Unlock the full power of machine learning for your campaigns
Smart bidding on programmatic platforms such as Google and the Meta apps (Facebook, Instagram and WhatsApp) has come a long way in the last decade.
Not only do these platforms collect a wealth of data about their audience, but their artificial intelligence and machine learning algorithms have improved by leaps and bounds. In addition to the fact that you may know your customers, there is a good chance that Google and Meta know them better.
Consider Google and the digital intent signals it collects from customers as they move through an ecosystem of apps that includes Gmail, YouTube, the app store, search and display advertising. Few companies – not even banks or insurance companies – can gain such a comprehensive view of a customer’s habits, interests, behavior and intentions. This intelligence is available to us, but to make the most of it, marketers need to lean into their platforms’ automation capabilities.
Here are some of the best practices that will help any marketing team achieve better results as they take a more automated approach to bidding and targeting on the major programmatic platforms:
- Help the machine learn
Smart bidding strategies use intent signals from audience segments to improve results for you. As smart as the platform algorithms are, they perform better when you support their learning process. An important first step is to set up your campaign or user journey correctly with accurate conversion tracking. Be sure to tag all events relevant to the user journey so you can switch between conversion goals and help the machine learn. This will also help you optimize the user journey and user experience based on insights into how users interact with your digital touchpoints.
2. Set goals higher up the conversion funnel
With most bid strategies, a campaign must generate a certain amount of conversions to end the learning period. During this period, we recommend setting goals that are higher up in the conversion funnel. For example, we will set our conversion goal as a click on an Add to Cart button instead of the customer arriving at the “thank you” page after a successful conversion. This will increase the conversion volume of the campaign and improve performance. After the learning period, you can switch goals to feed the algorithm with the data most relevant to the overall goal of your campaign.
3. Change the target if it doesn’t work for you
On Google’s platforms, the smart bid strategy must match the campaign objective. For search, conversion-focused bid strategies work well. These include maximizing conversions, target cost per acquisition (tCPA), target return on ad spend (tROAS) and improved cost per click (eCPC). But if a campaign is struggling to get traction, switching to a traffic-focused bid strategy—like target impression share and maximizing clicks—will boost volumes.
4. Give the algorithms time to learn
The machine learning algorithms will not deliver immediate results. They need time to collect sufficient data through user intent signals. The recommended time for learning is two weeks. During this time, it’s best not to change the campaign or the tags or goals associated with it. This will restart the learning period and cause a further delay in achieving the results you want from your campaign.
5. Go broad instead of granular
As I mentioned earlier in this article, the platforms know your customers very well. We no longer recommend granular targeting because Facebook and Google will do the granular targeting for you and with more success than any human can. On Google Search, keyword match types are now irrelevant for conversion-focused smart bidding. The keywords are no longer the main drivers of performance, but instead help the algorithm, which is why we recommend flexible match terms.
On Facebook, we have noticed a movement away from audience segments. We still use remarketing tags, but we generally see better conversion results from targeting strategies where no customer lists or segmentation are implemented. The algorithm plays a big role here. Domain verifications and conversion API requirements are critical to ensure you’re using machine learning to its fullest potential.
6. Use your first-party data to gain an advantage
With digital platforms moving away from third-party cookies and identifiers, tracking customer behavior across the internet is becoming difficult. Feeding Google and Facebook your first-party data will help their algorithms improve their performance. Relevant, accurate data from your customer relationship management systems and other platforms will help the algorithms to significantly improve targeting, leading to higher conversion volumes.
7. There are still some useful manual interventions
Campaign optimization is becoming increasingly automated, but there are still some useful manual steps to keep in mind. Creating negative keywords and exclusion lists for target groups can help steer the platforms from showing ads in the wrong places. For example, if you sell casual summer wear, you might redlist terms like evening wear or formal. With audience exclusions, an obvious use case is to exclude known existing customers from seeing a brand ad, and existing customers who are unwanted (for example, customers who subscribed but failed to pay their monthly subscription). You can also exclude specific data using an advanced Google Ads API. For example, if an account’s conversion tracking was incorrect during a date range, you can use data exclusions to tell Smart Bidding to ignore all data from those dates.
Focus on strategy rather than operations
With automation tools like smart bidding becoming more sophisticated, we can leave more and more of our day-to-day decisions to algorithms. In our experience, these algorithms not only save people a lot of manual work, they also significantly improve results. Also, they free up our time to focus on the larger strategic business goals rather than on small campaign optimization.
Carli Gey van Pittius is head of digital media at +OneX. She has worked in the digital media space for over five years and as head of digital media. She is currently responsible for the digital campaigns management team at +OneX. She helps organizations achieve better results from their digital marketing investments by unlocking the full potential of campaign performance data.
Do you want to continue this conversation on the Media Online platforms? Comment on Twitter @MediaTMO or in spring Facebook page. Email us your suggestions, comments, contributions or tips to [email protected]
(Visited 2 times, 4 visits today)