Data Science Senior Analyst

Citi • New York, NY

1d • Hybrid

About The Position

Citibank, N.A. seeks a Data Science Senior Analyst for its New York, New York location.
Duties: Perform Exploratory Data Analysis to understand the patterns and anomalies in the data. Build dashboards with customized visualizations for presenting Key Performance Indicator metrics such as business opportunities and efficiency gains. Build machine learning models such as linear models with regularization, classification models, ensemble models including gradient boosting and random forest on structured data. Build customized AI predictive models for mortgages, syndicated loans and application usage by training them on the domain specific data. Build AI models using Natural Language Processing and Natural Language Understanding techniques of neural network and deep learning methods. Build custom entity extraction of critical data elements from unstructured documents such as credit loan agreements, contracts and invoices. Build API services for the developed AI models and validate them. Identify the process gaps and the quality issues of the data and communicate to data owners. Analyze the product usage data and recommend enhancements to the product. A telecommuting/hybrid work schedule may be permitted within a commutable distance from the worksite, in accordance with Citi policies and protocols.
Requirements: Requires a Master’s degree, or foreign equivalent, in Computer Science, Machine Learning, or related field and 2 years of experience as a Data Analyst, Data Scientist, Project and Operations Manager or related position involving data analysis and visualization. Alternatively, employer will accept a Bachelor’s degree in the stated fields and 5 years of the specified progressive, post-baccalaureate experience. Full span of experience must include: Exploratory Data Analysis using Pandas, NumPy, JSON, and Matplotlib; Data extraction from databases using SQL queries; Data sources identification, data quality, consistency, timeliness and completeness assessment, data cleaning, and data conversion into suitable format; Data visualization using Tableau, building custom visualizations such as spider charts, funnel charts, Tornado charts and circle packing charts, and documentation of the visualization process; Creation of interactive dashboards including design layout and functionality and user-friendliness testing; Predictive and prescriptive models building using Python; Model feature engineering and impact analysis; Model feature importance evaluation using permutation and tree-based methods, scoring systems, and impact analysis of feature changes; Data training, validation and testing using machine learning algorithms for model evaluation and hyperparameter tuning; and Machine learning models development, including decision trees, random forests, linear regression, classification and logistic regression. Applicants submit resumes at https://jobs.citi.com/. Please reference Job ID #26937885. EO Employer.
Wage Range: $169,541 to $169,541
Job Family Group: Technology
Job Family: Data Science

Requirements

• Requires a Master’s degree, or foreign equivalent, in Computer Science, Machine Learning, or related field and 2 years of experience as a Data Analyst, Data Scientist, Project and Operations Manager or related position involving data analysis and visualization.
• Alternatively, employer will accept a Bachelor’s degree in the stated fields and 5 years of the specified progressive, post-baccalaureate experience.
• Full span of experience must include: Exploratory Data Analysis using Pandas, NumPy, JSON, and Matplotlib
• Data extraction from databases using SQL queries
• Data sources identification, data quality, consistency, timeliness and completeness assessment, data cleaning, and data conversion into suitable format
• Data visualization using Tableau, building custom visualizations such as spider charts, funnel charts, Tornado charts and circle packing charts, and documentation of the visualization process
• Creation of interactive dashboards including design layout and functionality and user-friendliness testing
• Predictive and prescriptive models building using Python
• Model feature engineering and impact analysis
• Model feature importance evaluation using permutation and tree-based methods, scoring systems, and impact analysis of feature changes
• Data training, validation and testing using machine learning algorithms for model evaluation and hyperparameter tuning
• Machine learning models development, including decision trees, random forests, linear regression, classification and logistic regression.

Responsibilities

• Perform Exploratory Data Analysis to understand the patterns and anomalies in the data.
• Build dashboards with customized visualizations for presenting Key Performance Indicator metrics such as business opportunities and efficiency gains.
• Build machine learning models such as linear models with regularization, classification models, ensemble models including gradient boosting and random forest on structured data.
• Build customized AI predictive models for mortgages, syndicated loans and application usage by training them on the domain specific data.
• Build AI models using Natural Language Processing and Natural Language Understanding techniques of neural network and deep learning methods.
• Build custom entity extraction of critical data elements from unstructured documents such as credit loan agreements, contracts and invoices.
• Build API services for the developed AI models and validate them.
• Identify the process gaps and the quality issues of the data and communicate to data owners.
• Analyze the product usage data and recommend enhancements to the product.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level