Data Scientist

pave; Los Altos (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Pave is seeking a data scientist to build and optimize cashflow-driven credit risk models in the US fintech space. You will design, evaluate, and productionize models that demonstrate the impact of cashflow scores and attributes on approvals and defaults, collaborating with data engineers and stakeholders.

Applicants should have strong data science skills, experience with scikit-learn and XGBoost, and a deep understanding of US credit risk practices.

Qualifications

• Strong analytical and data exploratory skills and the ability to translate data into actionable insights.
• Experience from data analysis to building high-performing ML models, including feature engineering.

Responsibilities

• Develop and maintain models (ML-based or heuristic) to enhance product offerings.
• Analyze the impact of Pave scores and attributes on customer performance metrics, aiming to increase approvals and reduce defaults.
• Design, implement, and evaluate experiments to test new attributes and models.
• Collaborate with data engineers to deploy models, monitor performance, and update for accuracy.
• Communicate findings and recommendations to stakeholders through reports, dashboards, and presentations.
• Stay current with advances in data science, AI/ML, and credit risk analytics tools and techniques.
• Translate fair lending considerations into model attributes and analyses for credit risk.

Skills

Data analysis

ML modeling

Experiment design

Stakeholder communication

Tools

scikit-learn

XGBoost

Job description

What We Do

Pavefi.com helps consumer and SMB credit risk teams increase approvals through AI-powered cashflow analytics.

100 million+ US consumers and businesses are financially underserved, simply because their data is not recognized by the traditional financial system.

We solve this by transforming transaction data, loan performance outcomes, and credit reports into Cashflow-driven Attributes and Scores, enabling increased financial access to new customer segments without increasing risk.

Our mission is to build a future where every person and business has access to equitable credit solutions by creating a new standard of Cashflow-driven Analytics.

Pave is backed by Better Tomorrow, Bessemer, 8VC, and other top funds and angels from Coinbase, Chime, SoFi, CashApp, and Plaid.

The Role

Reporting directly to the Director of Data Science, you will play a crucial role in driving customer adoption by producing models that demonstrate the impact of our cashflow scores and attributes on customers’ bottom lines. Your analytical skills, coupled with experience in building highly-performing statistical models and knowledge of credit risk in the US, will be instrumental in improving our data products and in influencing our product roadmap.

Responsibilities

• Develop and maintain models (whether ML-based or heuristics-based) to enhance our product offerings.

• Analyze the impact of Pave’s scores and attributes on customer performance metrics, particularly focusing on increasing approvals and reducing defaults.

• Design, implement, and evaluate experiments to test the effectiveness of new attributes and models.

• Collaborate with data engineers to put your models in production, monitor their performance and conduct regular updates to maintain their accuracy.

• Communicate findings and recommendations to stakeholders through clear, concise reports, dashboards and presentations.

• Stay up-to-date with industry best practices and advancements in data science, AI and ML, and credit risk analytics tools, and technologies.

• Help ensure all models, attributes, and analyses are compliant with fair lending practices, translating these considerations into the attributes and analyses we conduct for credit risk.

Requirements

• Strong analytical and data exploratory skills with the ability to ask the right questions, interpret data and provide actionable insights.

• Demonstrated experience of going from data analysis to building highly performing ML models, including feature engineering and measuring performance.

• Solid understanding of machine learning libraries like scikit-learn, and tree ensemble packages like XGBoost.

• Strong problem-solving skills and a detail-oriented mindset.

• Ability to work independently and collaboratively in a team environment.

• Ability to clearly communicate findings and insights to both technical and non-technical stakeholders, including external partners and customers.

• Knowledge and experience building credit risk models, with an understanding of credit risk in the US.

• Work experience in US fintech or in the financial industry.