Skill diminta
PyTorchPythonSQLScikit-learnTensorFlow
Gaji pasar untuk posisi ini
Median Rp8,5 jt/bulan · rentang umum Rp7,7 jt – Rp9 jt
Berdasarkan 32 lowongan Data Science se-Indonesia (semua level).
Lihat data gaji selengkapnya →Deskripsi
Tanggung Jawab
- Develop, train, validate, and optimize machine learning models for alternative credit scoring and risk assessment.
- Analyze alternative data sources to identify relevant variables, patterns, and predictive signals for credit risk evaluation.
- Perform data exploration, feature engineering, and statistical analysis to improve model accuracy and predictive performance.
- Build and maintain data processing workflows to support model development, validation, and deployment.
- Evaluate model performance using appropriate statistical metrics and conduct ongoing model monitoring and improvement.
- Ensure data quality, completeness, consistency, and reliability across various alternative data sources.
- Translate complex analytical findings into actionable insights and recommendations for business and risk decision-making.
- Collaborate with Product, Business, Risk, and Engineering teams to translate business requirements into data-driven solutions.
- Prepare model documentation, validation reports, and analytical reports to support internal reviews, audits, and regulatory requirements.
- Conduct research and experimentation on new modeling techniques, alternative data variables, and credit scoring methodologies
Kualifikasi
Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, Statistics, Mathematics, Software Engineering, or a related field.
- Strong programming skills in Python, particularly for data analysis and machine learning.
- Strong understanding of statistical modeling, machine learning algorithms, predictive analytics, and model evaluation techniques.
Hands-on experience developing, training, and validating machine learning models, rather than solely implementing pre-built or off-the-shelf models.
- Experience with machine learning libraries such as XGBoost, Scikit-learn, TensorFlow, or PyTorch.
- Proficiency in SQL and experience working with large or complex datasets.
- Experience in data preprocessing, feature engineering, exploratory data analysis, and model optimization.