Senior Data Scientist

Roles & Responsibilities

We are living in dynamic times. Technology is reshaping how we live, and we want to use it to redefine how financial services are offered. Digibank is a Grab-Singtel consortium, aimed at enabling the underserved groups to easily access transparent financial services that are embedded in their everyday activities, helping them achieve a better quality of life. We are incredibly excited to build a Digital Bank with the right foundation using data, technology and trust to solve problems and serve customers

Get to know the Role:

• Develop and deploy analytical solutions across a variety of business functions, including, but not limited to: customer acquisition, customer retention, product development, pricing decisions, credit risk, fraud identification and many other business needs within Digibank for both retail and wholesale banking customers
• Manage and own the entire end-to-end lifecycle of building and validating predictive models along with their deployment and maintenance.
• Interface with business, risk & operation teams across the bank to formulate solutions & product changes informed by your findings and business inputs/reality.
• Work independently or in a team to solve complex problem statements.
• The day-to-day activities: Build predictive models using a mix of machine learning and traditional analytics methods.
• Validate models on new datasets, based on in-market performance.
• Engineer predictive features from internal data assets to build refined customer profiles. Identify external data assets to bring into the model mix.
• Track model performance KPIs and improve performance of analytic models developed
• Stay current on cutting edge machine learning tools and approaches.

Must Haves:

• Significant relevant experience (At least 4 years of experience) in building and deploying machine learning and predictive model solutions on large amounts of data.
• Advanced degree preferred: Masters degree in Computer Science, Applied Mathematics, Statistics, Machine Learning, or a related quantitative field.
• Extensive hands-on experience in coding and modelling skills in Spark, Python, R, SQL, Presto, Hive proficiency
• Deep technical and data science expertise, including experience in the following:
• Analytical methods: statistical modeling (e.g., logistic regression, time series, CHAID, PCA), supervised machine learning (e.g., random forests, neural networks), unsupervised learning, design of experiments, segmentation/clustering, text mining, network analysis and graphical modelling, optimization, simulation
• Experience building in-production models, including associated scripting, error handling and documentation
• Understanding of trade-offs between model performance and business needs.
• Strong record of professional accomplishment
• Highly self-driven, demonstrate critical thinking, team player & fast learner
• Work experience and knowledge of more than one domain is a plus - Risk Analytics, Marketing Analytics, Telecom analytics, Retail analytics, Fraud analytics etc.