In this role, you will be an integral player within the Data Science team based in Singapore. You will take the wheel in overseeing building, evaluating, and monitoring credit risk models for a variety of consumer and merchant lending products GTF offers in Indonesia. Your responsibilities will include enhancing our credit risk models through heavy feature engineering of data as well as data purchased from third-party data vendors, and ensuring that they are stable and scalable in the production environment. Most importantly, your efforts will work to bring wider financial inclusion to more people in the region and beyond.
Own end-to-end modeling modeling initiatives and business outcomes / metrics. Work with the business/product team in defining, prototyping, and implementing data science models and other supporting DS initiatives. Recruit, mentor, and develop a high-performing data science team, fostering a culture of collaboration and innovation. Oversee the development of consumer credit risk models and statistical analyses to optimize decision-making and business outcomes.
What you will need Bachelor degree or above in science and engineering related majors such as statistics, mathematics, physics, computer science, etc. At least 4-5 years of hands-on experience in building, evaluating, and monitoring risk models. Excellent understanding of machine learning techniques and algorithms Comfortable using Python, SQL, and UNIX Shell Understand business concerns and formulate them as technical problems that can be solved using data and math/stats/ML Self-driven and entrepreneurial with a strong sense of ownership, and thrive in a fast-paced environment Good communication skills and ability to present technical concepts to a non-technical audience Able to write model documentation clearly and concisely and support recommendations with research and data
About the team :
Our team leverages big data from the Financial universe, as well as external data, to build various predictive models to support the risk strategy team in real-time credit underwriting and management of the customer lifecycle. We use models to predict the customer’s probability to default on our Cicil (BNPL) and Pinjam (cash loans) products, and use this score to risk-rank our customers. As our model scores are key inputs to risk decisioning (e.g. approval/rejection of loans, credit limit adjustments), we are also able to see the direct impact of our models on the business and our customers. We are a growing team and are constantly looking for opportunities to use data science to enhance our credit and fraud risk management capabilities. We are focused on growth and efficiency. We are all about open knowledge sharing and self-improvement. We believe that “Data Science is a team sport.
