Data Scientist – Credit Risk & Predictive Modeling

Who you’ll be working with

Our Singapore based client is a Device-as-a-Service organisation that is making tech more accessible and sustainable for businesses and individuals. Their mission is to create a more flexible, inclusive, and environmentally friendly purchasing model for consumer electronics across Asia Pacific. They have developed a subscription-based business model for customers to flexibly and conveniently access their favourite tech products, disrupting a $700bn industry!

Job Summary

We are seeking a mid-level Data Scientist with at least four years of experience to join our growing team. This role is ideal for professionals proficient in credit risk modeling, statistical analysis, and machine learning techniques such as regression, bagging, and random forests.

The successful candidate will play a critical role in developing data-driven risk assessment strategies, enhancing predictive modeling frameworks, and optimizing feature engineering for improved decision-making.

The ideal candidate should have a strong portfolio of past projects demonstrating expertise in building and validating credit risk models that drive business impact. Experience with EDA (Exploratory Data Analysis), trend analysis, and model development will be essential for success in this role.

Key Responsibilities

• Work closely with cross-functional teams, including risk management, finance, and product teams, to integrate data science solutions into business operations.
• Present insights and recommendations through visualizations and data storytelling to non-technical stakeholders.
• Perform Exploratory Data Analysis (EDA) and feature engineering to uncover hidden patterns and improve model accuracy.
• Develop and validate credit risk models using techniques such as logistic regression, decision trees, random forests, and boosting algorithms to assess customer creditworthiness and optimize risk scoring.
• Has experience with ensemble methods such as bagging and boosting to enhance predictive power and minimize overfitting in risk assessment models.
• Conduct trend analysis on customer behavior, loan performance, and macroeconomic indicators to refine risk strategies.
• Collaborate with engineering teams to deploy models into production environments and monitor performance over time.
• Continuously research and experiment with new techniques in machine learning, risk modeling, and big data analytics to enhance decision-making processes.

Key Requirements

• 4+ years of experience in data science, machine learning, or risk analytics, with a focus on credit risk modeling.
• Proficiency in statistical modeling techniques such as logistic regression, decision trees, random forests, and boosting algorithms.
• Strong experience in feature engineering, EDA, and data preprocessing for structured and unstructured data.
• Hands-on experience with bagging, boosting, and ensemble learning methods to improve model generalization.
• Advanced proficiency in Python (NumPy, Pandas, Scikit-Learn, XGBoost, TensorFlow) or R for data analysis and model development.
• Solid SQL skills for querying and manipulating large datasets from relational databases.
• Experience working with cloud platforms (specifically AWS) is a plus.
• Strong communication skills with the ability to translate complex data insights into actionable business recommendations.
• A proven track record of delivering end-to-end data science projects in credit risk, including model development, validation, and deployment.

Preferred Qualifications and Experience

• Master’s or Ph.D. in Statistics, Mathematics, Computer Science, Data Science, Economics, or a related field.
• Experience with time series forecasting and anomaly detection for credit risk applications.
• Knowledge of model interpretability techniques such as SHAP, LIME, or others
• Bonus: hands-on experience in deploying models using MLOps practices and monitoring model performance in production.