Data Scientist [Multiple Positions Available]

JPMorgan Chase & Co.•Jersey City, NJ

16h•$142,000 - $170,000•Onsite

About The Position

Work collaboratively with cross-functional partners to understand and address key business challenges while identifying novel solutions to complex problems that impact multiple lines of business. Leverage modern data science/analytics techniques to mine large amounts of complex data stored in big data environments, spanning multiple sources and lines of business, to develop and implement new attributes and insights for use across risk management and fraud. Analyze new and existing attributes to identify areas of opportunity to drive incremental revenue, decrease expenses, and/or reduce losses across the business line, and improve operational efficiency. Partner with stakeholders to drive implementation of application attributes into line of business strategies and models for risk management and fraud mitigation. Learn and adopt new techniques for solving new business challenges. Provide subject matter expertise support to teammates and stakeholders to ensure application attributes are appropriately interpreted and utilized across the business.

Requirements

Master's degree in Business Analytics, Econometrics, Statistics, or related quantitative field of study plus 1 year of experience in the job offered or as Data Scientist, Data Engineer, Data Analyst, or related occupation.
Bachelor's degree in Business Analytics, Econometrics, Statistics, or related quantitative field of study plus 3 years of experience in the job offered or as Data Scientist, Data Engineer, Data Analyst, or related occupation.
Advising senior leadership in technical presentations by providing data-driven recommendations that guide decision-making processes.
Translating analytical findings including statistical modeling results, machine learning outputs, and multi-source data analyses into business value propositions.
Facilitating data-driven strategy sessions.
Presenting ROI analyses with risk assessments and implementation roadmaps.
Using natural language processing to build features from unstructured data, including automated matching, string similarity, transformer models including BERT, word embeddings including Word2Vec and GloVe, named entity recognition, topic modeling including LDA, and text classification at scale.
Leveraging Excel, python, and visualization tools in PowerBI and Tableau to create charts and user dashboards that augment and enrich analytical insights.
Designing interactive dashboards with drill-down capabilities.
Implementing real-time data visualization.
Building automated reporting systems with dynamic filters and parameters.
Performing statistical analysis to create actionable management insights from data using statistical techniques including univariate and bivariate statistics, central tendencies, dispersions, chi-square test, ANOVA causal inference methods including propensity score matching and difference-in-differences, Bayesian inference, and experimental design including A/B testing and multivariate testing.
Leveraging supervised machine learning to find key drivers and estimate outcomes, including linear regression, logistic regression, decisions trees, integrated ensemble modeling techniques including Random Forest and XGBoost, hyperparameter optimization techniques including grid search, and model interpretation methods including SHAP and LIME.
Developing and optimizing data solutions using SQL, Python, Snowflake Data Cloud, and AWS using query plan analysis, indexing strategies, and partitioning schemes.
Leveraging distributed computing frameworks such as Apache Spark for scalable data processing.
Utilizing AWS services including S3, EMR, and SageMaker for end-to-end data pipeline development.
Utilizing data modeling and feature engineering techniques including normalization, regularization, polynomial feature generation, rolling average, and k-means clustering, as well as dimensionality reduction methods including PCA, feature selection algorithms including recursive feature elimination and LASSO, and embedding techniques for categorical variables.
Implementing automated feature engineering pipelines and feature stores.
Manipulating and managing data sets with billions of records across platforms to ensure data integrity and accessibility.
Establishing data governance frameworks.
Implementing data quality monitoring systems.
Designing data lineage tracking.
Managing real-time streaming data using technologies such as dbt.
Executing ETL processes using Python, PySpark, and SQL.
Utilizing workflow automation tools including Jupyter notebooks, scheduled scripts, and task schedulers with Windows task scheduler.

Responsibilities

Work collaboratively with cross-functional partners to understand and address key business challenges while identifying novel solutions to complex problems that impact multiple lines of business.
Leverage modern data science/analytics techniques to mine large amounts of complex data stored in big data environments, spanning multiple sources and lines of business, to develop and implement new attributes and insights for use across risk management and fraud.
Analyze new and existing attributes to identify areas of opportunity to drive incremental revenue, decrease expenses, and/or reduce losses across the business line, and improve operational efficiency.
Partner with stakeholders to drive implementation of application attributes into line of business strategies and models for risk management and fraud mitigation.
Learn and adopt new techniques for solving new business challenges.
Provide subject matter expertise support to teammates and stakeholders to ensure application attributes are appropriately interpreted and utilized across the business.