Patents by Inventor Alan Z. Zhao
Alan Z. Zhao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11861666Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: GrantFiled: March 31, 2021Date of Patent: January 2, 2024Assignee: Toast, Inc.Inventors: Pearse J. O'Flynn, Hardeep K. Gill, Alan Z. Zhao
-
Patent number: 11775969Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: GrantFiled: March 31, 2021Date of Patent: October 3, 2023Assignee: Toast, Inc.Inventors: Martin Kressirer, Binghuan Zhang, Alan Z. Zhao
-
Patent number: 11587092Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: GrantFiled: March 31, 2021Date of Patent: February 21, 2023Assignee: Toast, Inc.Inventors: Pearse J. O'Flynn, Hardeep K. Gill, Alan Z. Zhao
-
Patent number: 11562425Abstract: A system for automated origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor generates prices for capital product offers to subscribers of a point-of-sale (POS) subscription service, where the prices are generated by employing probability of default (PD) values that are derived from historical POS data corresponding to each of the subscribers. The revenue forecaster is coupled to the rate processor and is configured to employ the configured to employ the historical POS data and locations of establishments corresponding to the each of said subscribers to predict future POS data for the establishments corresponding to the each of the subscribers, and to employ the future POS data to generate predicted total revenues corresponding to the each of the subscribers over a payback period.Type: GrantFiled: May 8, 2019Date of Patent: January 24, 2023Assignee: Toast, Inc.Inventors: Kevin A. Vo, Jared J. Rand, Alan Z. Zhao, Alexander H. Hails
-
Patent number: 11532042Abstract: A system for automated origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor generates prices for capital product offers to subscribers of a point-of-sale (POS) subscription service, where the prices are generated by employing probability of default (PD) values that are derived from historical POS data corresponding to each of the subscribers. The revenue forecaster employs the historical POS data to predict future POS data for establishments corresponding to the each of the subscribers and employs the future POS data to generate predicted total revenues corresponding to the each of the subscribers over a payback period. The offer processor generates and transmits the capital product offers corresponding to the each of the subscribers, where the capital product offers comprise the payback period, the prices, and maximum dollar amounts that are a percentage of the predicted total revenues.Type: GrantFiled: May 8, 2019Date of Patent: December 20, 2022Assignee: Toast, Inc.Inventors: Clement Masson, Alexander H. Hails, Benjamin Gordon, Alan Z. Zhao
-
Publication number: 20220327546Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: ApplicationFiled: March 31, 2021Publication date: October 13, 2022Applicant: Toast, Inc.Inventors: Alan Z. Zhao, Benjamin C.W. Tang
-
Publication number: 20220318812Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: ApplicationFiled: March 31, 2021Publication date: October 6, 2022Applicant: Toast, Inc.Inventors: Pearse J. O'Flynn, Hardeep K. Gill, Alan Z. Zhao
-
Publication number: 20220318792Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: ApplicationFiled: March 31, 2021Publication date: October 6, 2022Applicant: Toast, Inc.Inventors: Martin Kressirer, Binghuan Zhang, Alan Z. Zhao
-
Publication number: 20220318862Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: ApplicationFiled: March 31, 2021Publication date: October 6, 2022Applicant: Toast, Inc.Inventors: Pearse J. O'Flynn, Hardeep K. Gill, Alan Z. Zhao
-
Publication number: 20220318832Abstract: A computer-implemented method for predicting interchange charges includes: retrieving a historical transactions set, where each completed transaction in the set includes transaction features, a bank identification number (BIN), and a corresponding true interchange code; transforming all BINs in the set into a corresponding plurality of BIN features that comprise probabilities; creating a first training set including all transaction features, all pluralities of BIN features, and all true interchange codes associated with the historical transactions set; training a random forest model using the first training set and generating a second training set including rounded BIN features, rounded transaction features, discrete ones of the transaction features, and the true interchange codes; training the random forest model using the second training set to generate a trained random forest model for prediction of the interchange codes; and executing the trained random forest model for new transactions to generate corresType: ApplicationFiled: March 31, 2021Publication date: October 6, 2022Applicant: Toast, Inc.Inventors: Martin Kressirer, Binghuan Zhang, Alan Z. Zhao
