Job Description:

Data Support Analyst

The GTS Data and AI team drives innovation within one of the largest commercial payment businesses in the world. At the core, the team is a collection of curious and driven data scientists, data engineers, and product managers that welcome challenging problems.

Our team often operates in a think tank setting, brainstorming and pinpointing opportunities alongside other business teams to create traceable value through data. We deepen our understanding of client behavior primarily from transaction-level payments across multiple rails (ACH, wires, FX, among others) and account dynamics (including balances and terms). The team meticulously balances long term and short-term projects, resulting in constant delivery of production level solutions at scale. Each member of the team holds themselves accountable and is driven by an insatiable curiosity.

If you are passionate about working in cross-functional teams to generate revenue through statistical analytics and predictive modeling, consider applying to this role.

Your contributions and learning will be fueled by communication and collaboration with data engineers, product managers, and business teams. Utilizing database and programming knowledge, you will tackle a variety of statistical analyses and machine learning implementations ranging from EDA, hypothesis generation, regression, and classification, time series analysis (e.g., forecasting and anomaly detection), recommendation systems, and stochastic optimization. You may also implement A/B testing and research emerging technologies, among other day-to-day duties.

• Collaborate with stakeholders, including GTS business and Data & AI team product managers, to identify opportunities to leverage internal and external data sources for modeling. Then, linking model results to actionable insights to enhance sales teams’ ability to prospect, generate revenue, and manage risk

• Research and devise ways to lever methods from other domains, such as latent representations and preventative maintenance, to GTS use cases

• Combine models through ensemble modeling

• Coordinate with Data Engineers to build data environments providing data identified by Data Analysts, Business Analysts and Product Managers

• Collaborate with Product Managers and Data Scientists to develop an understanding of needs

Required skills:

• Extensive experience using the scientific Python stack—including, Pandas, NumPy, and Sklearn

• Strong understanding of regression and classification techniques such as regularization, dimensionality reduction and feature selection, K-NN, Naïve Bayes, logistic regression, and gradient boosting machines or random forests

• Understanding of common Natural Language Processing techniques for topic modeling and sentiment analysis

• Awareness of statistical concepts, including distributions and outliers, significance testing, and general linear models

• Ability to communicate results to both technical and non-technical audiences, including facility with PowerPoint and Excel

Desired skills:

•

Graduate level (masters or PhD) degree in a quantitative field such as computer science, engineering, math, and physics

Understanding of Bayesian inference, optimization, bandit algorithms, and reinforcement learning

• Ability to communicate results via interactive visualization tools such as D3.js, GGplot, Matplotlib and Tableau

• Proficiency in using query languages such as SQL and HiveQL and NoSQL databases, such as MongoDB and Cassandra

Shift:

Hours Per Week: