Data Scientist - Machine Learning/Deep Learning - BFS

Duties and Responsibilities:

- Drive data-backed decisioning for customer wrt products, processes, offer strategies, channel selection, timing, etc.

- Deploy ML / Deep learning methodologies for feature engineering

- Create and fill existing variables through model variable inference methodologies

- Create methodologies to utilize sparse data to predict known use cases for marketing and risk

- Establish relationships between customer information, events, etc. to trigger marketing, risk use cases

Examples of use cases to create capabilities for:

- Create and manage complex inferred variables - like a share of wallet, size of the wallet, propensity to buy (when, where, how), propensity to repay, etc.

- Create solutions based on Geo data - negative area marking, household score

- Create solutions for managing marketing properties on the wallet, creating solutions to match marketing content to customers through various tags

- Create metrics to evaluate the performance of the solutions created, enhance capabilities to better performance metrics

- Own execution and availability of solutions to teams for retrospective analysis, transaction recommendation / approval management

Minimum Qualifications :

- 6+ years of experience building sparse data models: Neural Network / Deep Learning / Bayesian Networks / Monte Carlo Markov Chain / SVM / GBM / Lookalike models / Feature engineering

- Passionate about extracting value out of data by creating new variables, understanding base variable relationships

- 6+ years of experience in managing other team members in a formal or informal capacity

- 4+ years of experience doing quantitative analysis

- Experience initiating and driving projects to completion with minimal guidance

- Experience communicating the results of an analysis

Preferred Qualifications:

- Bachelor Degree in Computer Science, Math, Physics, Engineering, or related quantitative field

- Understanding of statistical analysis, experience with packages, such as R, MATLAB, SPSS, SAS, Stata, etc.

- Experience with large data sets and distributed computing (Hive/Hadoop)

- Minimum 4+ years of industrial experience in implementing | managing very large data platforms Like Data Lake & Enterprise Data Warehouse