# US 12,118,440 B2 · Automated order execution based on user preference settings utilizing a neural network prediction model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,440 B2 - Document ID: US12118440B2 - Status: Granted - Kind: B2 - Application number: 17/525,675 - Filed: 2021-11-12 - Published: 2022-04-21 - Granted: 2024-10-15 - Earliest claimed: 2020-05-07 - Assignees: Nowcasting.ai, Inc. - Applicants: Nowcasting.ai, Inc. - Inventors: Damian Ariel Scavo - Web page: https://patentgrep.com/patent/US12118440B2 ## CPC - G06N 20/00: Machine learning - G06F 16/215: Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors - G06F 16/2465: {Query processing support for facilitating data mining operations in structured databases} - G06F 16/254: {Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses} - G06F 16/258: {Data format conversion from or to a database} - G06F 16/285: {Clustering or classification} - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06Q 10/0633: Workflow analysis - G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis} - G06Q 30/0202: Market predictions or forecasting for commercial activities - G06Q 30/0282: Rating or review of business operators or products - G06Q 40/04: Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange - G06Q 40/06: Asset management; Financial planning or analysis - H04L 67/55: Push-based network services - G06N 3/084: Backpropagation, e.g. using gradient descent - G06Q 40/12: Accounting - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A computer-implemented method comprising receiving user preference information, based on the received user preference information, determining one or more user settings, processing data to determine a data condition, wherein, to determine the data condition, a plurality of alternate data inputs of different types are processed and normalized, and applied to a series of operations to generate a forecast having a degree of confidence, and the data condition is compared with third party information; providing an electronic notification indicative of the data condition to the user device, wherein the electronic notification includes the data condition compared with the third party information, a confidence indicator associated with the data condition, and a user prompt; in response to a single user input, the user device generating an instruction to execute the user request; and based on the instruction, executing the user request based on the determined one or more user settings. ## Claims ### Claim 1 A computer-implemented method comprising: receiving, by an online application associated with a user device, user preference information, and transmitting the user preference information to a server; determining, by the server, one or more user settings based on the received user preference information, wherein the one or more user settings comprises a price limit associated with the user preference information; training, by the server, a neural network prediction model using back propagation based on a plurality of alternate data inputs of different types associated with at least one company; applying, by the server, the neural network prediction model to new data from a plurality of data sources to generate a forecasted value of a critical indicator of the at least one company; determining, by the server, a data condition based on the forecasted value of the critical indicator of the at least one company; providing, by the server, an electronic notification indicative of the data condition to the user device based at least on the price limit of the one or more user settings, wherein the electronic notification includes a recommendation associated with the at least one company based on the data condition, and a user prompt to perform a user request in accordance with the recommendation; and executing, by the server, the user request in response to a single user input to the user device to select the user prompt, wherein executing the user request comprises automatically submitting an order, in accordance with the recommendation, to a brokerage service without further input from the user, wherein training the neural network prediction model using back propagation comprises: receiving, by the server, the plurality of alternate data inputs of different types from a plurality of alternate data providers, each of the plurality of alternate data providers having different types of data; standardizing, by the server, the plurality of alternate data inputs of different types received in real-time from the plurality of alternate data providers by performing filtering, de-duplication, normalization, and classification; receiving, by a modelling system for the neural network prediction model executed by the server, the standardized plurality of alternate data inputs of different types and published information of the at least one company, the modelling system employing neural networks to generate, as an output, the forecasted value of the critical indicator of the at least one company; receiving the output as the forecasted value of the critical indicator of the at least one company in real-time, comprising one or more revenue predictions; and performing, by the server, model validation using historical data associated with the at least one company using back propagation to periodically update the neural network prediction model; for the neural network prediction model being determined as not successfully validated, iteratively performing, by the server, retraining and updating of the neural network prediction model until the neural network prediction model is successfully validated. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the user preference information comprises risk information, financial information, or demographic information received via the online application, wherein determining the one or more user settings comprises determining the price limit based on at least one of the risk information, financial information, or demographic information received via the online application. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the risk information comprises a timing preference to execute the user request, a first frequency preference to execute the user request, an amount preference to execute the user request, a second frequency preference over a prescribed period to execute the user request, and a broker and market preference associated with one or more respective brokers and markers, to execute the user request, wherein executing the user request comprises executing the user request based on the timing preference, the first frequency preference, the amount preference, the second frequency preference, and the broker and market preference. