Automated Bond Price Extraction from Unstructured Emails
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Credit Default Swap traders face challenges in extracting trading opportunities from unstructured and voluminous emails containing bond price information, as they lack consistent formatting, leading to missed profit opportunities due to the inability to read through all emails in time.
Innovation Solution
A system and method that processes partially unstructured data to identify securities and extract trade information by selecting and processing data items such as tickers, coupons, maturities, and bid/offer prices from emails, generating a security identifier and outputting relevant trade information, thereby automating the extraction of valuable market data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traders manually read through emails to extract bond price information, then they can accurately identify trading opportunities, but they cannot process all emails in time due to the high volume and unstructured nature of the data
Solution Approach 1:
The patent replaces the mechanical manual reading process with an automated computer-based system that uses natural language processing and pattern recognition algorithms to extract bond price information from unstructured emails, thereby increasing processing speed while maintaining accuracy
Solution Approach 2:
The system enables automated self-processing of email data by training machine learning models to automatically identify and extract relevant trading information from unstructured text without requiring manual intervention for each email
2Productivity
If traders focus on reading emails quickly to process high volume, then they can increase processing speed, but they miss important trading opportunities due to lack of consistent formatting making accurate extraction difficult
Solution Approach 1:
The system changes the parameters of data processing by transforming unstructured text data into structured data through automated parsing and normalization processes, allowing for both high-speed processing and accurate extraction of trading opportunities
Solution Approach 2:
The system performs preliminary processing of emails by pre-training algorithms on email patterns and formatting conventions, enabling the system to quickly and accurately extract information from newly received emails without manual formatting adjustments
Data Source
AI summary
A system and method for processing partially unstructured data relating to a financial security. The system and method resolve first- and second-identifying data from the partially unstructured data and determine whether a security is defined by the first-identifying data and the second-identifying data. Additionally, the system and method resolve trade information relating to the security identifier from the partially unstructured data. If a security is defined by the resolved identifying data, a security identifier representing the defined security, along with the trade information relating to the defined security, are output.