Utilize advanced models to predict profit and its different components.

Develop backend forecasting, optimization, and simulation engines.

Build monitors for model performance and make recommendations for adjustments to increase accuracy.

Evaluate and critique the assumptions of the models and refine approaches.

Perform high quality data analysis to uncover trends and patterns in both text and data.

Generate ideas and new solutions that result in the creation of intellectual property.

Develop classification and clustering algorithms for large datasets using a variety of languages and tools (e.g. Java, Hive, Python, C++, R/Matlab, etc.).

Build and maintain robust and accurate predictions of profit and vendors.

Create, enhance, and maintain documentation for data, modeling choices, rationale and results.

Contribute to building the internal knowledge base on best practices in data/text mining and machine learning.

Identify areas for continuous improvement and research.

Master’s Degree in CS, machine learning, Engineering, Statistics, Operations research or in quantitative field.

2+ years experience working in an analytics role developing and implementing machine learning algorithms.

Proficiency in several techniques including but not limited to: clustering, graphical models, Bayesian nonparametrics, Gaussian processes, SVM, random forests and boosting/bagging.

Competence in model-building/model-validation Proven ability to structure and analyze large data sets