Machine Learning / Python Analyst
|Reference # :||18-01455||Title :||Machine Learning / Python Analyst|
|Location :||LONG ISLAND CITY, NY|
|Position Type :||Contract|
|Experience Level :||Start Date / End Date :||10/01/2018 / 10/01/2019|
Our client, a leading global financial services company, has approximately 200 million customer accounts and does business in more than 140 countries. They provide consumers, corporations, governments and institutions with financial products and services, including consumer banking and credit, corporate and investment banking, securities brokerage, transaction services, and wealth management
Consultant will work with Global Performance Insights team implementing Machine Learning project in Big Data environment to analyze customer Digital and offline behavior and segmentation to achieve servicing goals across customer journeys in near-real time. In addition will work with staff to onboard Machine Learning Models, developed in Python, Spark, and Hive, into client's Big Data environment (HDFS). Once initial models are operational, consultant will work to update and retrain Models to accommodate new Data Sources, extensions to additional channels, and operational efficiencies to compress execution timeline.
Provide technical assistance to Predictive Analytics team with the following tasks:
• Productionize current models, developed in Python, Spark, and Hive, making adjustments to model code as needed to score customers, and working with partner big data, digital, and messaging teams to facilitate execution.
• Update and retrain current models in Python with new data, parameters, and extensions beyond initial channels and targeting platforms.
• ETL in Hive.
• High level of understanding and good working knowledge with Data Science fundamentals, Predictive Analytics and Machine Learning Algorithms.
• Expertise programing in Python, using Machine Learning and other relevant packages (scikit-lean, NumPy, pandas, matplotlib, etc.), particularly as related to random forests.
• Expertise with ETL using SQL/Hive SQL.
• Work experience, preferably in a large corporation, implementing models in production HDFS/big data environment, preferably via Spark integration.
• Experience with Digital Data (SiteCatalyst) or customer journey data (Clickfox) highly desirable.
• Undergraduate or graduate education in Quantitative field or Data Sciences highly desirable.
Please see our complete list of jobs at:
Job Status: Contract/Temporary