System and method for influencing recommender system
A system and method for implementing/influencing a recommender system which provides recommendations to users based on characteristics of certain trendsetters within a member population. The trendsetters are determined by studying historical adoption behavior of a group within the member population, or by reference to known indicia.
1. A method for suggesting items of interest to a community of online subscribers, comprising:
determining, with a network computing device, a first set of items that have been adopted by more than half the subscribers within the community of online subscribers;
computing an adoption rate for each online subscriber, wherein the adoption rate comprises:
aggregating each online subscriber's adoption score for at least one item of the first set of items to produce an aggregated adoption score, and
dividing the aggregated adoption score by a number of items from the first set of items actually adopted by the online subscriber;
identifying respective subscribers within the community of online subscribers by ranking each online subscriber's adoption rate;
classifying a predefined percentage of the respective subscribers as trendsetters;
measuring, with a network computing device, a second adoption rate by the trendsetters for a particular item of a second set of items; and
making recommendations by the recommender system for the first particular item of the second set of items based on a value of the second adoption rate.
2. The method of claim 1 wherein the second set of items include at least one of human readable content, products and services.
3. The method of claim 1 , wherein a trendsetter is selected by identifying an item from the first set of items that achieves a greater than 50% adoption rate within the community of online subscribers, and then identifying the first N persons who adopted such item.
4. The method of claim 1 , wherein said trendsetters are at least one of users purchasers, and renters of the first or second set of items.
5. The method of claim 1 , wherein the recommender system uses a collaborative filtering algorithm, and said trendsetters are weighted more heavily than other subscribers within the community of online subscribers.
6. The method of claim 1 , further comprising:
identifying trend rejecters for said first particular item; and
modifying a recommender system recommendation by reducing contributions by said trend rejecters for said particular item.
7. The method of claim 1 , further comprising:
identifying a second particular item of the second set of items rejected by said trendsetters; and
modifying a recommendation for said second particular item based on a rejection rate exhibited by said trendsetters.
8. The method of claim 1 , wherein the adoption score is a measure of how a person adopted an item.
9. A method for suggesting items of interest to a community of online subscribers comprising:
determining, with a network computing network device, a first set of items that have been adopted by more than half the subscribers within the community of online subscribers;
computing an adoption rate for each online subscriber, wherein the adoption rate comprises:
aggregating each online subscriber's adoption score for at least one item of the first set of items to produce an aggregated adoption score, and
dividing the aggregated adoption score by a number of items from the first set of items actually adopted by the online subscriber;
identifying respective subscribers within the community of online subscribers by ranking each online subscriber's adoption rate;
classifying a predefined percentage of respective subscribers of the ranked subscriber adoption ratings as trendsetters;
measuring, with a network computing device, a trendsetter rating for a first particular item of a second set of items provided by said trendsetters;
modifying a user rating for said first particular item for other subscribers based on said trendsetter rating and;
using said trendsetter rating to generate recommendations to a user requesting a suggestion from an electronic recommender system.
10. The method of claim 9 , further comprising:
identifying a second particular item of the second set of items rejected by said trendsetters; and
generating a recommendation for said second particular item based on a rejection rate exhibited by said trendsetters.
11. The method of claim 9 , wherein said trendsetters are associated with web pages on the Internet.
12. The method of claim 9 , wherein the adoption score is a measure of how a person adopted an item.
13. A system for providing recommendations of items of interest to a community of online subscribers, comprising:
a network computing device executing software module which is configured to:
determine a first set of items that have been adopted by more than half of subscribers within the community of online subscribers;
compute an adoption rate for each online subscriber, wherein the adoption rate comprises:
aggregating each online subscriber's adoption score for at least one item of the first set of items to produce an aggregated adoption score, and
dividing the aggregated adoption score by a number of items from the first set of items actually adopted by the online subscriber;
identify respective subscribers within the community of online subscribers by ranking each online subscriber's adoption rate;
classify a predefined percentage of the respective subscribers of the ranked subscriber adoption ratings as trendsetters;
measure a second adoption rate by the trendsetters for a first particular item of a second set of items; and
provide recommendations for said particular item of the second set of items based on a value of second adoption rate.
14. The system of claim 13 , wherein said trendsetters are at least one of users, purchasers, and renters of the first set of items.
15. The system of claim 13 wherein said software module includes a collaborative filtering algorithm in which said trendsetters are weighted more heavily than other subscribers within the community of online subscribers.
16. The system of claim 13 , wherein the software module is further configured to identify trend rejecters for said first particular item, and provide a recommendation by reducing contributions by said trend rejecters for said particular item.
17. The system of claim 13 , further comprising:
the network computing device executing a second software module for adjusting advertising presented with said recommendations based on adoption rate.
18. The system of claim 13 , wherein the trendsetters are associated with individual web pages.
19. The method of claim 13 , wherein the adoption score is a measure of how a person adopted all item.