What you’ll do:

· Research, design, and implement predictive models, use data sciences to detect and prevent high risk fraud and reduce false positives.

· When that means high precision classification, you will work fraud and trust SMEs to understand domain knowledge, business expectation and turn them into data driven machine learning approach.

· Develop machine learning, data mining, statistical, and graph-based algorithms designed to analyze massive data sets; partner with Cloud technologists to ensure proper implementation and usage of said algorithms

· Analyze large data sets to develop multiple, custom models and algorithms to drive innovative correlations for fraud and acceptance data as well as social data

· #OperateAtDepth - Ideate, brainstorm and drive projects from conception to completion Conduct exploratory data analysis, supervised, unsupervised and semi-supervised machine learning to identify fraud trend, segment and clusters, and optimization opportunity

· Lead identification of trends and KPI’s with the objective of improving customer performance

· Mentor junior data analysts and demonstrate Data Science and development best practices

What you’ll need

· An M.S., P.H.D., or equivalent experience in a related discipline (Engineering, Mathematics, Physics, Finance or C.S.)

· Experience in Python, R, or other Data Science object-oriented programming language

· Experience with applying machine learning techniques at scale and their tuning parameters (Neural Networks, Random Forest, Bayesian Models, K-Means Clustering)

· 7+ years of experience applying Machine Learning, Statistical Modeling, and Data Mining.

· Expert in anomaly detection algorithms including Regressions, Random Forrest, GBMs, Support Vector Machines, KNNs, Neural Nets and Social Network Link analysis.

· Expert with SQL, NoSQL, and unstructured databases (MySQL, Hadoop, Redshift, MongoDB)

· Applied data science techniques, data management and advanced analytic techniques while doing fraud analysis/anomaly detection.

· Hands on experience with software design for scalability, reliability, and performance

· Proven track record in developing mathematical models to predict business outcomes and determine cause and effect relationships

· Comfort level with ambiguity and ability to manage multiple projects at the same time

· Ability to communicate analytical insights clearly and concisely to individuals across the organization

· Experience working with real time data and deploying models in a real time scoring environment

· Be an active participant and source of inspiration within the broader data science community at Chewy and contribute to a culture of learning

· Candidate must be organized, driven, and exhibit critical thinking skills.

· Candidate must have an entrepreneurial and self-starting mentality.