全职 Machine Learning Engineer 工作, 薪水 up to MYR 22,000, PERSOL Workforce Solutions Malaysia WP Kuala Lumpur 公司招聘中 - Ricebowl

About the role:

The Data Scientist leads analytical workstreams across end‑to‑end credit card portfolio optimisation projects, translating large‑scale transaction and customer data into actionable insights and data‑driven strategies. By applying advanced analytics and machine learning, the Data Scientist will help client’s make smarter decisions across the card lifecycle and delivers impact through modelling, experimentation, and performance measurement, enabling payment volume growth, profitability improvement, and risk optimisation for client’s card portfolio.

Qualifications

• 5–8+ years of experience in data science or advanced analytics, preferably within financial services or retail banking

• Master’s degree or higher in Data Science, Statistics, Computer Science, Mathematics, or a related quantitative field

• Demonstrated experience in credit card portfolio analytics, customer lifecycle modelling, or marketing optimization

• Advanced skills in analytics and statistical modeling (e.g., Regression, Clustering, Classification)

• Experience working with large datasets using SQL, Hive, Hadoop, Spark, Python or cloud-based analytics environments for data manipulation and analysis

• Solid grounding in statistical inference, experimental design, causal inference, and time-series analysis

• Hands-on experience with supervised and unsupervised machine learning techniques

• Exposure to fraud, credit risk, authorization, or payment success optimization

• Experience translating analytics into business strategy and client recommendations

• Strong communication skills with the ability to engage non-technical stakeholders

• Experience in consulting or client-facing analytics roles

Key Responsibilities:

• Own analytics workstreams for card portfolio optimisation across acquisition, activation, usage, retention, payment success, fraud, and credit risk

• Build and deploy statistical models and machine learning solutions to identify growth, efficiency, and risk-mitigation opportunities

• Conduct customer segmentation, lifecycle modelling, propensity modelling, and uplift analysis to inform portfolio strategies

• Design and evaluate test-and-learn frameworks, including control groups, A/B testing, and causal inference approaches

• Analyse large-scale transaction, customer, and behavioural datasets (e.g. issuer data, network data) to generate insights

• Produce data sets for predictive modeling by parsing and aggregating incomplete, unstructured data sources.

• Annual Leave
• Medical and Hospitalisation Leave
• EPF
• SOCSO
• EIS
• Medical Insurance
• 5 Working Days