Data Scientist

Summary

Developed a machine learning model, using Python's sklearn, for the marketing team to identify donors at risk of churning with a 67% accuracy. Prior to the model being developed and launched to production, marketing was struggling to tailor their outreach efforts to the specific needs and uncertainties of donors and were using a blanket approach for all of them. Part of the model's functionality was to separate donors into clusters based on their donation history, which marketing campaign they engaged with, and demographic information, then each of the five resulting donor clusters had a unique machine learning model, all with slightly different parameters to ensure performance was at its best depending on which type of donor's information was going through the pipeline.
Six months after launch, the project resulted in an increase in donor satisfaction of 27%, 35% increased donor retention, and gave marketing better direction on how to best communicate with donors at risk of churning given that now they had specific characteristics based on the cluster they belonged to.

Expectations

Good work-life balance, flexibility in schedule, leadership/management that promotes communication from all team members and addresses their needs, a team that spends more time getting things done rather than in meetings.

Employment Preferences

Expected Base Salary

**,000 USD

Academic Degree

Experience

Skills

• Python
• R
• SQL
• Data Science
• Machine Learning
• Regression
• Statistics