Director, Decision Science

At TreviPay, we believe loyalty begins at the payment. Thousands of sellers use our global B2B payments and invoicing network to provide choice and convenience to buyers, open new markets and automate accounts receivables. With integrations to top eCommerce and ERP solutions and flexible trade credit options, TreviPay brings 40 years of experience serving leaders in manufacturing, retail and transportation.

Every day, TreviPay employees are challenged and empowered in a supportive, collaborative, entrepreneurial environment.

Step into a high-impact role where your analytics shape real business decisions. At TreviPay, we’re looking for a Director of Decision Science who is a data-driven risk expert who thrives on turning complex data into actionable insights. In this role, you’ll influence credit and fraud strategy, pricing, and profitability—partnering cross-functionally to drive smarter decisions and fuel growth across our global fintech platform.

Responsibilities

Develop statistical models and other types of predictive models as appropriate to improve our risk position (both fraud and credit), pricing strategies, and profitability.

Support the creation of a Model Development Framework, documenting the approach the Risk Management team will use so that we incorporate a consistent, stable modeling process at Trevipay

Monitor the results of risk and pricing strategies by evaluating performance relative to expectations.

Analyze customer usage, competitor pricing and market trends to increase market share and profitability.

Access, cleanse, and analyze relevant internal and external data to support the creation, monitoring, and improvement of effective B2B credit risk management and pricing strategy techniques across new account origination and existing account management.

Develop/enhance the Portfolio Risk Assessment reporting package detailing Key Risk Indicators, trends, and projections for presentation to the executive leadership team.

Deliver and communicate high quality data-driven analyses to key stakeholders and senior management that provide key insights leading to actionable results.

Conduct data exploration, data validation, and data audits to identify and address data quality issues and recommend improvements.

Support Engineering and Product teams with resolution of roadblocks and interdependencies.

Support internal/external Data Scientists with subject matter expertise and clean, actionable datasets for the growth of predictive and advanced analytical capabilities.

Requirements

Bachelor’s Degree Required

Minimum 10+ years of proven work experience in a highly analytical environment performing complex business analyses, generating data-driven insights and presenting findings to leadership and other stakeholders.

Strong knowledge of B2B credit and/or Business Banking credit risk, pricing, and profitability principles

Ability to deal with ambiguity and be flexible enough to shift workload in accordance with changing priorities.

Ability to extract, cleanse, merge and analyze data from varied internal and external sources.

Strong analytical and data simulation skills including SAS, Python, MS Excel, Tableau/Sisense, or similar analytical and reporting/data visualization packages.

Strong presentation skills and proficiency in MS Word and PowerPoint

Experience in analyzing segments of data or utilizing tools to identify and explain patterns, trends and/or process improvements

Ability to create clear, concise graphs, charts, reports and presentations summarizing analytical results and justifying suggested improvements

High performing contributor with ability to collaborate cross-functionally with management, product, technology, compliance and enterprise risk

The ability to multitask in a fast-paced environment

Strong communication skills, both verbal and written

Preferred Qualifications

Bachelor’s or Master’s Degree in Statistics, Mathematics or similar quantitative field of study

Strong knowledge of B2B and/or Business Banking credit product pricing and profitability principles

Statistical modeling experience (logistic regression, machine learning, SVM, and more)

Prior leadership/management experience