Predictive Analytics Consultant

📋 Description

• • Lead the design, development, and deployment of predictive analytics solutions including Automated Underwriting, Risk Scoring, and Portfolio Monitoring for financial institution clients.
• • Manage and transform large, complex datasets from multiple sources, ensuring data accuracy, cleanliness, and structure for use in predictive modeling and analysis.
• • Perform detailed data wrangling and preprocessing tasks to resolve inconsistencies and prepare data for machine learning and statistical modeling.
• • Implement advanced data transformation techniques such as feature engineering, aggregation, and normalization to optimize input variables for predictive models.
• • Build, test, validate, and monitor predictive models using classification, regression, and clustering algorithms including decision trees, random forests, and neural networks.
• • Optimize model performance through hyperparameter tuning and rigorous evaluation using cross-validation techniques to meet both business and technical requirements.
• • Develop end-to-end analytical solutions from data collection and model training through deployment, ensuring alignment with client objectives like improving credit underwriting and lending strategies.
• • Ensure analytical outputs directly contribute to measurable KPIs tied to credit risk assessment, decision automation, and operational efficiency in lending workflows.
• • Collaborate on the internal development of new data science methodologies to address evolving underwriting needs across consumer lending, banking, and credit union environments.
• • Present complex analytical findings in clear, actionable formats to both internal stakeholders and external clients, translating technical results into strategic insights.
• • Interpret credit bureau data, loan origination system outputs, and core underwriting practices to inform model design and enhance predictive accuracy.
• • Apply deep understanding of decisioning engines in lending contexts to integrate data sources and automate credit risk assessment processes.
• • Contribute to continuous improvement of data science workflows by identifying inefficiencies and implementing best practices for project execution and model monitoring.
• • Utilize Python with Pandas, Scikit-learn, and related libraries for model development, analysis, and automation of analytical tasks.
• • Write complex SQL queries to extract, manipulate, and analyze structured data from relational databases supporting lending operations.
• • Leverage AWS for training, deploying, and managing machine learning models, including integration with MLOps practices for model lifecycle management.
• • Work independently and collaboratively in a fast-paced, remote environment while managing multiple projects and deadlines with precision and attention to detail.
• • Communicate technical concepts effectively to non-technical audiences, including clients and business teams, to drive data-informed decision-making in credit risk contexts.