A primary application for browser cookies in marketing is the ability to remarket/retarget a browser (person) that has been to the website. This seems great, as it shows interest. But, it has led to lazy marketing habits.

Blanket remarketing gives no real thought to context or timing. It intrudes on users when they are completely removed from the context or concerns that led them to the advertiser in the first place.

But doesn’t Google automation deal with this? Not really. In theory, it should. But we’ve all experienced the unsettling sensation of being “followed” around the Internet by a site we visited. 

This recent article in AdAge speaks to this very issue. 

The next level of automation

As Google pushes everyone to trust their AI, it expands on the concern raised by blindly retargeting users based on cookies: that, as marketers, we are relinquishing our control to a black box of automation. We are told this improves our marketing ROAS, but I am not convinced.

I think AI will improve results when it comes to unmanaged programs. For marketers who do not have the time to monitor and adjust their campaigns, AI provides a level of optimization that is bound to make things better.

I have seen dedicated campaign managers do much better for the average company. One thing AI is good at is finding the low-hanging fruit. A freshly launched program managed by AI can get quick wins, but they often plateau. Changes to pages, offerings, and budgets can reset the AI to a learning phase. Manually managed programs can get beyond the low-hanging fruit.

The other area where AI will excel is data analysis and response. However, the response/output is only as good as the data input, and the average company has issues with this.

A full circle of ads, outcomes, and feedback works well for AI. The most basic of these is E-commerce sites that feed all the sales back into Google Ads (directly or through G4.) AI is likely your best bet if you have an e-commerce website, and your primary conversion is an online sale.

Where Google AI falls short is when the value of an action is determined after the conversion point. All Google knows is that a conversion point was triggered. Herein lies the problem. 

Left to Google, the initial round of leads is more likely to be filled with junk than value. However, Google doesn’t know this, so junk leads are used equally in conversions. The AI is optimizing the program to deliver junk.

Can this be fixed? Yes. Absolutely. But not by the resources of the average company.

Fixing Junk Leads in Google Ads

Google provides valuable mechanisms to improve lead generation for offline activity following an online conversion.

Every lead submitted to Google Ads should include the corresponding lead ID, which should be carried with the lead through the sales/closing process.

When leads are closed, a file can be generated (or API used) to load the results back to Google. With this file, Google can assign value to each lead, allowing the AI to optimize lead generation.

For junk leads, which are usually identifiable very quickly, a file with the lead ID can be uploaded to Google to have these leads deleted from the system.

Like so much of the ad tech hype, leading-edge tools require resources and knowledge that are not available in the average company. 

Beyond the issue of resources is that of reliance on technology and complacency. Remarketing as we know it will end this year. And that’s not a bad thing. It reminds us that we are prone to accepting the easy out, allowing technology to do what we should be doing—or at least paying a great deal more attention to. 

As we continue to push the envelope of AI in advertising, we must always pay close attention to the outputs and ask ourselves if this really is the best that can be done.

The post The demise of Cookies and lessons from it appeared first on Fanatically Digital.

If you are new to digital advertising, you’ll see that implementing a PMax campaign is not too difficult. But that is part of the issue. As the path of least resistance, it makes it easy not to consider what you don’t see and don’t know. For advertisers that have worked through the programs of manually managing ads and automated campaigns, as well as implementations between the two, fully trusting PMax is a challenge.

Trust issue with Google Ads

When you speak with a Google rep, they are confident that the automated system is the best. They quite sincerely believe and recommend advertisers use it. The confidence with which they tout PMax is borderline cult-like. If you dive into the details of the ads and run a PMax for an extended period, your trust in their confidence will wane.

Some basic observations with Search Terms

In a fully automated program, Google will present your ads to users in various channels that the AI considers important and likely precursors to a conversion. With all the data that the AI is fed, it makes sense that it should be able to determine what leads to a conversion. So, why do we lack confidence?

Run a managed search campaign

Even if you use an exact match or phrase match, Google will present your ads to people based on what it deems to be a close variant. While doing this, Google continually asks you to move all your terms to a broad match. In theory, this allows the system to match against what it deems intent, even if the search term used doesn’t appear to match with your target keywords.

