Volunteer: Data Scientist — Refine Student and Loan Risk Scoring Model

About the Role

This volunteer opportunity with Taproot Foundation supports the Pay Your Tuition Foundation (PYT) in refining an existing student and loan-risk scoring model. The model is being developed with AI, but its score definitions, variables, assumptions, formulas, weights, and thresholds require review by an experienced data scientist.

The volunteer will help define what the proposed “AI risk score” and “loan risk score” should measure, determine which student and education-related data should influence the scores, and refine the scoring methodology. Factors may include tuition, scholarships, grants, remaining net cost, the student’s circumstances, selected school or program, and comparable educational options.

The refined model will support human decision-making, ensuring more consistent, transparent, and evidence-informed decisions for students facing last-mile education funding gaps. The model will not automatically approve or deny students but will help PYT evaluate funding options while clearly explaining the reasoning and limitations behind each score.

Responsibilities

• Define what the “AI risk score” and “loan risk score” should measure.
• Determine which student and education-related data should influence the scores (e.g., tuition, scholarships, grants, remaining net cost, student circumstances, selected school or program, and comparable educational options).
• Refine the scoring methodology, including variables, assumptions, formulas, weights, and thresholds.
• Test the model using realistic sample cases, including Laurens’s master’s-degree example, to identify inaccurate, unfair, biased, or misleading results.
• Deliver a model assessment, refined scoring methodology, test-case workbook, data dictionary, fairness and sensitivity review, and documentation of limitations and confidence levels.
• Provide recommendations for future data collection and clear implementation requirements for integration with PYT’s systems.
• Document missing information or data limitations rather than filling gaps with unsupported assumptions.

Deliverables

• Model assessment and refined scoring methodology.
• Test-case workbook with realistic sample evaluations.
• Data dictionary outlining variables and definitions.
• Fairness and sensitivity review of the model.
• Documentation of limitations, confidence levels, and assumptions.
• Recommendations for future data collection.
• Clear implementation requirements for integration with PYT’s website, Salesforce, NetSuite, and intake workflows.

Support Provided

• Access to the current model, formulas, prompts, variables, assumptions, sample outputs, and available historical data.
• A designated primary project contact and scheduled regular working sessions.
• Leadership availability to answer questions and approve key decisions.

About Pay Your Tuition Foundation

At PYT, we empower underserved communities through innovative financial solutions, striving to make higher education accessible and sustainable. We address the significant funding gaps that hinder low- to moderate-income undergraduate students from starting, staying in, and completing their degrees—financial obstacles account for 50% of the reasons why low-income students fail to complete their degrees.

Our vision is to reshape the socioeconomic landscape by ensuring equitable access to education. Through our Student Loanership product—a unique blend of loan and scholarship—we connect families and banks to groundbreaking financing solutions. By harnessing technology and data, we bridge the higher education funding gap while championing student advocacy, financial interests, and overall well-being.