526 S. Church St. charlotte, NC 28202
CONTRACT ROLE IN CHARLOTTE, NC
You will be conducting business-consulting activities for the Analytics Services and Transformation group with a regional utility provider. You will focus on insights around determining non-technical line loss, customer usage patterns, asset protection, and power theft. Another goal of the program is to produce a multi-year load-forecasting model at the circuit level.
The environment is very dynamic and provides for a very balanced workload. Any aspiring data scientist will enjoy the innovative environment with over 50+ data scientist, modern tech stack, and unique business challenges.
Experience with time series modeling is necessary to be successful in this role. Utility experience is not required, but preferred.
• Serve as an expert in translating complex data into key strategy insights and valuable actions.
• Discover business narratives told by the data and present them to other scientists, business stakeholders, and managers at various levels.
• Developing ETL’ s using a variety of scripting languages and ETL tools to ingest data into Hadoop; working collaboratively with customers and team members supporting large business initiatives
• Develop and test heuristics.
• Create and run models.
• Perform data exploration and data mining spanning a range of disciplines
• Work with highly dynamic team of data scientist, data engineers, SMEs and product owners to deliver insights
• Create business intelligence, dashboards, visualizations, and/or other advanced analytics reports to adequately tell the business narrative and offer recommendations that are practiced, actionable, and have material impact, in addition to being well-supported by analytical models and data.
• Graduation from a four-year college or university with a degree in statistics, physics, mathematics, engineering, computer science, or management of information systems.
• 3-5 years experience plus degree in Machine Learning and Data Analysis
• Masters degree in Data Science or Analytics (preferred)
• Strong programming experience in Python, R, SQL
• Experience with Statistical Techniques: Logistic Regression and Linear and Multiple Regression, Decision Trees, Clustering, Random Forest
• Working experience with Time Series Modeling (Required): Skills such as analysis of variance (ANOVA) and forecasting techniques using ARIMA, ARMA, NARX
• Expert knowledge of PySpark required
• Strong knowledge of statistical methods (regression, time series, hypothesis testing, A/B testing, ANOVA, randomized experiment), machine leaning, algorithms, data structures and data infrastructure
• Experience with R for statistical analysis
• Experience with Numpy packages, Pandas, Jupyter and Zeppelin notebooks
• SQL experience required
• Hands on development experience with Apache technologies such as Hadoop, Spark, Hbase, Hive, Pig, Solr, Sqoop, Kafka, Oozie, NiFi, etc. Working knowledge of statistics, programming and predictive modeling
• Experience designing data queries against data in the HDFS environment using tools such as Apache Hive and Apache HBase
• Experience working in data mining or natural language processing.
• Mastery of statistics, machine learning, algorithms and advanced mathematics.
• Hands-on development experience with one or more of Java, Python, Scala.
• Knowledge and experience in implementing Deep neural networks is a plus
• Consulting experience in an agile environment is a plus
• Experience with visualization utilizing PowerBI is a plus
• General Energy and Utility experience is a plus
• Utility forecasting, metering, GIS, distribution planning knowledge would be a plus