Data Scientist

Responsibilities

• Responsible for developing a robust machine learning model for credit scoring that is highly scalable and compliant with BASEL II guidelines.
• Re-evaluate credit risk model performance on a periodic basis for retraining using statistics such as probability of default, confusion matrix, f1&f2 score, Lorenz Curve, Kolmogorov–Smirnov, GINI and AUC.
• Develop innovative data science methodologies to manage credit risk of the lending portfolio.
• Familiar techniques for implementing and automating continuous integration (CI), continuous delivery (CD), and continuous training (CT) for machine learning (ML) systems.
• Synthesize requirements from stakeholders, develop innovative and effective approaches in collaboration with data engineers, Machine learning engineers, product managers, and technical teams.
• Contribute to core advanced analytics and machine learning platforms and tools by research, discover new methodologies and new data feeds to support credit decisioning and other key business processes.
• Identifies what data is available and relevant, including internal and external data sources, leveraging new data collection processes; Work with machine learning and Data Engineering teams to discover new data feeds with predictive power to derive borrower credit worthiness.
• Understand data sources, conduct data discovery, apply complex techniques to produce features for automation using a hypothesis driven approach.
• Implementing bleeding edge academic research into pragmatic modelling solutions.

Qualifications

• Bachelor’s degree in Statistics, Operations Research, Mathematics, Physics, Computer Science, or Engineering, or in a related field, a Master’s degree is will be an additional advantage.
• Experience in all or some of the following scripting languages : SQL, Python, R, SAS, Java, C++, SPSS, MATLAB.
• Minimum 4-6 years’ experience in propensity modelling.
• Cloud experience is a plus.

Seniority level

Associate

Employment type

Full-time

Job function

Other

Location

Kuala Lumpur, Federal Territory of Kuala Lumpur, Malaysia

#J-18808-Ljbffr