Credible · posted · checked
Data Scientist
AWSPythonSnowflakeSQLRemote · United StatesMid-level
Who can apply
Remote · United States
Location: Remote, United States
Who is Credible?
Credible is a leading U.S. consumer finance marketplace, transforming the way consumers access and compare financial products. We operate at a consumer and enterprise level. On the consumer side, we help millions of people make smarter financial decisions by comparing personalized, pre-qualified offers across student loans, personal loans, mortgages, credit cards, and insurance — all without impacting their credit score. On the enterprise side, we power financial product comparison and distribution through deep integrations and partnerships with lenders, insurance carriers, and financial institutions, as well as providing marketplace technology and capabilities to third-party partners and distribution channels.
About the role
Our Business Intelligence and Analytics team is seeking to grow the company’s Data Science and Machine Learning capabilities across several facets of our business. We are seeking a seasoned Data Scientist to lead this transformative step change function and nurture its growth across several focus areas. You will drive tactical and strategic execution of several data science projects and manage their entire lifecycle.
You will:
Drive the long-term statistical modeling and machine learning vision of the company.
Conducting exploratory data analysis (EDA) prior to model development
Performing feasibility assessments (POCs) for proposed ML solutions
Monitoring and diagnosing model performance issues, including drift and degradation
Researching and evaluating additional use cases for existing models
Supporting ad hoc ML-related analytics requests from stakeholders and senior data scientists
Conduct analysis to develop and improve our product recommendation and user classification systems. Use this understanding to help optimize our adaptive user experience, cross selling initiatives, and retargeting efforts.
Design, prototype, and implement models across several domains. Manage each part of a project’s life cycle, including ad-hoc exploration, preparation of training data, model development, and production deployment.