Take a look at the search terms that were entered and triggered your ads. Some very basic things stand out. As an example, look at geographic terms. 

Run ads for your local market using geo-targeting. With that, you can also use geo modifiers, such as “xyz companies in Chicago.” You will notice some things:

1. People who enter “xyz companies in Canada.”  will show up.
2. If you add “Canada” as a broad negative match, suddenly, “XYZ companies in Toronto” or some other geography like France, New York, San Diego etc will show on the search query report.
3. Long-tail bidding has not been possible for a long time, but Google is still showing that people are using long-tail searches.

Google Ads Deliver to Inappropriate Searches

These few (of many issues) used to be fully manageable through match-type implementation. Now that Google ignores match types, all we can do is add negatives. This has always been part of the process, but it is now the only tool we have.

To the issue of trust in Google’s AI: A company can only work with other companies in a market, they set up the Geo-targeting correctly and also set up target keywords correctly, but Google is showing ads to people who explicitly are looking for providers in other markets. 

When giving the AIs even a little latitude, Google spends advertising dollars on searches that cannot lead to a qualified prospect. It seems to be a simple concept that when we target a geo and use geo-targeted terms, the AI should be able to weed out bad queries. It just doesn’t.

A cynical perspective is that Google is simply amping up the number of bidders for each user search, thereby driving up the average CPC. Similar to the implication of removing long-tail bidding. Lump every 4+ word query into an auction with three or fewer words, and you increase the number of bidders for each auction. 

Whatever the drivers behind showing queries that are not appropriate, the effect is the same: higher CPC and lower qualified clicks.

The Fragility of PMax

Moving from keywords to complete AI-managed campaigns through PMax, there are a few things that show up.

Consistency matters to AI

The PMax platform depends on a period of learning. Set a budget, and the system starts slowly, learning how people respond and eventually spending the entire daily budget. This can take 1-2 weeks. If you have a change, your PMax campaign can reset itself. 

Budget Matters

The representatives at Google will direct PMax users with large budgets to a special team with more experience on the platform. One thing we did notice is that the performance at the higher spending level did not match the performance at the lower spending level. It deteriorated. 

This can happen with manually managed programs as well. However, there is a notion being presented that PMax is some kind of magic that can make your program work on any budget. 

Learning Matters

As marketers, understanding our customers and how they respond to our marketing is important. We can cross-seed our channels by learning from another channel. PMax campaigns (and, to a lesser extent, the responsive ad campaigns) remove our ability to learn. It either performs or it doesn’t. We can’t tell why because we can see nuance.

Premature Confidence in Artificial Intelligence

Over the past couple of years, AI has been hyped as the holy grail of advertising optimization. In reality, it has a long way to go. From basic mistakes that it doesn’t know are happening, or the need for a relatively steady state in order to maintain optimization, or not truly outperforming manually managed paid search programs at scale, PMax has a role in search but not the only part to play.

Opaque AI Tools

As mentioned earlier, learning matters in marketing. It is not enough that the AI “learns,” but the people managing the programs also learn. This is important to other marketing campaigns. Understanding how changes in your overall marketing, products, and competitors might affect campaign performance is also important. With the black-box AI, not only can you not see what is working, but you can’t see what isn’t… and the AI doesn’t know either.

Take the recent problems with Google Generative AI Gemini and it’s image generation. It produced historically inaccurate images when users asked for it to create images of the pope (and other historical cases), and the images were clearly not an accurate historical representation(CNN.) Given that only white men have been popes (for better or worse), it is a simple historical fact; there is no ambiguity. But Gemini didn’t know that, or wasn’t allowed to apply it. 

If real people hadn’t reviewed the images, the AI would continue to produce inaccurate results and never make adjustments. 

So, we know Google Ads’ AI delivers ads for a Chicago company (that only wants to do business with other Chicago companies) to people interested in Canadian companies. What else is it doing that we can’t see? How much waste is there when implementing a fully AI-driven campaign with no inputs or visibility other than your URL?

