Back to results
US 11,106,987 B2Granted
Forecasting systems
AssigneeiRuiz Technologies Ltd.
InventorIgnacio Ruiz
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeiRuiz Technologies Ltd.
InventorIgnacio Ruiz
Estimating the term…
A computer-implemented method of determining an approximated value of a parameter in a first domain is described. The parameter is dependent on one or more variables which vary in a second domain, and the parameter is determined by a function which relates sets of values of the one or more variables in the second domain to corresponding values in the first domain. The method is implemented on a computer system including a processor, and the method comprises: determining a plurality of anchor points in the second domain, wherein each anchor point comprises a set of values of the one or more variables in the second domain; evaluating, at each anchor point, the function to generate corresponding values of the parameter in the first domain; generating an approximation function to the function by fitting a series of orthogonal functions or an approximation to a series of orthogonal functions to the corresponding values of the parameter in the first domain; and using the approximation function to generate the approximated value of the parameter in the first domain.
A control system for configuring a system/device to accommodate a future state of the system/device or further events related to the system/device, the control system comprising:
A control system for configuring a system/device to accommodate a future state of the system/device or further events related to the system/device, the control system comprising:
A computer-implemented method of determining an approximated value of a parameter in a first domain, the parameter being dependent on one or more variables which vary in a second domain, and the parameter being determined via a function which relates sets of values of the one or more variables in the second domain to corresponding values in the first domain, the method being implemented on a computer system including a processor, and the method comprising:
A computer-implemented method of determining an approximated value of a parameter in a first domain, the parameter being dependent on one or more variables which vary in a second domain, and the parameter being determined by a function which relates sets of values of the one or more variables in the second domain to corresponding values in the first domain, the method being implemented on a computer system including a processor, and the method comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Computing arrangements based on specific mathematical models
Commerce: marketing; Price estimation or determination; Fundraising
Administration; Management: forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or…
Market modelling; Market analysis; Collecting market data: price or cost determination based on market factors
About 11 years 6 months of term left · ends 18 Apr 2038 (estimated)
The present invention concerns improved forecasting systems, in particular, but not exclusively to a system for accurately carrying out predictive functions using approximation techniques.
Predicting future values of parameters is desirable in many fields and endeavours, including molecular biology, oil and gas, structural engineering, financial modelling and weather forecasting. Typically, in these fields, the value of the parameters is dependent on a complex relationship between several underlying variable factors and sub-variables. Forecasting (i.e. determining future potential events with a probability associated with each of them) is useful as decisions and expectations can be made based on predictions. Also, such predictive analysis can result in useful feedback being provided to a control system to configure a system or device to accommodate the future state or events.
Predictive functions using approximation techniques are used in situations where a given parameter can only be determined by consideration of a group of functions where each function is determined based on multiple scenarios. The scale of computational effort required for this future behaviour simulation is so large, for example there may be millions of variable values requiring millions of approximation calculations, that even current state of the art computing platforms struggle to meet the desired level of accuracy and performance. For example, current forecasting systems may reduce the number of approximation calculations performed, thus reducing accuracy, or increase the amount of processing power used, thus increasing the electrical power and resource requirements of the system. The application of such predictive analysis techniques includes fields such as structural engineering, molecular biology weather forecasting, oil and gas and financial modelling.
FIG. 1 (8b) have already been described above by way of background, in which:
FIG. 1 is a schematic block diagram of a prior art forecasting system;
FIG. 2 is a schematic block diagram of a scenario module of the system of FIG. 1;
The present invention can be realised in many different ways and has been explained previously for many different applications. In the following description, a specific embodiment is described which is in the financial forecasting domain. The reason for illustrating the present invention using this embodiment is because the present invention can be described efficiently using some of the elements of a system for forecasting future price of an OTC contract which have already been described in the background section. Also, benchmarking results using the prior art system 100 and the forecasting system of the present embodiment can be carried out and these results have been provided towards the end of this specific description. However it is to be clearly appreciated that the present embodiment is exemplary only and the structure of the specific embodiment described herein can readily be adapted by the skilled person to work with any of the other areas of application mentioned in the introduction.
As described above, the step of determining the price parameter scenarios in the process 204 described in relation to FIG. 8(b) comprises evaluating the price parameter function 156 potentially quintillions of times and is the most computationally expensive part of the overall process 200 of determining counterparty credit risk metrics.
FIG. 9(a) shows a forecasting system 300 according to an embodiment of the present invention. The forecasting system 300 has substantially the same structure as the prior art forecasting system 100 shown in FIG. 1(a). However, the prior art price parameter module 106 described with reference to FIG. 6(a) is replaced in the current embodiment with an approximation module 302 to significantly reduce the computational time required to generate the required results of the forecast. The modules and database shown with dashed lines in FIG. 9(a) are substantially unchanged from the prior art forecasting system 100.