Data Scientist, Insights & Analytics

Key Skills

Apache Hadoop, Continuous Integration & Continuous Delivery - CI/CD, Databricks, Decision trees, Large data sets, Logistic Regression, Machine learning techniques, matplotlib, Natural Language Processing (NLP), Neural Networks, NumPy, Pandas, PowerBI, Predictive analytics, Predictive Modeling, PySpark, Python Programming, Random forests, Scikit-learn, Snowflake, SQL, Statistical modeling, SVN, Tableau, TensorFlow

Job Description

This key role within Decision Science & Analytics will lead the ongoing development and execution of the Company’s customer and marketing analytics program. This role will work collaboratively with key third parties, internal IT resources and the broader Decision Science organization to analyze transactional data, develop predictive and deterministic models to deliver insights. Projects may include automating analytics processes, creating/updating customer segmentations, or ad hoc open-ended deep dives into category performance

Duties & Responsibilities:

• Perform analytical tasks that include data gathering, analysis, visualization, and data-driven storytelling as a basis of project justification and innovation. Present findings in PowerPoint or Tableau/PowerBI to stakeholders, “telling the story” with data to non-technical audiences
• Perform statistical/machine learning projects as necessary for given business needs. These projects may consist of – large scale/rapid hypothesis testing, classification, prediction, and recommender systems.
• Develop dynamic, productionized, and scalable customer-level models that generate ROI for both DG and their customers. These models may include predictive propensity models and customer segmentations
• Create automated, reusable analytics workflows from end-to-end: from developing and maintaining SQL/Python code to the final report or dashboard deliverable

Qualifications

Knowledge, Skills and Abilities (KSAs):

• Strong problem-solving skills utilizing expertise, business judgment and robust quantitative analyses
• Develop code to combine, clean and prepare data for modeling using some combination of SQL, Python and PySpark (including but not limited to pandas, numpy, scikit-Learn, matplotlib, tensor-flow)
• Identify and implement proper data preparation and feature engineering methods, such as outlier identification and removal, principal components analysis (PCA), and general data structuring
• Experience with common modeling techniques, such as logistic regression, decision trees, random forest, SVM, regularized regression, neural networks, and natural language processing (NLP)
• Demonstrated ability to translate complicated analytics topics into easily communicable concepts to less technical audience, including model accuracy and feature importance
• Practical experience ingesting and manipulating large volumes of data (millions of records)
• Proficiency with common analytical platforms, including distributed compute (e.g. Databricks, Hadoop, Snowflake, etc.)
• Experience with code management tools such as Github (familiarity with CI/CD practices preferred)
• Experience with retail industry or marketing and media networks is preferred

Work Experience &/or Education:

• MS in Data Science, Statistics, Economics, Computer Science, Mathematics, or related applied quantitative field preferred. Bachelor’s in a highly quantitative/STEM field considered with the right experience.
• 2-5 years hands-on industry (non-academic) experience in Data Science (or equivalent quantitative job title). Strong background in applying statistical machine learning techniques to predictive modeling and experience with Machine Learning libraries.