Data Scientist - Risk Analytics & Modelling

PT Dwi Cermat Indonesia; Kebayoran Baru; On-site; IDR 180,000,000 - 240,000,000; Full time

Job summary

PT Dwi Cermat Indonesia is seeking a data-driven analyst to monitor portfolio health and uncover drivers of risk. You will collaborate with business, product, and engineering teams to translate insights into actionable credit decisions and improvements to the scoring framework.

You will build SQL-based analyses, maintain dashboards, and occasionally evaluate models to support score refinements, while working in a data-rich environment with a strong team of data scientists.

Qualifications

• Fresh Graduate/Bachelor's degree in an analytical or quantitative discipline (e.g. math, statistics, engineering, computer science), however other disciplines will be considered
• Experienced in using statistical computer languages such as Python, SQL, and MS Excel
• Have good communication skills and able to work together in a team
• Excellent problem-solving skills and have the drive to learn and master new technologies and techniques
• Willingness to learn new skills independently and have a strong sense of project ownership
• Not afraid to get your hands dirty exploring data, investigating anomalies, and building SQL-based analyses
• Exposure to credit scoring modelling concepts is a plus.

Responsibilities

• Monitor portfolio risk metrics on a regular basis and proactively flag anomalies or emerging trends
• Perform root cause analysis when risk indicators deteriorate to pinpoint what's driving the change
• Translate findings into concrete recommendations and implement adjustments as needed
• Build and maintain SQL-based features, analyses, and monitoring dashboards to support ongoing risk surveillance
• Perform occasional model evaluation to support credit scoring improvements

Skills

Python

SQL

MS Excel

Analytical thinking

Communication

Teamwork

Education

Bachelor's degree in mathematics/statistics/engineering/computer science

Tools

Jupyter

Dashboards

Job description

We're looking for candidates with strong analytical skills and hands-on experience working with financial datasets. You will be responsible for monitoring portfolio health, performing deep-dive exploration and analysis to identify risk drivers and improvements in our existing framework, and translating findings into actionable credit decisions. You will partner with business, product, and engineering teams to solve some of the most challenging problems in lending while also continuously improving portfolio quality by balancing risk control with growth opportunities. You will be embedded in a fast-paced environment, working within a strong team of data scientists with access to a robust data infrastructure.

Responsibilities

• Monitor portfolio risk metrics on a regular basis and proactively flag anomalies or emerging trends
• Perform root cause analysis when risk indicators deteriorate to pinpoint what's driving the change, such as identifying suspicious behavioral patterns
• Translate findings into concrete recommendations and implement adjustments as needed
• Build and maintain SQL-based features, analyses, and monitoring dashboards to support ongoing risk surveillance
• Perform occasional model evaluation to support credit scoring improvements

Qualifications

• Fresh Graduate/Bachelor's degree in an analytical or quantitative discipline (e.g. math, statistics, engineering, computer science), however other disciplines will be considered
• Experienced in using statistical computer languages such as Python, SQL, and MS Excel
• Have good communication skills and able to work together in a team
• Excellent problem-solving skills and have the drive to learn and master new technologies and techniques
• Willingness to learn new skills independently and have a strong sense of project ownership
• Not afraid to get your hands dirty exploring data, investigating anomalies, and building SQL-based analyses
• Comfortable working with large tabular datasets to detect trends and anomalies, and communicating findings as actionable recommendations.
• Exposure to credit scoring modelling concepts is a plus.