Get to Know the Team
The Grab Financial Risk & Compliance team serves as the guardians of risk and compliance for all the financial products within Grab. Our data science team uses our datasets to uncover solutions to multiple problems such as predicting payment risk with sequence-based models, detecting money laundering with graph algorithms, and automating ID verification using image recognition. Additionally, we lead research to outpace latest fraud tactics, contributing to the development of secure products.
Get to Know the Role
In this role, you'll be at the forefront of fighting fraud by analyzing transactional data, developing and deploying machine learning models, and collaborating with teams to ensure seamless integration of fraud detection systems. You'll help keep our financial products safe and trustworthy. You will report to a Data Science Manager. This role is based in Singapore and is a hybrid role
The Critical Tasks You will Perform
- Analyze transactional data to identify patterns and trends in fraudulent activities using statistical and machine learning techniques.
- Work with partners to translate their needs into analytical requirements and comprehend the operational impact of fraud.
- Develop and test hypotheses about fraudulent behavior, designing experiments and conducting analyses.
- Create, train, and deploy scalable machine learning models for transaction monitoring and real-time fraud detection.
- Evaluate the performance of models, ensuring they are highly accurate and efficient.
- Maintain fraud detection solutions in production, regularly monitoring and improving their effectiveness.
- Collaborate with data scientists, engineers, product managers, and financial operations teams to integrate systems into Grab's platform.
What Essential Skills You Will Need
- You have at least 2 years experience with statistical analysis and machine learning to understand and detect patterns of fraud.
- Skills in formulating hypotheses, designing experiments, and validating findings.
- Proficiency in creating, training, and deploying machine learning models for fraud detection.
- Knowledge of using appropriate metrics and datasets to evaluate model performance.
- Expertise in deploying and maintaining machine learning models in a production environment.
- Ability to work with data scientists, engineers, product managers, and financial operations teams.
- Strong skills in Python and SQL. Familiarity with numeric libraries, containers, and modular software design.
- Experience with machine learning libraries like Tensorflow, Pytorch, XGBoost, and Sklearn.
- Understanding of DNN architectures, such as graph neural networks and diffusion models.
- An approach to staying updated with new research and advancements in relevant fields.