuReum Yim

• Grab · Oct 20, 2017

  The Data and Science Behind GrabShare Part I: Verifying Potential and Developing the Algorithm

  Expanding from point-to-point dispatch services to dynamic carpooling requires matching independent passenger requests traveling in similar directions without causing unacceptable delays. Grab evaluated the feasibility of its GrabShare service by analyzing historical trip data with DBSCAN clustering on coordinates projected into a Universal Transverse Mercator system. This analysis demonstrated that 35% to 46% of rides across typical daytime windows fell into tight geographic clusters with near-identical pickup and drop-off coordinates. The resulting matching framework adapts the baseline dispatch flow by searching for in-transit drivers and enforcing real-time seat reservation constraints. Route assignment decisions subsequently evaluate detour times, trip angles, and expected arrival times to ensure driver utilization improves while total driving distance decreases.

  Tang Muchen

• Grab · Mar 7, 2019

  Recipe for Building a Widget: How We Helped to “Peak-Shift” Demand by Helping Passengers Understand Travel Trends

  Transport demand spikes during regular commuting hours often outpace driver availability, resulting in passenger wait times and fare surges. To mitigate these imbalances, Grab created the Travel Trends Widget for its mobile feed to redistribute ride requests toward off-peak windows. The widget uses machine learning forecasting to present historical supply-demand patterns alongside pricing trends for the upcoming two hours. To handle anticipated high query rates across millions of database entries, engineers periodically load precomputed trend data into an in-memory data structure rather than querying the database per request. The feature rolled out to feeds in Singapore and Jakarta within four weeks of initial development.

  Lara PuReum Yim