Cognitive training app.
This position is responsible for specification and development of direct mail data science efforts for each of Elevate’s lending portfolios.
This position will lead efforts to develop data strategies, predictive models, and decision processes, and algorithms for use in direct mail and other marketing campaigns. The Manager will collaborate with risk leaders, marketing, and` other data scientists to develop, evaluate, and implement data and scoring products to drive marketing strategy and decisions.
Principal Duties and Responsibilities:
Manage and lead a team of data scientists which develops predictive models for direct mail campaigns and for other production marketing efforts.
Develop and implement methodologies to optimize selections for prescreened offers in the direct mail channel for all products.
Identify novel data sources for inclusion in Elevate’s progression of internally-developed predictive models for marketing efforts.
Collaborate with Risk Management and Product leaders to specify scoring algorithms and models; partner with IT and external partners to ensure timely, effective implementation of all scoring and decisioning tools.
Collaborate with internal Compliance and Legal resources to ensure adherence to relevant regulations and laws, while maintaining maximal flexibility and predictive power.
Develop and maintain relationships with Risk Management, Marketing, and other internal and external support functions to ensure alignment of Data Science initiatives with Company objectives.
Complete all other projects as assigned.
Experience and Education:
Advanced degree (MA/MS/MBA/PhD/DSc) in an analytical field required.
6+ years of experience developing and deploying advanced scoring algorithms.
Demonstrated experience in machine learning, data mining, and advanced econometric modeling.
Management experience, preferably of large groups of quantitative analysts and modelers.
Required Skills and Abilities:
Ability to thrive in a dynamic and fast-paced environment and drive change, and collaborate effectively with a variety of individuals and teams.
Demonstrable familiarity with machine learning techniques and algorithms: decision trees, penalized regressions, bootstrap aggregation, boosting, model ensembling, model stacking, and other methods of contemporary predictive analytics.
Familiarity with methods of retrospective data analysis, e.g., stratification, propensity score matching, entropy balancing.
Familiarity with techniques of ensuring model robustness, including k-fold crossvalidation, nested crossvalidation, and concept drift.
Demonstrable familiarity with unsupervised and semi-supervised data mining techniques, e.g., cluster analysis (DBSCAN, DENCLUE, sparse clustering).
Familiarity with experimental design and testing methodologies.
Experience with R, Python, and other high-level languages.
Experience with SQL, Hadoop and/or Spark.
Proficiency in SAS.
Strong understanding of databases and database architecture.
Strong planning, organizational, people, and project management skills.
Excellent interpersonal, verbal and written communication skills.