Risk Data Scientist

Get to know our Team:


Risk team is in charge of protecting Grab Financial ecosystem of consumers, partners and merchants in Southeast Asia against fraudulent behaviours.

Get to know the Role:

• Research internal and external data to identify fraudulent behaviours such as account take-over, credit card fraud, merchant risk, collusion schemes, syndicated fraud attacks as well as money laundering schemes.

• Develop and maintain machine learning behavioural models to detect fraudulent behaviours.

• Use statistics and anomaly detection to recognize fraudulent and abusive behavioural patterns and derive actions such as risk rule writing.

• Optimise systems to achieve optimal conversion rate while keeping financial loss to a minimum.

• Work in close collaboration with product teams to design / optimise fraud / ML prevention systems.

• Act as risk science subject matter expert within the risk team.

• Own risk data, ensure necessary databases are maintained for research and regulatory purposes.

• Perform forensics, deep dives and root cause analysis on various fraud- or business-related matters.

The must haves:

• Problem-solving, positive and constructive attitude is a must.

• Comfort in dealing with ambiguity and operating in a fast-growing environment.

• Excellent verbal and written communication in English and ideally one local SEA language.

• Recognised experience in online payments is a plus.

• A passion for data and insights.

• Advanced data science skills, recognised experience in applied statistics and machine learning / data mining tools such as SQL, R, Python, SAS.

• Advanced knowledge and experience in e-wallet / online payments abuse (account take-over, credit card fraud, merchant/buyer collusion fraud, money laundering...).

• Advanced degree in statistics or related field (e.g. applied mathematics, quantitative economics, computer science, bioinformatics).

• Hands-on experience with fraud detection tools e.g. scoring models and rules engines.

• Structured, factual and data-driven. Ability to deep dive into data and elaborate clear and synthetic insights.

• Meticulous attention to detail and double-checking as a second nature.