Company Name: Chartboost
Location: San Francisco, CA
Date Posted: 26th Oct, 2016
- Develop complex statistical models to predict ad-click and install outcomes and learn from petabytes of data.
- Develop models and explore features and its influence using Spark MLlib and R and present results. Convert these offline analysis to online models.
- Develop processes and tools to help team members monitor, debug and analyze model performance and data cleanliness.
- Develop A/B testing framework, and measure model quality.
- Work on several data classification problems at petabyte scale data and incorporate back into statistical models.
- Develop / Solve time series analysis, classification, and clustering problems.
- Collaborate closely with product & data science teams to build new features and infrastructure
- Develop tools to assess financial impact of initiatives
- MS / PhD in Machine Learning, Statistics, Computer Science, Data Mining, Math or any quantitative discipline
- 5+ years of experience
- Ad Tech industry experience (mobile ad tech a plus!)
- Proficiency with Scala, Spark MLlib (or equivalent), Python, R.
- Experience building statistical models with stream data is a plus.
- Background with feature engineering and model building.
- Experience training a model and successfully rolling out to production