US-12620032-B2 - Dynamically-generated electronic database for portfolio selection

US12620032B2US 12620032 B2US12620032 B2US 12620032B2US-12620032-B2

Abstract

A system for creating a financial instrument selection, sharing the selection, and executing trade instructions thereof: a selector engine for creating selection parameters according to a statistical model for weighting desirability of financial instruments combined with entered user selection preferences or objectives for financial instruments, creating investment portfolios of financial instruments based on the selection parameters, and converting the investment portfolios data to output data representing trade instructions of financial instruments; a deep learning decision engine providing predicative input data and an investment sharing and democratization and portfolio monitoring module providing peer investment portfolio shared data input to the selector engine; and an execution platform for executing the trade instructions, the execution platform including electronic selection limiters to prevent execution of specific trades based on electronic flags computed from electronic checks relating to the amounts and types of the trades.

Inventors

Kim Hwa LIM

Assignees

Kim Hwa LIM

Dates

Publication Date: 20260505
Application Date: 20240716
Priority Date: 20170508

Claims (10)

1 . A system for autonomously creating one or more investment portfolios of selected financial instruments, sharing the investment portfolios, and executing trade instructions thereof, comprising: a selector engine comprising a first computer processor configured for: creating selection parameters used in selections of financial instruments according to a statistical model representing selection desirability of financial instruments combined with entered user selection preferences for the selections of financial instruments; creating the one or more investment portfolios of financial instruments selected based on the selection parameters, a factor weight to each of the selection parameters, and a weighting of each of the financial instruments selected in each of the investment portfolios; and converting the investment portfolios data to output data representing the trade instructions of financial instruments; wherein input to the selector engine for setting the selection parameters created comprising one or more of financial data, analysts' reports, accounting data, news data, corporate data, trading data, and sustainability factor data; an execution platform comprising a second computer processor configured for receiving the output data of the selector engine and autonomously executing the trade instructions represented by the output data; an investment sharing and democratization module comprising a third computer processor configured for: accessing one or more invention portfolio data of other users of the system to generate a specified target investment portfolio adjustable by a degree of imitation of the one or more invention portfolio data of the other users; and generating from the specified target investment portfolio an additional input to the selector engine for setting the selection parameters; a sustainable investing module comprising an eighth computer processor configured to provide the sustainability factor data as input to the selector engine for setting the selection parameters so to optimize the investment portfolios in terms of sustainability and returns on investment while minimize transaction costs and risks; and a deep learning decision engine configured to optimize the investment portfolios by estimating one or more of the factor weights to the selection parameters and the weightings of the financial instruments selected for the investment portfolios; wherein the deep learning decision engine comprises a Heirarchical Risk Parity (HRP) model employed in the estimation of the weightings of the financial instruments selected for the investment portfolios.
2 . The system of claim 1 , wherein the HRP model is trained to: organize the financial instruments selected in each of the investment portfolios into a plurality of hierarchical clusters arranged in a logical tree structure according to similarity among the financial instruments such that the hierarchical clusters logically mimic real-life interactions between the financial instruments and that similar financial instruments are placed close to each other and dissimilar financial instruments are placed far apart; compute a volatility for each of the hierarchical clusters; and estimate one or more of the weightings of the financial instruments selected based on the volatility of each of the hierarchical clusters under a recursive bisection operation in which weights are assigned in a top-down recursive manner following the logical tree structure.
3 . The system of claim 1 , wherein the deep learning decision engine is configured to employ a nonlinear autoregressive recurrent neural network (NARX); wherein the NARX is trained to estimate one or more of the factor weights to the selection parameters using past estimated factor weights and other contemporaneous variables including trade volumes and rates of price change of financial instruments.
4 . The system of claim 1 , wherein the deep learning decision engine is configured to employ a long short-term memory (LSTM) neural network; wherein the LSTM is trained to estimate one or more of the factor weights to the selection parameters using previous time steps in a time series of sequence of the factor weights.
5 . The system of claim 1 , further comprising: a leads tracking, ideas passporting and revenue split module comprising a fourth computer processor configured for: tracking leads including one or more of targeted electronic communications, online advertisements, social media postings, and click-throughs thereof promoting a investment portfolio allowed to be licensed; tracking licensing activities of the investment portfolio allowed to be licensed; passporting the investment portfolio allowed to be licensed to a licensee entity; determining a portion of a licensing fee generated from the investment portfolio allowed to be licensed according to a contributor ratio.
6 . The system of claim 1 , further comprising: a portfolio modeler comprising a fifth computer processor configured for executing a performance simulation of one of the investment portfolios; and a portfolio stress test engine comprising a sixth computer processor configured for introducing one or more market stress scenarios in the performance simulation of the investment portfolio by the portfolio modeler.
7 . The system of claim 1 , further comprising a portfolio monitoring engine comprising a seventh computer processor configured for: continuously monitoring market prices of one or more financial instruments in the one or more investment portfolios; generating a take profit trade order signaling a sale of a financial instrument having market price reaching at or above a defined take profits level price; continuously calculating a stop losses sell-trigger price and a stop losses limit sell price of a financial instrument, wherein the stop losses sell-trigger price and the stop losses limit sell price move in proportion with a rising market price of the financial instrument, and wherein the stop losses sell-trigger price and the stop losses limit sell price remain unchanged with a falling market price of the financial instrument; and generating a stop losses trade order signaling a sale of a financial instrument having market price reaching at or below stop losses sell-trigger price; wherein the portfolio monitoring engine prevents accidentally short-selling a financial instrument due to volatile market when both take profits level price and stop losses limit sell price are set; wherein when either the take profit trade order or stop losses trade order on a financial instrument is fully executed, any remaining pending trade order on the financial instrument is canceled; wherein when either the take profit trade order or stop losses trade order on a financial instrument is partially executed, any remaining pending trade order on the financial instrument is reduced proportionately by the partially executed amount; and wherein when either the take profit trade order or stop losses trade order on a financial instrument is canceled before execution, any remaining pending trade order on the financial instrument is canceled.
8 . The system of claim 1 , further comprising an Explainable Artificial Intelligence module configured for: explaining a first deviation between an actual return and a mean predicted return of each of the investment portfolios; and explaining a second deviation between a predicted return at any point in time and the mean predicted return of each of the investment portfolios.
9 . The system of claim 1 , wherein the investment sharing and democratization module is further configured for: matching and suggesting investment portfolios and strategies to users; allowing an investment portfolio of a creator to be licensed by one or more licensees, and followed by one or more followers; propagating changes in the investment portfolio allowed to be licensed made subsequently by the creator to its followers; allowing referral by an influencer the investment portfolio allowed to be licensed to followers; tracking each of the users' contributions to fees generated; computing rewards for the users; reconciling and splitting the fees generated to the users who contributed to the fees generated according to an agreed ratio.
10 . The system of claim 9 , further comprising an Explainable Artificial Intelligence module configured for: explaining a first deviation between an actual revenue and a mean predicted revenue of licensing fees generated from an investment portfolio allowed to be licensed; and explaining a second deviation between a predicted revenue at any point in time and the mean predicted revenue of licensing fees generated from the investment portfolio allowed to be licensed.

