Bank of America Corporation

Elaine C Marino

Debashis Ghosh

Kurt Newman

David Joa

Naveen Gururaja Yeri

Agus Sudjianto

Thayer S Allison

Mark V Krein

William Anthony Nobili

Yanghong Shao

Arun Pinto

Timothy John Breault

Aijun Zhang

Benhong Zhang

Zhe Zhang

Meghan Alita Steach

Ulrich A Bruns

John Delmonico

Shelly X Ennis

Ruilong He

Glenn B Jones

WeiCheng Liu

Shuchun Wang

Hungjen Wang

Joy M Tarquin

Maryann Mangini

Techniques for bridging data from business support units, e.g., call centers and marketing operations, with a data warehouse to augment and enrich pre-existing customer information. Unstructured data is received with incomplete integration information. A data key is created from the unstructured data, and the unstructured data is integrated with the structured data in a data warehouse based on the data key. Unstructured data can assume different forms of data, including recorded audio data, facial image data, and iris image data. At least one customer identifier is extracted from the unstructured data by data mining. A data key is subsequently created from the at least one customer identifier. Incomplete integration may include partial integration information or may not include any integration information.

Unstructured data integration with a data warehouse

A data driven and forward looking risk and reward appetite methodology for consumer and small business is described. The methodology includes customer segmentation to create pools of homogeneous assets in terms of revenue and loss characteristics, forward looking simulation to forecast expected values and volatilities of revenue and loss, and risk and reward optimization of the portfolio. One methodology used for modeling revenue and loss is a generalized additive effect decomposition model to fit historical data. Based on the model, a segmentation procedure is performed, which allows for creation of groups of customers with similar revenue and loss characteristics. An estimation procedure for the model is developed and a simulation strategy to forecast and simulate revenue and loss volatility is developed. Efficient frontier curves of risk (e.g., return volatility) and reward (e.g., expected return) are created for the current portfolio under various economic scenarios.

Risk and reward assessment mechanism

Growing community of inventors

Sterling, CT, United States of America

Elaine C Marino