Systems and methods for response curve estimation for distribution of data elements on an electronic network

A computer-implemented method of estimating response curves associated with the distribution of graphical data elements on an electronic network, the method comprising the following operations performed by one or more processors:

• determining at least one input-output point, comprising an input value and a corresponding output value, the input value and corresponding output value corresponding to the distribution of graphical data elements on the electronic network;
• transforming the input value of the at least one input-output point based on a range of input values;
• determining, based on the transformed at least one input value, values along a response curve to obtain a curve weight factor;
• transforming a second input value based on the range of valid input values;
• determining, based on the second transformed input value, values along the response curve and the first derivative of the response curve, to obtain an estimated output value and estimated output rate associated with the second input value;
• and
• redetermining the response curve based on the determined curve weight factor, estimated output value, and estimated output rate.

The method of claim 223, wherein the exchange associated with the distribution of graphical data elements on the electronic network comprises:

• receiving one or more exchange bids associated with one or more graphical data elements;
• determining the highest received exchange bid;
• and
• determining impression placements for graphical data elements associated with the highest exchange bid.

The method of claim 223, further comprising:

• determining one of a pacing or a delivery goal associated with distribution of the graphical data elements on the electronic network;
• determining a number of impressions needed to satisfy the determined goal;
• and
• determining, using the response curve, at least one exchange bid associated with the determined number of impressions.

A non-transitory computer-readable storage medium containing instructions for estimating response curves associated with the distribution of graphical data elements on an electronic network that, when executed by at least one electronic processor, causes the at least one electronic processor to perform the following operations:

• determining at least one input-output point, comprising an input value and a corresponding output value, the input value and corresponding output value corresponding to the distribution of graphical data elements on the electronic network;
• transforming the input value of the at least one input-output point based on a range of input values;
• determining, based on the transformed at least one input value, values along a response curve to obtain a curve weight factor;
• transforming a second input value based on the range of valid input values;
• determining, based on the second transformed input value, values along the response curve and the first derivative of the response curve, to obtain an estimated output value and estimated output rate associated with the second input value;
• and
• redetermining the response curve based on the determined curve weight factor, estimated output value, and estimated output rate.

A system for estimating response curves, comprising:

• at least one electronic processor;
• and
• a storage device that stores instructions that, when executed by the at least one electronic processor, causes the at least one electronic processor to perform a method for estimating response curves associated with the distribution of graphical data elements on an electronic network comprising:
• determining at least one input-output point, comprising an input value and a corresponding output value, the input value and corresponding output value corresponding to the distribution of graphical data elements on the electronic network;
• transforming the input value of the at least one input-output point based on a range of input values;
• determining, based on the transformed at least one input value, values along a response curve to obtain a curve weight factor;
• transforming a second input value based on the range of valid input values;
• determining, based on the second transformed input value, values along the response curve and the first derivative of the response curve, to obtain an estimated output value and estimated output rate associated with the second input value;
• and
• redetermining the response curve based on the determined curve weight factor, estimated output value, and estimated output rate.