Data Scientist – Fraud Analytics & Machine Learning

IntraEdge; Hyderabad; On-site; INR 2,600,000 - 3,800,000; Full time

Job summary

IntraEdge invites an experienced Data Scientist to lead fraud analytics and ML model development in a regulated industry. You will build, validate, and productionize models aligned with MRMV governance while collaborating with fraud strategy, risk, and compliance teams.

The role requires 6+ years in data science, strong Python/SQL, and a track record of deploying multiple models end-to-end in production.

Qualifications

• 6+ years of experience in data science and fraud analytics.
• Proven track record of deploying 5+ ML models in industry.
• Experience with MRMV and regulated environments.
• Strong collaboration with business, risk, and compliance teams.
• Ability to translate analytical concepts into business recommendations.

Responsibilities

• Design, develop, validate, and deploy ML models to solve fraud problems.
• Demonstrate experience deploying at least 5 ML models in an industry setting.
• Develop predictive models for fraud detection, risk assessment, and transaction monitoring.
• Perform feature engineering, model selection, and hyperparameter tuning.
• Monitor model performance and governance; optimize for accuracy and cost.

Skills

Machine Learning

Fraud Analytics

Fraud Strategy

Model Development

MRMV

Python

SQL

Feature Engineering

Model Deployment

Production ML

Education

Bachelor's or Master's in Computer Science/Data Science/Statistics/Mathematics/Engineering

Tools

Python

SQL

NumPy

Scikit-learn

XGBoost

LightGBM

Jupyter

Git

Job description

Job Title: Data Scientist – Fraud Analytics & Machine Learning

Experience: 6+ Years

Employment Type: Full-Time

Job Summary

We are seeking an experienced Data Scientist with strong expertise in Machine Learning, Fraud Analytics, Fraud Strategy, and Model Development to join our data science team.

The ideal candidate will have a proven track record of building and deploying multiple machine learning models in an industry environment, with hands-on experience taking models from experimentation through production. Experience working within highly regulated industries and navigating Model Risk Management and Validation (MRMV) processes is highly desirable.

The candidate will work closely with business, fraud strategy, data engineering, technology, risk, and model governance teams to develop data-driven solutions that identify and prevent fraudulent activities while maintaining strong model governance and regulatory compliance.

Key Responsibilities

• Design, develop, validate, and deploy machine learning models to solve complex business problems.
• Demonstrate experience building and deploying at least 5 ML models in an industry setting.
• Develop predictive models for fraud detection, risk assessment, transaction monitoring, and anomaly detection.
• Perform feature engineering, model selection, hyperparameter tuning, and model optimization.
• Evaluate model performance using appropriate statistical and machine learning metrics.
• Translate analytical findings into actionable business recommendations.
• Develop advanced analytics and machine learning solutions to identify fraudulent transactions and suspicious behavior.
• Analyze transaction, customer, behavioral, and historical data to identify fraud patterns.
• Develop fraud detection strategies using statistical and machine learning techniques.
• Identify emerging fraud trends and recommend appropriate detection strategies.
• Work with Fraud Strategy teams to translate business rules and fraud patterns into analytical models.
• Optimize fraud models to balance fraud detection, false positives, customer experience, and operational costs.
• Support development of real-time and batch fraud detection solutions.
• Partner with Fraud Strategy and Risk teams to understand business objectives and fraud challenges.
• Analyze existing fraud strategies and identify opportunities for improvement.
• Develop data-driven recommendations to enhance fraud detection and prevention.
• Evaluate the effectiveness of existing fraud rules and machine learning models.
• Support champion/challenger strategies and model performance comparisons.
• Monitor fraud trends and recommend changes to strategies based on emerging patterns.
• Take ML models through the complete lifecycle from development to production deployment.
• Collaborate with Data Engineers and ML Engineers to productionize models.
• Develop scalable model scoring and inference solutions.
• Monitor deployed models and identify performance degradation.
• Participate in model retraining and enhancement initiatives.
• Work within established Model Risk Management and Validation (MRMV) frameworks.
• Prepare documentation required for model governance and validation.
• Partner with Model Risk, Validation, Risk Management, and Compliance teams.
• Support model validation and independent review activities.
• Address model validation findings and implement remediation plans.
• Performance metrics
• Limitations
• Monitoring methodology
• Ensure models meet organizational risk and governance standards.

