Happy Money is looking to build machine learning models that directly drive customer acquisition and lending decisions to fuel the company's rapid growth and scale responsibly.
Requirements
- Proven experience with model calibration techniques
- Expert knowledge of Python/R and SQL for data manipulation, statistical analysis, and machine learning
- Experience with AWS technical stack and data infrastructure (Spark, Hive, Hadoop, EMR, or similar distributed computing frameworks)
- Deep knowledge of statistics, machine learning (logistic regression, ensemble methods, clustering), and optimization techniques
Responsibilities
- Build machine learning models for prescreen direct mail campaign targeting; your models will directly impact customer acquisition and lending decisions
- Perform rigorous model calibration to ensure predicted probabilities accurately reflect actual outcomes and drive reliable business decisions
- Design, implement, and deploy innovative data science solutions to bring data-driven prescreen strategies to life at scale
- Collaborate cross-functionally with Marketing, Risk Analytics, Product, and Engineering teams to translate analytical insights into executable strategies
- Monitor and optimize campaign performance metrics (response rates, conversion rates, approval rates, ROI) with continuous improvement
Other
- 4+ years of business experience working with and analyzing large datasets to solve marketing or risk problems, with demonstrated success in a similar role (prescreen campaigns, direct marketing analytics, or customer acquisition modeling)
- Advanced formal training in statistics — MS or PhD in a quantitative field (Statistics, Physics, Mathematics, Economics, Engineering, Natural Sciences, Operations Research) with rigorous statistical foundations
- Ability to communicate complex quantitative analyses in a clear, precise, and actionable manner to both technical and non-technical stakeholders
- 6 month Full-Time Contract (1099)
- Fully Remote (Must reside in AL, AZ, DE, FL, GA, IL, IA, KS, MI, MN, NV, NC, OH, PA, SC, TN, TX, UT, VA, or WI)
