Data Scientist

ID Analytics

(San Diego, California)
Full Time
Job Posting Details
About ID Analytics
ID Analytics is a leader in consumer risk management with patented analytics, proven expertise and real-time insight into consumer behavior. By combining proprietary data from the ID Network®—one of the nation’s largest networks of cross-industry consumer behavioral data—with advanced science, ID Analytics provides in-depth visibility into identity risk and creditworthiness.
Summary
The Data Scientist will be part of a team responsible for the development of ID Analytics’ advanced technologies in statistical score modeling, score model development and deployment, large scale database analysis and statistical algorithms. This position includes devising new approaches to solving difficult statistical modeling problems. The Data Scientist will resolve problems or coordinate score model design architecture and may require frequent client interaction to complete the deliverables.
Responsibilities
* Analysis, design, development, test, troubleshooting and documentation of complex data systems that may involve one or more of the following: predictive score models, feature extraction, data-driven analysis, application of machine learning algorithms, decision making and related utilities. * Completing written documentation and reports of results. This will take the form of business reports, internal technology white papers and statistical system documentation. * Devise new algorithmic approaches to solving difficult quantitative problems. * Adopt new tools and algorithms effectively to improve model performance. * Work independently on complex statistical score modeling and analysis problems with very large and complex data structures. * Design data experiments to verify assumptions and hypothesis. * Experiment with new algorithms and analytical approaches and report on the impact to model performance. * Other duties as assigned.
Ideal Candidate
**Qualifications:** * Master’s degree in a relevant technical discipline (Math, Engineering, Computer Science, Statistics or similar field) with at least 3 years of job experience or Bachelor’s degree in a relevant technical discipline with 5-7 years of job experience. PhD in a relevant technical discipline preferred. * At least 2 years of experience with Object-Oriented programming languages. * 1-2 years of experience with Unix/Linux system architecture and command line tools. * 1-2 years of experience with scripting languages such as python, awk or perl * Experience with statistical or scientific computing packages such as MATLAB, R or SAS * Strong interpersonal and communication skills (both written and oral) including the ability to communicate complex technical/statistical concepts to a non-technical audience. **Preferred Skills:** * Prior statistical score modeling and/or machine learning experience. * Experience and/or proficiency in emerging big data analytics tools and architecture. * Experience with distributed computing systems, noSQL and Hadoop based technologies * Fraud and risk management industry experience in developing scoring models from very large data sets. * Experience with the use of Java for delivering high-speed, large scale data modeling. * Experience with data visualization technologies such as d3, matplotlib, Tableau * Knowledge and/or experience with large scale Convolutional Neural Network will be plus.

Questions

Answered by on
This question has not been answered
Answered by on

There are no answered questions, sign up or login to ask a question

Want to see jobs that are matched to you?

DreamHire recommends you jobs that fit your
skills, experiences, career goals, and more.