The post Why is it hard to trust Google Ads AI? appeared first on Fanatically Digital.

In the rapidly evolving digital landscape, Artificial Intelligence (AI) has emerged as a game-changer, particularly in the realm of Search Engine Optimization (SEO).

As we reflect on the pivotal year of 2023, it is evident how large-language-models (LLMs) and generative AI tools have revolutionized SEO practices, akin to the transformative impact of internet and smartphones.

In this post, we’ll delve into the impacts and implications of AI on SEO, highlighting the efficiency and value brought by AI tools in simplifying labor-intensive SEO tasks, while also examining the yet-to-be-realized potential of AI-generated search results in influencing website traffic.

AI & SEO Tools

When it comes to search engine optimization, the biggest impact AI had was in the available toolset. Copywriting programs, bulk on-page optimization, and rank tracking tools have streamlined the more tedious aspects of SEO.

Content Generation

After the release of ChatGPT’s API, content generation software quickly became ubiquitous throughout the SEO and content marketing space.

Tools like Jasper and Copy.ai  can assist SEOs by suggesting blog topics, assist in writing the blogs posts themselves, as well as generate website copy like product descriptions.

As you can imagine, these tools helped to cut down the time and effort for tasks that many SEOs may find tedious like researching new potential blog topics and content spinning.

Data Analysis and Trend Identification

AI tools have also revolutionized data analysis and trend identification in SEO. Tools such as Pro Rank Tracker and MarketMuse can automatically perform keyword research, identify content gaps on a website, and suggest topics for future posts.

These AI-assisted programs allow for a new level of precision to keyword research and trend identification, enabling quicker response to search trends.

SEOs also find value in the predictive insights that these tools provide, allowing content to be appropriately tailored for future search algorithm changes.

When used properly, these advancements in natural language processing (NLP) and AI free up SEO from the more tedious elements of their job to focus on the strategic side for their clients.

Impact on Search Engines

Natural Language Processing & Search Engine Algorithms

In the early days, search engines relied heavily on keywords to understand a given text and match search queries to the appropriate results.

However, with the advancements in natural language processing (NLP) and AI, search engines can now analyze content more comprehensively and better understand context and intent, allowing for more accurate results.

This has rendered old SEO tactics such as keywords stuffing obsolete. Over the years, content marketers have had to place a greater emphasis on the quality and relevance of their content.

One example of these NLP algorithms in action is Google’s BERT, which uses AI to understand the meaning behind a search query and deliver more relevant results.

With systems like BERT, search engines are able to understand more complex and conversional queries and factors in context from previous searches.

This has led to the rise of voice search and the need for SEOs to optimize their content for natural language queries.

In essence, AI has forced SEO professionals to shift their focus from optimizing for robots to creating valuable and user-friendly content.

Generative Search Results

While advancements in NLP has had a massive impact on how search engines’ process language over the past decade, much of these improvements have occurred behind the scenes. However, technologies unveiled in the past year and a half have the potential to advance the capability of search algorithms to a new stage in their evolution.

We’ve seen these NLP and AI advancements go from improving search engine’s ability to understand and interpret text to actually generating text themselves. No longer simply selecting the best results for a particular query but understanding intent well enough to formulate a response itself.

Programs such as Google’s Search Generative Experience and Bing’s Copilot use generative AI to create answers to search queries on the spot by cross referencing relevant organic results with their own internal knowledge graph.

This technology has vast implications for SEO, as websites will need to compete not only for top placement in search results but also for generating the most relevant and accurate information.

As of now, these AI-generated search results have yet to achieve widespread prevalence that significantly impacts website traffic. However, as this technology continues to advance,  it may dramatically alter the current SEO landscape.

Wrapping Up

In conclusion, AI has already had a significant impact on the world of SEO, primarily through automation and optimization of tasks. But as we’ve seen with NLP advancements and generative search results, the potential for AI to shape the future of SEO is immense.

While it’s unclear exactly how these technologies will continue to evolve, it’s safe to say that AI will be a driving force in the world of SEO for years to come. As search algorithms continue to improve and become more sophisticated, so too must our strategies as SEO professionals.

