Online advertising - Predicting Keyword Performance (Microsoft) - Patent Application - PRIOR ART REQUEST

Question

This Patent Application was given a "final rejection" by the US Patent Office. An applicant has several ways to keep an application in this state alive. They include a request for continuing examination. It just involves paying more fees and responding to the rejection. Appealing the rejection is another avenue. If nothing is done it will go abandoned six months from the final rejection.

Some of the grounds for rejection (can be seen in Public PAIR) are based on things the applicant themselves cited to the USPTO.

Thanks to YOU, the Ask Patents community, overly-broad claims have at least been narrowed. Follow @askpatents to block more overly-broad patent applications.

---

AN OVERBROAD PATENT ON PREDICTING ADVERTISER KEYWORD PERFORMANCE - This application from Microsoft seeks to patent the idea of...predicting keyword performance for an advertiser by how the keyword has performed for similar advertisers! 10 minutes of your time can help narrow US patent applications before they become patents. Follow @askpatents on twitter to help.

QUESTION - Have you seen anything that was published before Dec 27, 2011 that discusses:

1. A method of predicting KEYWORD PERFORMANCE for an advertiser who has not previously bid on the keyword; and
2. Identifying SIMILAR ADVERTISERS and using that to predict the performance expected from the subject keyword;

If so, please submit evidence of prior art as an answer to this question.. We welcome multiple answers from the same individual.

EXTRA CREDIT - A reference to anything that meets all of the criteria to the question above AND ALSO use:

• EUCLIDIAN DISTANCE BETWEEN ATTRIBUTES BETWEEN ADVERTISERS to estimate similarity between advertisers; and

• CATEGORY, QUALITY SCORE, PAY-PER-CLICK, BID, ADVERTISER VERTICAL, GEOGRAPHIC LOCATION, DAY-TARGETING, DAY-PARTING, KEYWORDS IN COMMON to estimate the performance expected from the keyword.

TITLE: PREDICTION OF USER RESPONSE TO RECEIVED DATA

Summary: [Translated from Legalese into English] Within an online advertising system, a method of predicting keyword performance for an advertiser who has not previously bid on a keyword by identifying a similar advertiser who has used the same keyword and using the keyword’s previous performance to provide an expected result for the current advertiser.

• Publication Number: US 20130166371 A1
• Application Number: 13/337,709
• Assignee: Microsoft, Inc.
• Prior Art Date: Seeking prior Art predating Dec 27, 2011
• Open for Challenge at USPTO: Open through Dec 27, 2013

Claim 1 requires each and every step below:

{A METHOD} for predicting advertiser keyword performance indicator values, comprising:

1. receiving a keyword from a first advertiser, whereinthe first advertiser has not previously bid on the keyword;

2. identifying at least one other advertiser that is similar to the first advertiser and has previously bid on the keyword; and

3. calculating at least one predicted performance indicator value for the keyword for the first advertiser based upon at least one established performance indicator value of the keyword for the at least one other advertiser.

In English this means:

A method for detecting expected keyword performance for an advertiser, comprising:

1. Receiving from the advertiser a keyword which the advertiser has not previously bid on; and

2. Identifying a 2nd advertiser similar to the advertiser; and

3. Predicting the performance of the keyword (based on any metric) for the subject advertiser based on the performance of the keyword for the similar advertiser

Good prior art would be evidence of a system that did each and every one of these steps prior to the Dec 15, 2011.

You're probably aware of ten pieces of art that meet this criteria already... separately, the applicant is claiming using

• a EUCLIDIAN DISTANCE BETWEEN ATTRIBUTES BETWEEN ADVERTISERS to estimate similarity between advertisers; and

• CATEGORY, QUALITY SCORE, PAY-PER-CLICK, BID, ADVERTISER VERTICAL, GEOGRAPHIC LOCATION, DAY-TARGETING, DAY-PARTING, KEYWORDS IN COMMON to estimate the performance expected from the keyword.

---

"Predicting advertiser keyword performance indicator values” from Microsoft

---

What is good prior art? Please see our FAQ.

Want to help? Please vote or comment on submissions below. We welcome you to post your own request for prior art on other questionable US Patent Applications.

---

Answer 1

As answered by Joannes Vermorel above, see: Adobe SearchCenter+ Adds Keyword Performance Predictive Analytics:

"Adobe Systems Incorporated (Nasdaq:ADBE) today announced that Adobe® SearchCenter+, a comprehensive search marketing management system within the Adobe Online Marketing Suite, has added keyword performance predictive analytics through a partnering agreement with OptiMine Software, Inc. This agreement will enable search marketers to achieve significant increases in paid search performance (i.e. higher return on ad spend, increased leads, higher conversion rates, increased revenue, greater profit per keyword, etc.). Tests done with search marketers using OptiMine’s keyword modeling have shown improved performance of 25 percent or more."