Contact me at johnckane1@gmail.com or 815-871-588213+ years experience in statistics, data science, and project management. I have lead teams on big, capitalized, projects and mentored junior data scientists. The technical skills that I bring to my role include:Programming: Python (PySpark), Scala, SQL, R (tidyverse, R Shiny, Base R), Bash/Shell, SASBig Data Technologies: Spark, HadoopMachine Learning: Neural Networks, GBM, RegressionCloud Platforms: Azure, AWSDatabases: Snowflake, MySQL, Oracle, SQL Server, Yellowbrick, Netezza Version Control: gitData Visualization: ggplot2IDEs: Databricks, VS Code, RStudioMy career spans capital project leadership, client-facing analytics, internal R+D, and medical research. I was selected to lead a cross functional company wide initiative to modernize the management of business-critical data assets. This included the building of a single, flexible, extensible, and centralized data repository, an automated trade item classification algorithm driven by machine learning, and a user interface to accompany the new backend capabilities for a streamlined data management and access. I built from scratch an innovative and now industry leading approach to shopper segmentation, using enriched datasets to capture nuance in purchase motivations beyond traditional RFM metrics, leading the deployment to both legacy and new media touchpoints. I worked in “skunk works” efforts leading to new, major company breakthroughs. I was part of the transformations of those efforts to work more formally in an agile framework. I work with both on-prem RDBS and distributed cloud storage and computing. I led my projects through multiple data tech stack migrations. Rapid change in the industry often meant the company lacked available resources with a needed skill set. I proactively taught myself new disciplines to fill the resource gaps in data engineering, data governance, and scrum (PO/PM/SM) in addition to data science functions.