Google's current manual decision model for assigning customers to sales channels is limited by historical data and a narrow understanding of what drives customer performance, and the company is looking to develop a causal ML model to automate and enhance these assignments.
Requirements
- Master's degree in a quantitative discipline such as Statistics, Engineering, Sciences, or equivalent practical experience.
- 4 years of experience using analytics to solve product or business problems, coding (e.g., Python, R, SQL), querying databases or statistical analysis.
- Experience designing and implementing causal ML models.
- Experience designing and building large datasets for ML modeling.
- Experience with statistical modeling packages.
- Python, R, SQL
- Machine Learning
Responsibilities
- Develop core dataset and signal repository, using SQL or other scripting language, for Machine Learning.
- Investigate, ideate, build, and streamline major signal repository to enable ML and unique insights.
- Analyze data, partner with other Business Data Scientists, to help us understand drivers of historical business performance.
- Build causal ML models to improve business channel assignments and treatment.
- Develop expansive dataset that describes the Google Ads Customer, in as much detail as reasonable, that will enable us to establish causal effects from our business efforts.
- Leverage insights to determine areas of opportunity for improvement in business treatment.
- Use analytics to solve product or business problems, coding (e.g., Python, R, SQL), querying databases or statistical analysis.
Other
- Master's degree in a quantitative discipline
- 4 years of experience
- Excellent presentation skills
- Strategic thinker, using business and product judgment to guide data strategy
- Ability to work in the US, with possible locations including Mountain View, CA, USA; Atlanta, GA, USA; Boulder, CO, USA; Chicago, IL, USA; New York, NY, USA; Los Angeles, CA, USA; San Bruno, CA, USA; San Francisco, CA, USA; Sunnyvale, CA, USA; Washington D.C., DC, USA