Regulated Industry Experience

• Work effectively within highly regulated environments.
• Ensure analytical solutions comply with applicable regulatory and organizational requirements.
• Support audit and regulatory reviews related to machine learning models.
• Maintain strong documentation and traceability throughout the model lifecycle.
• Understand the importance of explainability, transparency, fairness, and model risk management.

Data Analysis & Feature Engineering

• Analyze large and complex datasets to identify patterns and relationships.
• Perform exploratory data analysis and statistical analysis.
• Develop meaningful features for fraud and risk models.
• Handle missing data, outliers, class imbalance, and noisy datasets.
• Work with structured and transactional data.
• Perform feature selection and dimensionality reduction where appropriate.

Model Performance & Monitoring

• Define and track appropriate model performance metrics.
• Monitor model stability and predictive performance in production.
• Analyze model drift and changes in fraud patterns.
• Develop model monitoring strategies and performance reports.
• Identify opportunities for model recalibration and enhancement.

Cross-Functional Collaboration

Collaborate with:

• Fraud Strategy Teams
• Fraud Operations
• Technology
• Product Management
• Compliance and Audit

Translate complex analytical concepts into clear business recommendations for technical and non-technical stakeholders.

Required Technical Skills

• Strong understanding of machine learning algorithms and methodologies.
• Experience with:
• Classification
• Regression
• Anomaly Detection
• Decision Trees
• Experience with model selection and hyperparameter optimization.
• Strong understanding of model evaluation and validation techniques.

Strong experience in one or more:

• Transaction Monitoring
• Anomaly Detection

Programming

• Strong proficiency in Python.
• Experience with:
• NumPy
• Scikit-learn
• XGBoost / LightGBM
• Strong SQL skills for data extraction and analysis.

Statistical & Analytical Skills

• Strong foundation in statistics and probability.
• Hypothesis testing.
• Regression analysis.
• Statistical modeling.
• Sampling techniques.
• Understanding of imbalanced datasets and appropriate evaluation techniques.
• Hands-on experience with Model Risk Management and Validation (MRMV).
• Understanding of model lifecycle governance.
• Model documentation and validation processes.
• Experience working with governance and compliance teams.

Experience working with appropriate ML and fraud analytics metrics such as:

• Precision
• Recall
• F1 Score
• ROC-AUC
• PR-AUC
• Confusion Matrix
• False Positive Rate
• False Negative Rate
• KS Statistic
• Population Stability Index (PSI)
• Model Stability Metrics

Understanding the business impact of these metrics in fraud detection environments is highly desirable.

• SQL
• Python
• NumPy
• Scikit-learn
• XGBoost
• LightGBM
• Jupyter
• Git

Experience with cloud platforms such as AWS, Azure, or GCP is a plus.

Preferred Qualifications

• Experience in Banking, Financial Services, FinTech, Payments, or Insurance.
• Strong experience with fraud analytics and fraud modeling.
• Experience with payment transaction data.
• Experience with large-scale transactional datasets.
• Exposure to MLOps and production ML deployment.
• Experience with model monitoring and model drift detection.
• Experience working with Model Risk Management, Model Validation, Risk, and Compliance teams.
• Knowledge of explainable AI and responsible AI practices.
• Master's degree in Data Science, Statistics, Mathematics, Computer Science, Engineering, or a related quantitative field is preferred.
• Production-ready machine learning models.
• Fraud detection and prevention models.
• Fraud analytics and strategy recommendations.
• Feature engineering frameworks and analytical datasets.
• Model validation and governance documentation.
• Model performance and monitoring reports.
• Data-driven recommendations for improving fraud detection.
• Continuous enhancements to fraud models and strategies.

Soft Skills

• Strong analytical and problem-solving skills.
• Excellent communication and stakeholder management abilities.
• Ability to explain complex ML concepts to business and risk stakeholders.
• Strong attention to detail and documentation skills.
• Ability to work effectively in cross-functional teams.
• Strong understanding of business impact and customer experience.
• Ability to operate effectively in highly regulated environments.
• Strong ownership and ability to work independently.

Education & Experience

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or a related quantitative discipline.
• 6+ years of professional experience in Data Science, Machine Learning, Risk Analytics, Fraud Analytics, or a related field.
• Proven experience building and deploying 5+ machine learning models in an industry environment.
• Demonstrated experience working with Fraud Analytics / Fraud Strategy / Fraud Modeling.
• Experience navigating MRMV / Model Risk Management and Validation processes in a highly regulated industry.