{"id":4855,"date":"2026-08-08T22:48:38","date_gmt":"2026-08-08T19:48:38","guid":{"rendered":"https:\/\/ivitskiy.com\/blog\/adworld-experience-2024\/"},"modified":"2026-08-09T00:32:33","modified_gmt":"2026-08-08T21:32:33","slug":"adworld-experience-2024","status":"publish","type":"post","link":"https:\/\/ivitskiy.com\/blog\/en\/adworld-experience-2024\/","title":{"rendered":"30x Conversions with N-Gram Negative Keywords: Igor Ivitskiy at Adworld Experience 2024"},"content":{"rendered":"\n
In short:<\/strong> A B2C SaaS client had been stuck at 50 conversions per day for two years. Igor Ivitskiy exported the full search-term report, ran an n-gram profitability analysis in Excel, excluded thousands of unprofitable words as negative keywords<\/a> and re-launched on broad match<\/a>. Within one week, the account reached 1,500 conversions per day \u2014 a 30x jump at a lower CPA. The case won first place in the PPC Caesars Award 2024.<\/div>\n\n\n\n

Adworld Experience 2024<\/a> took place in Bologna, Italy, on October 17\u201318, 2024. Igor presented this English-language PPC case at Europe\u2019s largest conference of real PPC cases.<\/p>\n\n\n\n

The case study, \u201c30x Conversions for B2C SaaS Through In-Depth Keyword Research<\/a>\u201d<\/strong>, shows how word-level profitability analysis of search terms \u2014 n-grams, broad match and thousands of negative keywords \u2014 broke a two-year growth ceiling in one week. The speaker, Igor Ivitskiy<\/a>, is a Google Ads expert and \u201cThe Google Ads Scientist\u201d \u2014 a PhD mathematician who applies optimization science to Google & YouTube Ads.<\/p>\n\n\n\n

\n
\n
Before<\/strong><\/div>\n
<\/div><\/div>\n
50 conversions\/day<\/div>\n<\/div>\n
\n
After<\/strong><\/div>\n
<\/div><\/div>\n
1,500 conversions\/day<\/div>\n<\/div>\n<\/div>\n
Source: Adworld Experience 2024 case, Igor Ivitskiy.<\/div>\n\n\n\n
\"Igor
Igor Ivitskiy presenting the award-winning PPC case at Adworld Experience 2024, Bologna<\/figcaption><\/figure>\n\n\n\n

How the n-gram method works<\/h2>\n\n\n\n

The starting hypothesis was that only a small fraction of potential users purposely search for services such as car-plate, phone-number or property-address reports, although the service can be useful to almost anyone. About 70% of search volume sits in the long tail \u2014 terms so rare that they barely show up in reports.<\/p>\n\n\n\n

Instead of bidding on particular queries, Igor bid on the broad market and excluded irrelevant traffic with negative keywords. The analysis turns the search-term report into word-level profitability data, then uses the unprofitable words as negatives and the most profitable words as new broad-match keywords<\/a>.<\/p>\n\n\n\n

\n
1<\/span>Export search terms<\/strong>
Export all search terms with their cost and profit data.
Check: include cost and profit for the full report.<\/div><\/div>\n
2<\/span>Split into n-grams<\/strong>
Break every term down into individual words, so each word becomes a unit of analysis.
Check: separate every term into individual words.<\/div><\/div>\n
3<\/span>Calculate profitability<\/strong>
For every word, total its contribution to cost and revenue, then sort by profitability.
Check: identify both unprofitable and most profitable words.<\/div><\/div>\n
4<\/span>Build and launch<\/strong>
Use unprofitable words as negatives, profitable words as broad-match keywords, then launch the broadest possible combinations.
Check: the account bids on the broad market while the waste is already excluded.<\/div><\/div>\n<\/div>\n
Source: Adworld Experience 2024 case, Igor Ivitskiy.<\/div>\n\n\n\n

How I filter negative keywords<\/a><\/strong><\/p>

I select negative keywords by money and by audience response, not by intuition. Spend and response determine whether a word stays, while the final decision follows the project\u2019s overall profitability rather than the cosmetic appeal of any single metric.<\/p><\/section>\n\n\n\n

This method works not as a one-off trick, but as a repeatable discipline of learning from the account\u2019s own data. Our school\u2019s free webinar is devoted to this same way of working.<\/p>\n\n\n\n\n\n\n\n

Key insights<\/h2>\n\n\n\n