Fractional Share Allocation via Neural Network Weight Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current asset offering systems cannot allocate fractional shares, and algorithms face constraints when optimizing distributions among numerous recipients due to the limitation of whole shares, leading to computational intractability in evaluating utility across large numbers of recipients.
Innovation Solution
A share allocation computing device with a neural network model that assigns candidate investors to nodes, adjusts weights using machine learning, and allocates fractional shares based on fitness values, enabling optimized distribution and computational tractability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If fractional shares are allocated to individual investors, then the precision of asset distribution is improved, but the complexity of the offering system increases
Solution Approach 1:
The patent introduces a share allocation computing device as an intermediary between the offering system and individual investors. This device automatically evaluates investor profiles, predicts investor behavior, and allocates fractional shares using computational models, thereby enabling precise fractional share distribution without manually increasing system complexity
Solution Approach 2:
The patent changes the fundamental parameter of share allocation from discrete whole shares to continuous fractional shares. By implementing a computational model that evaluates multiple investor parameters (profile data, predicted behavior, offering characteristics) and outputs precise fractional allocations, the system achieves high precision distribution while managing complexity through automation
2Measurement precision
If computational models evaluate utility across large numbers of investors, then the quality of allocation optimization is improved, but the computational tractability deteriorates
Solution Approach 1:
The patent segments the computational evaluation process into distinct model layers: a first model layer evaluates investor profiles and predicts investor behavior, while a second model layer evaluates offering characteristics and determines optimal allocations. This segmentation allows the system to process large numbers of investors by breaking down the complex utility evaluation into manageable computational stages
Solution Approach 2:
The patent performs preliminary computational actions by pre-evaluating investor profiles and predicting investor behavior before the actual offering allocation. The computational model pre-processes investor data, assigns weights based on predicted behavior, and prepares allocation recommendations in advance, thereby reducing the computational burden during the actual offering process and improving overall tractability
Data Source
AI summary
A share allocation (SA) computing device includes a processor in communication with a database. The processor is configured to execute a computational model including a plurality of model layers. The plurality of model layers includes a fractional node layer configured to assign each candidate investor of a plurality of candidate investors to a corresponding node. Each node is associated with a weight, and the nodes define an interconnected neural network. The fractional node layer is also configured to apply a machine learning algorithm configured to adjust the weights of the nodes in response to respective fitness values input to the nodes, and convert the adjusted weight for each node into a corresponding fraction. The fractional node layer is further configured to allocate, to each candidate investor, a respective fractional share of an offering, the fractional share corresponding to the fraction associated with the corresponding node.