Caylan Kolste

Background

About Caylan Kolste

I believe our path is predestined by the amount of determination and hard work feeding into our life. I am a high caliber data scientist with a demonstrated background in the information technology, health care, and marketing industry. Skilled in all aspects of the data science lifecycle: business scope, data collection, data preparation, exploratory data analysis, modeling, model evaluation\validation, model deployment, and model monitoring. The future is data and we need data linguists that harness the data’s true potential. Currently, I assist in the development of a subscription lifecycle tracking service, Kochava Subscriptions; leading most of the technical aspects of the product. I designed the structure of Google Cloud BigQuery tables scaling to client needs, wrote complex and scalable SQL queries to power over seven subscription specific visualizations, measured data integrity and worked with engineering to solve the issues, performed Quality Assurance testing, and architected a production Tableau solution. I designed a pipeline that automated data extraction, transformation, and loading (ETL) process utilizing Python, Google Cloud BigQuery, Tableau Server, Tableau Command Line, Google Cloud SDK (gcloud command line tools). Using Python, I produced algorithms to provide high level analytics that met clients needs; Customer Segmentation using RFM Analysis, Lifetime Value (LTV), Monthly Recurring Revenue (MRR), churn prediction scores and client specific key performance indicators (KPIs). Previously, I worked in the healthcare industry with an elite team of data scientists, data analysts, and data engineers. Cerner Intelligence is an elite organization specializing in overcoming the most complex problems in healthcare by using machine learning and artificial intelligence. I aided in the successful development and deployment of a Palliative Care risk stratification model by wrangling unstructured big data; leveraging Python, SQL, PySpark, AWS S3, AWS Athena, and AWS Sagemaker to create, engineer and select features that amplified the model’s operational performance. Simultaneously, I worked on designing a data science\analyst curriculum for training entry level associates, spearheaded a full scale attrition analysis, and assisted colleagues in various aspects of their models and analyses. I am determined to keep learning as the analytics community continues to evolve. I am a go-getter with a never ending passion and excitement for fun. I would love to connect to discuss theories, business, jobs, or anything else!