Decision Science Manager, Media Mix Modeling at Facebook
Menlo Park, CA, US
Facebook's mission is to give people the power to build community and bring the world closer together. Through our family of apps and services, we're building a different kind of company that connects billions of people around the world, gives them ways to share what matters most to them, and helps bring people closer together. Whether we're creating new products or helping a small business expand its reach, people at Facebook are builders at heart. Our global teams are constantly iterating, solving problems, and working together to empower people around the world to build community and connect in meaningful ways. Together, we can help people build stronger communities — we're just getting started.
The Consumer Marketing team focuses on building Facebook brand presence, improving user sentiment and product education. We are looking for a Decision Science Manager, Media Mix Modeling on our team. This person will lead our Media mix and attribution efforts and work with members of our Decision Science and Operations teams to improve our marketing efficiency and effectiveness. Key goal for this person will be to apply modeling techniques relevant to media mix modeling optimization and multi-touch attribution to our marketing efforts to connect the impact of marketing activities on business outcomes. This person will also manage a small team of Decision Scientists on projects related to understand marketing performance and ROI. The ideal candidate will have extensive graduate training in economics and econometrics, and will answer important product and business questions by applying appropriate econometric methodologies and developing new methodologies when necessary. Our ideal candidate will also have tremendous passion for building strong brands and understanding user sentiments.
RESPONSIBILITIES
  •  
     
    As a Decision Science Manager for media mix modeling and marketing attribution, build and enhance market level media mix models to connect the impact of marketing tactics on business and financial outcomes in the short and long term
  •  
     
    Apply the output of media mix models to improve user perception and engagement with sustainable ROI by optimizing spend across various channels
  •  
     
    More specifically, apply algorithms such as random forests, Bayesian models, generalized boosted models, generalized additive models, support vector machines, neural networks, time-series forecasting, game theory, or conditional probabilities, develop algorithms for classification tasks such as clustering, latent class analysis, etc.
  •  
     
    Implement modeling processes from end-to-end including data gathering, data profiling, numerical model building, calibration, cross-validation, and boosting model accuracy. Interpret and validate model results with statistical validity checks, and design data visualization reports to track model performance and business impact
  •  
     
    Collect, process and validate data from internal and external data sources. Build and/or utilize toolsets and set up processes for extracting information from unstructured data streams
  •  
     
    Work with data engineers to automate input ETL, handle missing data through an algorithmic approach such as multiple imputations to enable insights in sparse and messy datasets
  •  
     
    Run optimization and simulation scenarios to help provide the marketing investment and allocation recommendations to Operations and Finance teams, Marketing leadership and CMO
  •  
     
    Provide insights to marketing leadership on cost to acquire users, value of digital engagement, and cross-channel impact of media
  •  
     
    Explain complex modeling approaches in simple terms and develop compelling narratives that connect modeling results with business problems
  •  
     
    Partner with other Decision Scientists to validate and fine tune the model with experimentation
  •  
     
    Manage a small team of decision scientists on projects related to understanding marketing performance and ROI
  •  
     
    We expect this candidate to spend 70% or more time on hands-on work related to building media mix models and 30% or less time on managing Decision Scientists on the team
MINIMUM QUALIFICATIONS
  •  
     
    3+ years of hands-on experience with programming marketing mix modeling solutions
  •  
     
    Knowledge with predictive modeling techniques and experience in media mix and predictive modeling initiatives
  •  
     
    6+ years of experience in analytics or data science teams
  •  
     
    3+ years experience managing a team of data scientists
  •  
     
    Knowledge of hierarchical Bayesian, MCMC, random forests, generalized boosted models, generalized additive models, support vector machines, neural networks, time-series forecasting, ANOVA, multiple regression, principal component analysis, decision trees, clustering and other similar approaches
  •  
     
    Experience programming in SQL and R or Python
  •  
     
    Experience coding and maintaining predictive algorithms
  •  
     
    Experience developing measurement across marketing activities, including TV, print, radio, OOH, SEM, display, online video, owned media, sponsorships and promotions
  •  
     
    Knowledge with media data vendors (e.g. IRI, Kantar, Nielsen, etc.) and digital audience data (e.g. DMPs)
  •  
     
    Communication and experience influencing others to achieve buy-in for recommendations
PREFERRED QUALIFICATIONS
  •  
     
    Master's or Doctorate degree in statistics, economics, behavioral/social science, psychology, Engineering or a related quantitative field
Facebook is committed to providing reasonable accommodations for qualified individuals with disabilities and disabled veterans in our job application procedures. If you need assistance or an accommodation due to a disability, you may contact us at accommodations-ext@fb.com.