Electronic Trade Order Routing for Automated Execution Style Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current trading systems rely heavily on manual decision-making by traders, which slows down the trading process and compromises system efficiency, particularly in the IG corporate bond market, where high touch and low touch desks handle different types of orders with limited automation and scalability.
Innovation Solution
A smart order routing (SOR) algorithm that automatically recommends execution styles for trade orders based on historical patterns and market data, using a combination of implementation shortfall and propensity prediction models to optimize trade routing decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual decision-making is used by traders to execute trade orders, then trade execution can be customized based on expertise and market conditions, but trading speed and system efficiency are significantly slowed down
Solution Approach 1:
The system enables self-service by allowing the automated routing system to independently analyze market conditions, evaluate execution options, and make routing decisions without requiring manual trader intervention for each order, thereby maintaining customization while improving speed
Solution Approach 2:
The patent replaces the mechanical manual decision-making process with an automated electronic routing system that uses algorithms and machine learning models to evaluate trade orders and determine execution styles, eliminating the bottleneck of human review while preserving expert-level decision quality
2Reliability
If manual trade execution decisions are made for all orders, then each trade can receive individualized attention and expertise, but system scalability and throughput are compromised
Solution Approach 1:
The system segments trade orders into different categories based on risk profile, size, and complexity characteristics. High-risk or complex orders are routed to human traders for specialized attention, while routine lower-risk orders are automatically routed through electronic channels, enabling the system to scale while maintaining execution quality for critical trades
Solution Approach 2:
The automated routing system serves multiple functions: it acts as a preliminary filter for all orders, provides routing recommendations to traders, and can execute certain orders autonomously. This multi-functionality allows the system to handle diverse order types and risk levels while maintaining scalability
3Productivity
If automated trading platforms are used without human intervention, then trading speed and system efficiency are improved, but the ability to handle complex or risky trades with expert judgment is reduced
Solution Approach 1:
The system applies different levels of automation to different orders based on their specific characteristics. Routine standardized orders receive full automated routing, while complex or high-risk orders are flagged for human trader review. This localized approach to automation quality maintains system efficiency for bulk orders while preserving expert judgment capability where needed
4Reliability
If high touch desks handle all trade orders manually, then comprehensive trader expertise is applied to each order, but system throughput and scalability are severely limited
Solution Approach 1:
The system dynamically adjusts the level of human involvement in the routing process based on real-time assessment of each order's characteristics. The routing algorithm continuously evaluates order attributes, market conditions, and trader availability to determine the optimal execution path, enabling the system to maintain high throughput while applying expert judgment dynamically where it adds most value
Data Source
AI summary
The present application generally relates to electronic trading systems, and more specifically to systems and methods for electronic trade order routing. A routing algorithm may generate an execution style recommendation for incoming IG corporate orders. For example, the style recommendation may be shown as a new column in the trading application dashboard that suggests a course of action to traders for each order. In one implementation, automatic decision making may occur based on the style recommendation.


