Financial Instrument Selection via ML Clustering and Role-Based Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic trading platforms lack sufficient control over information access and participation levels, particularly in limited group settings, leading to inefficiencies in trading securities.
Innovation Solution
A computer-implemented method that hosts an electronic communication session for trading financial instruments, utilizing a machine learning model to identify suitable dealer users and invitee users based on liquidity scores, customer values, and trading intentions, enabling selective sharing of trade parameters and offers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all information is made available to all parties in electronic trading platforms, then transparency and market efficiency are improved, but control over information access and participation is lost
Solution Approach 1:
The patent implements differentiated information access rights where different participants in the trading session receive different levels of information. The host receives all trade parameters and offer information, the dealer receives trade parameters and invitee identities, while invitees receive only their own offer information or no information about other offers. This local quality differentiation resolves the contradiction by providing full information transparency to those who need it (host) while restricting information access for others (invitees) to maintain control.
Solution Approach 2:
The patent introduces a structured trading session framework with designated roles (host, dealer, invitee) that acts as an intermediary layer between complete information transparency and complete information secrecy. The host controls the session and receives all information, while the dealer and invitees receive filtered information appropriate to their roles. This intermediary structure enables controlled information sharing that maintains both transparency for the host and control over what other participants receive.
2Ease of operation
If traditional open electronic trading platforms are used, then ease of operation is maintained, but trading efficiency in limited group settings deteriorates
Solution Approach 1:
The patent implements dynamic role assignment and information sharing rules based on the specific trading session context. The system adapts information accessibility and participation rights according to the designated roles (host, dealer, invitee) and the nature of the trading instrument. This dynamic configuration enables the platform to optimize for controlled group trading efficiency while maintaining ease of operation through automated role-based access control rather than requiring complex manual configuration.
3Reliability
If information about all offers is shared with all invitees, then trading transparency is improved, but information leakage and loss of control increases
Solution Approach 1:
The patent applies local quality by granting different information access rights to different participants based on their roles. The host receives complete information about all offers and trade parameters to ensure transparency and enable informed decision-making. Meanwhile, invitees receive restricted information (either only their own offer or no offer information) to prevent information leakage. This differentiated approach maintains reliability for the host while preserving information control overall.
Data Source
AI summary
Systems and methods of the present disclosure enable an electronic transaction platform that receives a request to begin the electronic communication session identifying a preferred instrument feature relating to the target financial instrument to be traded. The electronic transaction platform receive instrument feature data relating to characteristics of financial instruments available to trade, and clusters, using a clustering machine learning model, the financial instruments into instrument feature groups based on the characteristics. The target financial instrument is classified with the clustering machine learning model into one of the instrument feature groups based on the preferred instrument feature to identify similar financial instruments. A dealer user is identified to act as an intermediate entity in a transaction with the similar financial instruments and a graphical user interface is presented to the user with active links to connect to the dealer user for each similar financial instrument.