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, further comprising providing the electronic notification to the user device via the online application on a periodic basis at a prescribed time based on the one or more user settings. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the data condition is associated with a plurality of entities provided in the user preference information, and the user prompt includes the user request for all of the plurality of entities. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the user device comprises an automobile or a home device, and the user prompt comprises an audio command. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the single user input is a privacy preserving gesture provided in the user preference information. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, further comprising determining the one or more user settings based on the user preference information associated with a risk profile, and upcoming or prior user events associated with a user financial condition. ### Claim 9 A computer-implemented method comprising: receiving, by an online application associated with a user device, user preference information, and transmitting the user preference information to a server; determining, by the server, one or more user settings based on the received user preference information, wherein the one or more user settings comprises a price limit associated with the user preference information; training, by the server, a neural network prediction model using back propagation based on a plurality of alternate data inputs of different types associated with at least one company; applying, by the server, the neural network prediction model to new data from a plurality of data sources to generate a forecasted value of a critical indicator of the at least one company; determining, by the server, a data condition based on the forecasted value of the critical indicator of the at least one company; providing, by the server, an electronic notification indicative of the data condition to the user device based at least on the price limit of the one or more user settings, wherein the electronic notification includes a recommendation associated with the at least one company based on the data condition, and a query to perform an automated user request in accordance with the recommendation; and executing, by the server, the automated user request in response to an automated determination to perform the automated user request based on the one or more user settings, wherein executing the automated user request comprises automatically submitting an order, in accordance with the recommendation, to a brokerage service without further input from the user, wherein training the neural network prediction using model back propagation comprises: receiving, by the server, the plurality of alternate data inputs of different types from a plurality of alternate data providers, each of the plurality of alternate data providers having different types of data; standardizing, by the server, the plurality of alternate data inputs of different types received in real-time from the plurality of alternate data providers by performing filtering, de-duplication, normalization, and classification; receiving, by a modelling system for the neural network prediction model executed by the server, the standardized plurality of alternate data inputs of different types and published information of the at least one company, the modelling system employing neural networks to generate, as an output, the forecasted value of the critical indicator of the at least one company; receiving the output as the forecasted value of the critical indicator of the at least one company in real-time, comprising one or more revenue predictions; and performing, by the server, model validation using historical data associated with the at least one company using back propagation to periodically update the neural network prediction model; for the neural network prediction model being determined as not successfully validated, iteratively performing, by the server, retraining and updating of the neural network prediction model until the neural network prediction model is successfully validated. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein the user preference information comprises risk information, financial information, or demographic information, wherein determining the one or more user settings comprises determining the price limit based on at least one of the risk information, financial information, or demographic information received via the online application. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the risk information comprises a timing preference to execute the automated user request, a first frequency preference to execute the automated user request, an amount preference to execute the automated user request, a second frequency preference over a prescribed period to execute the automated user request, and a broker and market preference associated with one or more respective brokers and markers, to execute the automated user request, wherein executing the automated user request comprises executing the automated user request based on the timing preference, the first frequency preference, the amount preference, the second frequency preference, and the broker and market preference. ### Claim 12 (depends on 9) The computer-implemented method of claim 9, further comprising providing the electronic notification to the user device via the online application on a periodic basis at a prescribed time based on the one or more user settings. ### Claim 13 (depends on 9) The computer-implemented method of claim 9, wherein the data condition is associated with a plurality of entities provided in the user preference information. ### Claim 14 (depends on 9) The computer-implemented method of claim 9, determining the one or more user settings based on the user preference information associated with a risk profile, and upcoming or prior user events associated with a user financial condition.