Role: Sr. Data Scientist
Duration: Full Time / Permanent
Location: Memphis, TN
Overall Responsibilities:
- Senior data scientist.
- Research various analytical approaches.
- Recommend and develop mathematical algorithms for related business problems.
- Communicate and direct development teams on implementation of statistical models.
- Interface with Business users and gather feedback on delivered analytical data.
- Deploy solutions on to big data platforms.
Functional Responsibilities:
- Work on one of following initiatives within Predictive Client Analytics group: RFM recommendations, CCAR and other projects TBD.
- Validation of analytical approaches produced by vendor and 3rd party consulting teams.
- Developing data validation methods.
Required Skills:
Technical / Analytical Skills:
- Excellent understanding and experience with application of machine learning concepts and techniques (linear/logistic regression, clustering, classification, PCA, Naive Bayes, association rules, Collaborative Filtering, recommendation techniques etc.).
- Experience with regression techniques for modeling the relationship between an output variable and several input variables.
- Experience with Big Data technologies.
- Experience with visualization tools like Tableau.
- Experience creating interface specification documents, attribute mapping documents, functional specifications.
- Experience with web scraping.
- Experience with Text Matching applications.
Nice to have:
- Understanding of regulatory guidelines (CCAR, Basel) around Model Risk Management.
- Working knowledge of various Fixed Income and Equities products, for example Derivatives, FX and Cash Equities.
Essential Skills:
- Strong verbal and written communication skills.
- Strong research skills.
- Python, R, SQL, Hive, Spark.
- Statistical analysis: To understand and work around possible limitations in models.
- Being able to develop hypothesis and test the Hypothesis with careful experiments.
- Research and implement data mining machine learning algorithms in supervised and unsupervised learning areas.
- Should have experience with time series modeling.
- Should have experience with optimization approaches.
- Familiarity with the Big Data Ecosystem tools: Hadoop, Hive, Impala, Mahout, Spark (Spark SQL, MLLib), Hbase and be comfortable with the using the tools.
- Strong experience in data manipulation using SQL on Hive/Impala or other Databases.
- Experience in developing and deploying model with Mahout, Spark MLLib is preferable.
- Must be proficient in programming either R/Python/Scala.
- Should have experience in Financial services industry - Capital market would be preferable.
- Should have exposure to Data Visualization tools: Tableau (Preferable)/Qlikview/Excel.
Additional Information
All your information will be kept confidential according to EEO guidelines.
#J-18808-Ljbffr