Systems and methods for response rate determination and offer selection

Patent metadata

Field	Value
Publication number	US-2016189176-A1
Application number	US-201414583709-A
Country	US
Kind code	A1
Filing date	Dec 28, 2014
Priority date	Dec 28, 2014
Publication date	Jun 30, 2016
Grant date	—

Abstract

Methods and systems for calculating a current response rate to an offer are disclosed. Examples of offers include but are not limited to design options for a web page and scripts used by operators in a call center. An offer may be served multiple times to one or more users and the current response rate may be determined for a point in time. The method may comprise obtaining estimates of response rate in successive iterations of response rate estimation. Each estimate may be determined over a period of time ending at the point in time, and each estimate may be determined over a larger period of time than the previous estimate. A range of uncertainty may be defined by upper and lower bounds for the estimates of response rate, with at least the first estimate being within the range of uncertainty. Each estimate may be compared to one or both of the upper and lower bounds and the result of the comparison may be used in the selection of one of the estimates as the calculated current response rate.

First claim

What is claimed is:

1 . A method of calculating a current response rate at a point in time to an offer that is served multiple times to one or more respondents, the method comprising, in one or more processors in a computing system:
obtaining estimates of response rate in successive iterations of response rate estimation each estimate being determined over a period of time ending at said point in time, and each estimate being determined over a larger period of time than the previous estimate; determining a range of uncertainty defined by upper and lower bounds for the estimates of response rate, wherein at least the first of said estimates is within the range of uncertainty; comparing each estimate of response rate to one or both of the upper and lower bounds; and using the results of the comparing to select one of the estimates as the current response rate.

2 . The method of claim 1 wherein said determining comprises determining a range of uncertainty at each iteration of response rate estimation.

3 . The method of claim 2 wherein the upper and lower bounds are maximum lower bound and minimum upper bound one or both of which are determined at previous iterations of response rate estimation.

4 . The method of claim 1 wherein the upper bound or lower bound or both are derived from the standard error of the response rate estimation.

5 . The method of claim 1 comprising incrementing the time period between successive response rate estimations.

6 . The method of claim 1 comprising incrementing the number of serves of the offer between successive response rate estimations.

7 . The method of claim 1 in which said using comprises selecting the first estimate that is outside the range of uncertainty or equal to one of the bounds of the range of uncertainty.

8 . The method of claim 1 in which said using comprises selecting the estimate before the first estimate that is outside the range of uncertainty.

9 . The method of claim 1 in which said using comprises selecting an estimate that is within a predetermined margin of one of the upper and lower bounds.

10 . The method of claim 1 comprising using the time period corresponding to the selected estimate to estimate when a change in response rate for the offer occurred.

11 . A method of selecting an offer to be served amongst a set of offers using one or more processors in a computing system, wherein the method of selecting comprises:
receiving a request for a selection of an offer from the set of offers; determining for each offer of the set of offers a current response rate corresponding to the current time; using the determined current response rate to select which offer of the set of offers to serve; and outputting a signal identifying the selected offer to cause the selected offer to be presented to a respondent; and wherein the determining a current response rate comprises: obtaining estimates of response rate in successive iterations of response rate estimation, each estimate being determined over a period of time ending at said current time, and each estimate being determined over a larger period of time than the previous estimate; determining a range of uncertainty for the estimates of response rate, wherein at least the first of said estimates is within the range of uncertainty; identifying when the estimated response rate is outside and selecting one of the estimates as the current response rate based on said identifying.

12 . The method of claim 11 comprising:
for at least one offer of the set of offers, determining a corresponding serve proportion using the determined current response rate; and
using a random selection process to select an offer to be served in which the determined serve proportion is used as a weighting factor for the corresponding offer.

13 . The method of claim 12 wherein the determining of serve proportion is performed before each selection of an offer or at regular intervals of time or number of serves.

14 . The method of claim 12 comprising:
if said random selection process selects an offer for which a serve proportion has been determined, serving said selected offer, and
if said random selection process does not select an offer for which a serve proportion has been determined, using a further selection process to determine which offer of said set of offers is to be served and serving an offer determined by said further selection process.

15 . The method of claim 14 in which the further selection process uses an upper confidence bound algorithm or selects the offer with the highest response rate.

16 . The method of claim 12 further comprising identifying the offer with the highest response rate, wherein said at least one offer is other than the offer with the highest response rate

17 . The method of claim 12 wherein determining a serve proportion comprises:
determining the number of serves required to achieve an upper confidence bound “UCB” for said at least one offer that is less than or equal to the UCB for the offer with the highest response rate.

18 . A system for determining a current response rate at a point in time to an offer that is served multiple times to one or more respondents, the system comprising:
a data store logging serves of the offer prior to the point in time, and corresponding responses; and one or more processors configured to use data in the data store to: perform successive iterations of response rate estimation to provide successive estimates of response rate, each estimate being determined over a period of time ending at said point in time, and each estimate being determined over a larger period of time than the previous estimate; determine a range of uncertainty defined by upper and lower bounds for the estimates of response rate, wherein at least the first of said estimates is within the range of uncertainty; compare each estimate of response rate to one or both of the upper and lower bounds; and use the results of the comparing to select one of the estimates as the current response rate.

19 . A system as claimed in claim 18 wherein the one or more processors are further configured to:
carry out said estimation, determination, comparison and selection to determine current response rates for each offer of a set of offers;
receive a request for a selection of one offer of the set of offers;
use the current response rates to select one of the offers; and
output a signal identifying the selected offer to cause the selected offer to be presented to a respondent.

20 . A system as claimed in claim 19 wherein using the current response rates to select one of the offers comprises:
for at least one of the offers of the set of offers determining a corresponding serve proportion that depends on the current response rate; and
using a random selection process to select an offer to be served in which the determined serve proportion is used as a weighting factor for the corresponding offer.

Assignees

• Nice Systems Ltd

Inventors

• Newnham Leonard Michael

Classifications

• G06Q30/00

  Commerce · CPC title

• G06Q30/0202 Primary

  Market predictions or forecasting for commercial activities · CPC title