-
Patent number: 11100575Abstract: A system for automated origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor is configured to generate prices for capital product offers to subscribers of a point-of-sale (POS) subscription service, where the prices are generated by employing probability of default (PD) values that are derived from historical POS data corresponding to each of the subscribers, and where each historical POS datum comprises an indicator denoting a season of the year in which the datum was generated. The revenue forecaster employs the historical POS data to predict future POS data for establishments corresponding to the each of the subscribers and employs the future POS data to generate predicted total revenues corresponding to the each of the subscribers over a payback period.Type: GrantFiled: May 8, 2019Date of Patent: August 24, 2021Assignee: Toast, Inc.Inventors: Alan Z. Zhao, Kevin A. Vo, Jared J. Rand
-
Patent number: 10956974Abstract: A system for dynamic origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor is configured to generate a price for a capital product offer to a first subscriber of a point-of-sale (POS) subscription service, where the interest rate is generated by employing a probability of default (PD) value that is derived from historical POS data corresponding to all subscribers. The revenue forecaster is coupled to the rate processor and is configured to employ first historical POS data for an establishment corresponding to the first subscriber to predict future POS data using a neural network trained on the historical data corresponding to all subscribers, and to employ the future POS data to generate a predicted total revenue over a payback period for the first subscriber.Type: GrantFiled: May 8, 2019Date of Patent: March 23, 2021Assignee: Toast, Inc.Inventors: Jared J. Rand, Kevin A. Vo, Alan Z. Zhao
-
Publication number: 20200357058Abstract: A system for dynamic origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor is configured to generate a price for a capital product offer to a first subscriber of a point-of-sale (POS) subscription service, where the interest rate is generated by employing a probability of default (PD) value that is derived from historical POS data corresponding to all subscribers. The revenue forecaster is coupled to the rate processor and is configured to employ first historical POS data for an establishment corresponding to the first subscriber to predict future POS data using a neural network trained on the historical data corresponding to all subscribers, and to employ the future POS data to generate a predicted total revenue over a payback period for the first subscriber.Type: ApplicationFiled: May 8, 2019Publication date: November 12, 2020Inventors: Jared J. Rand, Kevin A. Vo, Alan Z. Zhao
-
Publication number: 20200357054Abstract: A system for automated origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor generates prices for capital product offers to subscribers of a point-of-sale (POS) subscription service, where the prices are generated by employing probability of default (PD) values that are derived from historical POS data corresponding to each of the subscribers. The revenue forecaster is coupled to the rate processor and is configured to employ the configured to employ the historical POS data and locations of establishments corresponding to the each of said subscribers to predict future POS data for the establishments corresponding to the each of the subscribers, and to employ the future POS data to generate predicted total revenues corresponding to the each of the subscribers over a payback period.Type: ApplicationFiled: May 8, 2019Publication date: November 12, 2020Inventors: Kevin A. Vo, Jared J. Rand, Alan Z. Zhao
-
Publication number: 20200357055Abstract: A system for automated origination of capital includes a rate processor, a revenue forecaster, and an offer processor. The rate processor is configured to generate prices for capital product offers to subscribers of a point-of-sale (POS) subscription service, where the prices are generated by employing probability of default (PD) values that are derived from historical POS data corresponding to each of the subscribers, and where each historical POS datum comprises an indicator denoting a season of the year in which the datum was generated. The revenue forecaster employs the historical POS data to predict future POS data for establishments corresponding to the each of the subscribers and employs the future POS data to generate predicted total revenues corresponding to the each of the subscribers over a payback period.Type: ApplicationFiled: May 8, 2019Publication date: November 12, 2020Inventors: Alan Z. Zhao, Kevin A. Vo, Jared J. Rand