Company Name: AIG
Location: New York, NY
Date Posted: 27th Oct, 2016
- Build predictive models utilizing both traditional statistical methods (Generalized Linear Models, Mixed Effects Models, Ridge, Lasso, etc.) and modern machine learning techniques (Gradient Boosted Trees, Random Forests, Kernel Methods, Deep Learning, etc.).
- Extract, clean, and manipulate large datasets (both structured and unstructured) for model building.
- Communicate insights from quantitative analyses to technical and non-technical audiences.
- Research and implement novel machine learning algorithms.
- Work with business sponsors and IT teams to implement analytic solutions.
- You have expertise in SQL and at least one of the following: R, Python, or SAS.
- You have experience with big data technologies such as Hadoop, Apache Pig, MongoDB, etc.
- You have built predictive models that have been put into live production.
- You obsess over sample bias, over-fitting, variable selection, missing values, etc.
- A dataset with 10 million rows and 5000 columns does not faze you.
- You understand the need to balance predictive power, interpretability, and ease of implementation.
- You appreciate that all models are wrong, but some are useful.