The post The Impact of AI on SEO (So Far) appeared first on Fanatically Digital.

In digital marketing, AI is pushing into everything from media optimization(not actually a new thing), to content writing and even image generation.

Having been in marketing for over 35 years, I am seeing things come full circle. Before digital, the greatest asset a marketing professional could bring was strategic direction. As digital unfolded and more knowledge was required to manage the actual campaigns, a greater reliance was placed on people who knew how to execute the programs. How do you set up, manage and optimize a Google Search or Bing Search campaign or Facebook campaign?

In fact, with Google dominating paid search, and the ROAS on it being so good, companies could expend entire budgets on Google, and measure the direct returns. But Google is removing tools and visibility, pushing advertisers into more opaque campaigns.

For some advertisers where something like e-commerce revenue is the sole goal, Google’s AI is great. But, business tends to be messy, with micro-conversions, changes in direction, or post-click actions as important as online metrics that are not easily incorporated into the value equation. We have to make judgment calls that the AI can’t see or quantify.

As the “doing” with managing becomes less and less, digital marketers need to broaden their scope of channels and platforms to become more strategic in recommendations.

As AI becomes more prevalent, marketers also need to understand AI. So, I decided to ask chatGPT what marketers need to do to keep up with AI. Here is the response…

To evolve with AI in digital advertising, digital marketers can take the following steps:

1. Educate Yourself: Start by gaining a solid understanding of AI and its applications in digital advertising. Familiarize yourself with concepts like machine learning, natural language processing, and data analysis. Stay updated with industry trends and advancements in AI technologies.
2. Leverage Data: AI thrives on data, so focus on collecting and organizing relevant data sets. Ensure you have access to clean, accurate, and comprehensive data that can be used for AI-driven analyses and decision-making.
3. Embrace Automation: AI can automate repetitive tasks, allowing marketers to focus on higher-value activities. Identify areas in your digital advertising workflow that can be automated using AI tools and platforms. This may include tasks like data analysis, campaign optimization, ad targeting, and content personalization.
4. Utilize Predictive Analytics: AI-powered predictive analytics can help you anticipate customer behavior and trends. By analyzing historical data, AI algorithms can make accurate predictions about consumer preferences, purchase patterns, and engagement levels. Use these insights to refine your digital advertising strategies and tailor your campaigns for better results.
5. Implement AI-driven Ad Targeting: AI can enhance targeting precision by analyzing user data and behavior patterns. Leverage AI-based tools and platforms that can segment your audience effectively and deliver personalized ad experiences. This will lead to higher engagement rates and improved ROI.
6. Optimize Content with AI: AI can assist in creating and optimizing content. Use AI tools to generate engaging headlines, create personalized product recommendations, and test different variations of ad copy. AI-powered content optimization can help improve click-through rates and conversion rates.
7. Monitor and Optimize Campaigns: AI algorithms can analyze vast amounts of data in real-time, enabling marketers to make data-driven decisions quickly. Leverage AI-powered analytics platforms to monitor your campaigns, identify patterns, and optimize performance in real-time. This will help you allocate your budget effectively and make timely adjustments for better campaign results.
8. Stay Ethical and Transparent: As you incorporate AI into your digital advertising strategies, prioritize ethical considerations. Ensure compliance with data privacy regulations and communicate transparently with your audience about how their data is being used. Build trust and maintain transparency to foster long-term customer relationships.
9. Continuous Learning: AI technology is evolving rapidly, so it’s essential to keep learning and experimenting with new AI tools and techniques. Stay updated with the latest developments in AI and explore how they can be applied to enhance your digital advertising efforts.

By embracing AI in digital advertising, marketers can unlock new opportunities for improved targeting, personalization, and efficiency, ultimately driving better results and ROI.

That’s how AI says to keep up with AI. Most sounds about right to me. Even if you don’t have access to all of the tools listed, jumping in where we can as soon as we can is important to the future of careers in digital marketing.

The post Digital Marketers’ path forward with AI appeared first on Fanatically Digital.