This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description GAINSCO is seeking a Predictive Analytics Manager to lead the development of advanced models that inform pricing, underwriting, and strategic growth. This role blends technical expertise with business acumen, supporting cross-functional teams and regulatory compliance in a dynamic insurance environment. - Build predictive models for loss cost, retention, lifetime value, and more using internal and external data. - Apply advanced statistical and machine learning techniques (GLMs, GBMs, decision trees, clustering, random forests). - Present insights and recommendations to senior leadership and business stakeholders in a clear, actionable format. - Monitor model performance and implement iterative improvements. - Create documentation for regulatory filings and respond to Insurance Department inquiries. - Collaborate with Product, Actuarial, and Claims teams to align analytics with business goals. Qualifications - Bachelor’s degree required, preferably in Mathematics, Actuarial Science, Risk Management, Economics, Computer Science, Information Management, or Statistics. - 8 or more years of experience in insurance product development, actuarial, or product management within the personal auto insurance industry required. - 5 or more years’ progressive data science experience in designing, developing, evaluating, and deploying predictive modeling, machine learning and advanced analytics required. - Experience with structured and unstructured data analysis is required. - Proficiency with Python and SQL required. Requirements - Understanding of statistical and predictive modeling techniques such as GLMs, machine learning, decision trees, clustering, forests, and neural networks and their application to business decisions. - Proven skills as a business consultant who uses modeling skills to answer business questions and drive profitable growth. - Ability to convey complex topics and results to non-technical audiences. - Ability to adapt quickly to changing timelines. Benefits - Excellent benefits package including medical & dental, vision insurance, life insurance, short-term and long-term disability insurance. - Parental Leave Policy. - 401K + Company Match. - PTO Plan + Paid Company determined Holidays.

• Build and maintain data transformation workflows using dbt • Develop scalable and optimized data models in Snowflake • Partner with business stakeholders to understand requirements and translate them into technical outputs • Collaborate with internal engineers to align with data standards and best practices • Write clean, maintainable SQL transformations with appropriate testing and documentation • Troubleshoot production issues and support ongoing enhancements

• Build and maintain robust data pipelines that power our analytics and business operations • Own our Snowflake and dbt infrastructure—manage data warehouse architecture, optimize performance, and maintain clean, well-documented models • Set up and troubleshoot data connectors across various sources and systems • Deliver quick analytics and dashboards to answer business questions • Unblock yourself and others through collaboration, communication, or getting hands dirty with code • Experiment with new tools and technologies, even if you haven't used them before

• Advance the analytics layer end-to-end: Design, build, and maintain core dbt models that represent the business (e.g. customers, revenue, marketing performance, operations) and keep them production-ready. The means creating the source of truth for the business to operate on. • Define and evolve company metrics: Partner with stakeholders to create clear, consistent metric definitions, and implement them in Omni so teams can self-serve with confidence. • Lead cross-domain initiatives: Deliver high-impact analytics engineering projects that span multiple domains and teams—driving alignment, sequencing work, and shipping outcomes. • Make pragmatic modelling trade-offs: Balance speed, accuracy, and long-term maintainability; set patterns that scale as the company grows. • Raise data quality and trust: Introduce and maintain standards using dbt tests, CI/CD, documentation, and lightweight governance; catch issues early and reduce regressions. • Partner upstream to fix root causes: Work closely with Data Engineering to diagnose data issues, improve source/warehouse design, and keep the warehouse performant and reliable.