The Digital Commerce team is looking for a Data Scientist to support advanced analytics initiatives for our Digital and Loyalty/CRM business areas. The Data Scientist will be responsible for understanding data from multiple sources, writing complex SQL and Python to prepare data, for campaign insight, customer analysis, and modeling. This individual will be a part of a fast-paced agile team that is dedicated to providing insights that guide strategy and execution. This role works closely with the Digital and Loyalty/CRM strategy teams and fellow analysts to deliver insights.
The data scientist will utilize expertise to work with business users to develop data science products from business requirements. Strong, hands-on, technical skills are also needed for exploratory data analysis, explanatory analysis, business requirements gathering and development of statistical output. The data scientist performs analysis and delivers findings and presents to users of all technical backgrounds.
Perform ad hoc, descriptive, explanatory, and predictive analyses, applying ML/AI techniques when and where applicable
Create datasets from Google Cloud Platform and Oracle EDW for analysis
Analyze data from multiple sources, understand the data structure, and blend/wrangle the data together using complex SQL and Python
Analyze the results of existing programs and algorithms to determine program effectiveness
Responsible for experimentation and model building, as well as the research and development of predictive models that allow Panera to anticipate customer behavior
Work closely with Software Developers to incorporate insights and data assets into analytics-driven applications
Operationalize models and data assets into production for use in Digital and Loyalty/CRM initiatives
Communicate the results of their analyses to technical and business stakeholders, including senior management
Participate in experimental design to test models and digital treatment
Master’s Degree or foreign equivalent in Computer Science, Math or Statistics and two years of experience using mathematics, statistics, design of experiments and data visualization to discover insights using data
Experience using SQL and Python (required), Apache Spark or R (nice to have)
Ideal candidate would have hands-on experience developing, training, and validating a variety of ML models, such as decision trees/random forest, regression, clustering, advanced causal inference (e.g. synthetic controls, forecast/simulation), etc.
Ability to translate business requirements into data and analytical solutions
Demonstrated experience in handling large data sets, relational and non-relational databases
High-level written and verbal communication skills
Google Cloud Platform (GCP) experience with Big Query is a plus