Description

CROSS-REFERENCE WITH RELATED FIELD The present application is a continuation-in-part application of U.S. patent application Ser. No. 17/585,445 filed Jan. 26, 2022; which is a continuation-in-part application of U.S. patent application Ser. No. 16/611,860 filed Nov. 8, 2019; the disclosures of which are incorporated by reference in their entirety. FIELD OF THE INVENTION The present invention relates generally to improvements in electronic processing systems, particularly, electronic databases used for determining selections from real-time-updated electronic exchanges. The novel electronic database structure is dynamically generated for selection of financial instruments with user specified inputs. BACKGROUND Current techniques for achieving financial goals by automatically creating an optimal financial instruments portfolio are limited. Databases may be based solely on various market factors with no mechanism for customization based on various user selection preferences or user needs. Automatic portfolio selection is typically limited to exchange-traded funds (ETFs) in which the financial instruments selected match those of a particular exchange, linking the portfolio performance solely to the performance of that index without a clear link to how to achieve the financial goals. Alternatively, investors may purchase mutual funds in which a large portfolio management entity selects financial instruments for inclusion based on the portfolio management entity's knowledge and research. These funds do not allow customization of the underlying securities based on individual investor preference such as a desire to support green technology or avoiding financial instruments originating in certain countries. Users are also not able to combine investment funds in a way that directly enables them to achieve their goals optimally. Individual investors typically do not possess all the information to create an optimal portfolio and to rebalance it consistently in the future. Due to the fact that financial instruments are purchased on a real-time-updated exchange, it is technically impossible for human being to evaluate all of the factors needed to optimize and manage a financial instrument portfolio in real time. As used herein, the term “financial instrument” includes stocks, bonds, contracts related to the purchase of stocks or bonds, packages of capital, currency, funds, or any assets that can be traded by means of a representation on an electronic exchange. Due to the ever-changing user's financial requirements and the technical problem of being unable to process all the information needed to create and maintain a customized portfolio in real time, there is a need in the art to dynamically create an electronic database that evaluates various variables in real time to enable selection from a real-time electronic exchange based on attributes identified by the dynamically-created electronic database. SUMMARY OF THE INVENTION The present invention relates to a system, including an electronic database, and a method for executing a selection from a dynamically-generated electronic database. The database includes a plurality of selection parameters created according to statistical models for weighting desirability of financial instruments combined with user entered selection preferences for financial instruments. Each financial instrument is electronically associated with a dynamic electronic label indicating whether the financial instrument is restricted for selection at least in part based upon user entered selection preferences. The selection parameters are electronically converted by a selector engine to electronic output; the selector engine electronic output can be validated based on previously determined outcome parameters associated with past outcomes for the financial instruments in the electronic output of the selector engine. A computer processor is configured for executing external selections from a real-time updating external electronic exchange database based on the electronic output of the selector engine, the computer processor including electronic selection limiters to prevent execution of external selections based on electronic flags computed from electronic checks relating to the amount and type of external selections. BRIEF DESCRIPTION OF THE DRAWINGS Embodiments of the invention are described in more details hereinafter with reference to the drawings, in which: FIG. 1 schematically depicts an electronic processing system including dynamically-created electronic data storage in accordance to one embodiment of the present invention; FIG. 2 schematically depicts various details of the electronic processing system as shown in FIG. 1; FIG. 3 schematically depicts an external data filter in the electronic processing system as shown in FIG. 1; FIG. 4 schematically depicts a portfolio construction engine in the electronic processing system as shown in FIG. 1; FIG. 5 schematically depicts a decision flow of a proc