Pay-per-click (PPC) advertising creates new opportunities for businesses of all sizes to market to prospective customers in a more targeted and cost-efficient way, especially when compared to traditional ad mediums like print, billboards, and radio. These benefits are largely made possible by digital advertising networks like Google and Facebook that collect billions of data points from users to support effective demographic targeting.

For marketers, PPC advertising is a complicated and ongoing optimization problem. Using the data made available through major ad platforms, marketers work to design ads that effectively target prospects in the right demographic and with intentions that match campaign objectives. In this way, digital marketers are both creatives and data analysts.

The combination of N-gram analysis & PPC represents a powerful new analytical technique that PPC marketers can use to identify profitable keywords, write more effective ad text and optimize ad spending and marketing ROI.

For an overview of the PPC advertising model, check out our Pay-Per-Click Advertising Glossary Page where we explain how PPC works and the benefits it provides for growing a business.

Let’s review how PPC works in very simple terms:

1.       The advertiser creates an advertisement, a piece of creative that may include text and images and appear in different formats. Ads typically function as a link to a company website, landing page, special offer or some other type of content.
2.       Advertisers bid on keywords through an ad platform like Google or Facebook. A successful bid means that the ad will be shown to people who type that keyword into their Google or Facebook search engine.
3.       Ad platforms distribute ads to prospective customers in the target demographic.
4.       When a prospect clicks on the advertisement, they are redirected to the advertiser’s website or offer page.
5.       The ad platform collects data on how prospects interact with ads. Advertisers are charged each time a prospect from the target audience clicks on their advertisement.

Ad platforms collect many different types of data related to the performance of advertisements and keywords. The marketers that use these platforms must regularly check, investigate, review and analyze this data to measure the success of their advertising efforts and work towards increasing ad performance and ROI. For each marketing campaign, advertisers look at information such as:

•         Impressions: How many times was the ad displayed?
•         Clicks: How many clicks did the ad generate?
•         Average CPC: What was the average cost-per-click for the campaign?
•         Conversions: How many clicks converted to the desired action?

An ad campaign may include one or more pieces of creative and may target tens or hundreds of keywords. Within each campaign, ad platforms track the exact keywords that triggered each display of the advertisement. For advertisers, this means you can see exactly what keywords prospects are typing in before they see your ad. The next step is to analyze keyword data to discover which ones perform best. Typical metrics for keyword performance within an ad campaign include:

•         Clicks: How many clicks (total) were generated by searches for that keyword?
•         Cost: What was the total cost of all clicks generated?
•         CPC: What was the average cost-per-click for each keyword?
•         Conversion: How many conversions resulted from each keyword?
•         Conversion Rate: What was the conversion rate for each keyword?
•         ROI%: Which keywords provided the best ROI? Which ones are the most profitable to target?

Advertisers use this data to optimize keyword targeting for each campaign by selectively bidding on the most profitable keywords that demonstrate the best ROI.

N-gram analysis is a statistical method that advertisers can use to discover the most profitable keywords for a given ad campaign.

The definition for N-grams comes from natural language processing, (NLP) an area of machine learning application responsible for technologies like voice-to-text, speech recognition, language identification, and auto-correct. An N-gram is defined as a contiguous sequence of N words from a specified sample of text or speech.

For example, we can look at a simple text sample and turn it into N-grams. Our sample can be a basic sentence:

“The quick brown fox jumps over the lazy dog”

If we were to convert this sentence to 1-grams, we would have 9 of them:

1.       The
2.       Quick
3.       Brown
4.       Fox
5.       Jumps
6.       Over
7.       The
8.       Lazy
9.       Dog

If we converted the sentence to 2-grams, we would have eight of them:

1.       The quick
2.       Quick brown
3.       Brown fox
4.       Fox jumps
5.       Jumps over
6.       Over the
7.       The lazy
8.       Lazy dog

So, what’s the significance of reorganizing the data this way? Well, if we took a lot of query data for a single ad campaign, we would likely discover that certain keywords and phrases are present in many of the search terms that generated impressions for the campaign. N-gram analysis allows advertisers to see which of these keywords or phrases that reoccur within a campaign are best correlated with positive ad performance.

In N-gram analysis and PPC, advertisers look at all the keywords that generated impressions or clicks for a given ad campaign – these keywords are taken together as the text sample for the N-gram analysis. The next step is to group the keywords into N-grams of the desired length – typically either one, two or three-word phrases. N-gram analysis is basically interested in three things:

1.       How frequently does each N-gram appear throughout the query data?
2.       How many total clicks are generated by keywords that contain each of the specified N-grams?
3.       How many total conversions are generated by keywords that contain each of the specified N-grams?

Using this technique, advertisers can identify the specific words and phrases that are most strongly correlated (either positively or negatively) with ad performance for a given campaign.

At Directive Consulting, we stay at the cutting edge of PPC techniques so we can bring our clients the best results. We’ve discovered a handful of optimization opportunities using N-gram analysis & PPC that would have been difficult to spot otherwise, including:

•         Discovering the most profitable PPC opportunities by zeroing in on the highest-performing keyword combinations across an entire ad group
•         Identifying N-grams that negatively correlate with ad performance and introducing them as negative keywords to optimize ad spend
•         Reading buyer intention from N-grams, for example, the 1-grams “in” or “near” is commonly used when a prospect is searching for a business that is local to them. A 1-gram like “free” might be negatively correlated with buying intention.
•         Writing more effective ads. By deconstructing query data through N-gram analysis, we can incorporate several of the most profitable terms directly into ad text to improve ad performance.

Want to learn more about how we can help your business dominate PPC with N-gram analysis? Get a free customized proposal today!