Get to know our Team:
The Trust, Identity & Safety (TIS) User Trust team acts as guardians of all our users on Grab. We leverage our rich data-sets to find solutions to problems ranging from safety to fraud. We're a hands on team interested in the end to
end data life-cycle from analyzing the behavior of our consumers, identifying any anomalies to building a detection and prevention modules for any suspicious activities. If you're passionate about solving complex problems with immediate real-world impact, we want you!
Get to know the Role:
As the Data Risk Analyst, you will analyse Grab’s data to develop insights about user behaviours and payment risks. You will translate these insights into recommended actions to combat user and payment fraud.
The day-to-day activities:
- Analyze massive passenger, driver and merchant data to develop insights on user behaviors and/or payment risks.
- Develop and communicate insights and recommended actions to stakeholders to reduce user and payment fraud by contributing towards machine learning models, .rules and other detection systems
- Conduct data investigations and analysis on fraudulent rings that has been identified by stakeholders.
- Identify potential false positive cases and feedback to the Data Science team.
- Work cross functionally on managing risk associated with Grab products, processes, and payment methods
- Work with operations teams in various regions and cities to define risk policy and processes
- Work with business teams to translate requirements and needs to the Tech teams.
- Ensure incentives payouts to drivers and rewards to passengers are appropriately given.
The must haves:
- 3-6 years of experience as a hands-on analyst in a high tech company
- A technical degree in Computer Engineering, Information Technology, Data Sciences, Maths or related fields.
- Strong experience in handling large scale unstructured data. Experience in SQL, as well as ability to learn more advanced data
- Business intelligence experience using tools such as Tableau, Qliksense and Excel.
- Working experience of any of the data analysis tools such as R, Python, SPSS, SAS etc.
- Experience with application of experimentation and statistical techniques (such as hypothesis testing, probability distributions, regression, decision trees etc.)
- Relevant experience on data analysis and machine learning.
- Excellent written and verbal communication skills along with strong training skills.
- Ability to make sound judgement calls independently when presented with difficult decisions, especially when only partial information is available
- Ability to take initiative in a fast-moving environment
Nice to have:
- Proficient in RDBMS such as PostgresQL or MySQL.
- Proficiency in a local SEA language.
- Good understanding of the fraud space with hands-on knowledge of fraud, payments and risk.
