Data Scientist Analyst (Troy, MI, or other unanticipated locations throughout the U.S.) Responsibilities include: Bring data to life to solve industrial and manufacturing business problems. Predict suppliers' material shipments due to global shortages to optimize automotive production planning. For optimal allocation of constrained commodities to the most profitable use, automotive suppliers need to know what quantity of each constrained commodity supplier will receive each month to prepare production lines based on available materials. Help predict the level of material shipments of automotive and industrial materials for the following several weeks using historical supplier promises and actual past shipments. Developed a machine learning application that uses multiple methods to generate the best prediction with the smallest forecasting error related to industrial and manufacturing material supplies that the supplier relies on for its automotive production line. Work collaboratively to design analytical solutions that harness internal and external data (including connected vehicle data) and leverage visualizations, predictive analytics, and prescriptive methods, to help the right decision makers make the right decisions at the right time. Collaborate with partners in vehicle connectivity, purchasing, product development, warranty, and other Company functions to define problems, identify data, develop data pipelines, develop machine learning algorithms, leverage operations research techniques, and deploy software solutions to provide actionable insights that deliver measurable, transformational benefits to Company. Work with connected vehicle data and scalable technologies such as Hadoop/Spark. Explore and analyze both structured and unstructured data. Manipulate high-volume, high-dimensional data from a variety of sources to identify value-generating patterns, anomalies, relationships, and trends, and solve critical roadblocks. Alteryx; Python/PySpark; at least one of QlikView(preferred) or Tableau; Hadoop; R; SQL. Query and manipulate data from big data platforms and databases (e.g., Hadoop, Teradata, SQL Server, Oracle) using Hive, SCOOP, Spark, and/or SQL. Develop efficient Alteryx workflows, Python and PySpark scripts to perform data extraction, data mining, and data wrangling. Master the details of connectivity data, how it is produced, stored, and curated, and what the variables mean in relation to vehicle operation. Utilize analytical applications like Python and R and Big Data technologies (Hadoop/ Spark) to identify trends and relationships between different pieces of Company-owned and third-party data and draw insightful and actionable conclusions. Interact with business partners and stakeholders in Vehicle Connectivity, Purchasing, Material Cost, Product Development, Finance to acquire deep understanding of the business problems, processes, and data. Translate industrial and manufacturing problems into scalable machine learning models to address current global supply problems of manufacturing materials. Encode analytical models and mathematical abstractions into robust computer programs to obtain timely, meaningful, and actionable insight into the data. Deliver analytic models using skills such as statistical analysis, machine learning, algorithm design, and model development and refinement in R, Data Robot, Python, and/or Alteryx. Design intuitive visual interfaces in Python, QlikView, R, and/or Tableau for users to interact with the data. Python/PySpark, HPC/Hadoop cluster, Linux, SQL data analysis, and Alteryx. M.S. in Industrial Engineering or closely related and 6 months experience in Cyberinfrastructure Engineer or closely related. 6 months experience in: Python/PySpark, HPC/Hadoop cluster, Linux, SQL data analysis, and Alteryx. Telecommuting permitted.
40 hrs/wk. 8:00 am – 5:00 pm.