Familiarize yourself with the key concepts in Acoustic Personalization.
You must register Personalization in Acoustic Exchange and integrate with an analytics library (such as Google Analytics, Adobe Analytics or Digital Analytics) for sharing the events data.
A/B test is an experiment to test a visitor's response to variant A versus variant B and to determine which of the variants is more effective.
In the context of Acoustic Personalization, the channel visitors are shown different personalized content variants (such as an image, text, or video) and the visitor's response is tracked to determine which of the content variants received more attention (determined for example by, the number of clicks on the variants).
For A/B test, there is a group of visitors who are part of Control Group, who belong to a segment that is targeted for personalization but held back from receiving the personalization. This group receives the original content, as against to the rest of the visitors who are shown the personalized content variants (A, B, or C). Usage of control group serves as the baseline against which the results of A/B test are evaluated.
You create an A/B test with some goal (objective) in mind. Acoustic Personalization currently supports click rate as a goal. In other words, you can create an A/B test to track and measure the number of click events on the personalized content variants to determine which content variant is more effective.
Based on the results of the A/B test, you may then choose to show the winning content to your visitors to maximize your goal, or you can continue with your tests till you are satisfied and statistical significance is reached.
Channel tenant ID
To capture the click events on the zones of your Single-Page Application or Multi-Page Application, you need to use trackEvent function. If you do not configure the zone to capture the click events, the click rate cannot be calculated. For more information, see Capture click events.
In Acoustic Personalization, the control group receives the original content regardless of any rules in place. The visitors in the control group are randomly chosen from the visitors who match the personalization rule. The number of visitors allocated to Control group depends on the Control group percentage chosen during rule creation.
Control group is useful for evaluating the effectiveness of the personalization rule. If you see a statistically significant increase in conversions for the normal (non-Control) group, whereas the control group remains the same, you know your personalization was effective. However, if there is no increase in the normal group over the control group, you can decide to change your personalization strategy.
The original content is what the website has before you apply rules for personalization.
Personalization Library is responsible for matching the rules that are created by the Acoustic Personalization marketer. It works on the client website and interacts with behavioral data to form the correct results. Based on these results, the personalized content is shown on the website.
Personalization Library is available on Acoustic JFrog Artifactory.
Maximum rule impressions
Maximum rule impression is defined as the maximum number of times a personalization rule is to be applied or run.
When the "Number of times applied" metric matches the "Maximum rule impressions" count, then the status of the rule changes to Active - Completed.
Note The maximum rule impressions cannot be less than or equal to 0.
You can use maximum rule impressions metric to limit the number of times a rule is evaluated to prevent a piece of content from being shown on zone after certain number times.
You want to use Acoustic Personalization as an advertising management solution. You want to show a promotional offer on your website, but want it to be displayed to only 1000 visitors. After 1000 visitors see the promotion, you want to stop the offer that is displayed to the visitors immediately. So, all the remaining visitors would see either the default content or separate personalized content, depending on the segment they fall in.
You can use Maximum rule impressions field as follows:
- You can define the value for Maximum rule impressions when you create a new rule in Acoustic Personalization. Set a value for Maximum rule impressions field to 1000.
- Save and publish the rule.
Note The Number of times applied metric shows the number of times the published rules for the zone matched the visitor behavior and personalized content that is shown on the zone.
After the Number of times applied metric crosses 1000, personalization will not be applied and the status of your rule changes to Active - Completed.
When does my rule's schedule gets completed?
The status of your rule changes to Active - Completed in the following scenarios:
- When the rule hits the maximum rule impressions limit, before the end date
- If the end date of your rule is reached, before the rule hits its maximum rule impressions limit
A zone can have multiple rules.
Rules are ordered and evaluated by priority. For a channel visitor, If they belong to the segment for a higher priority rule then they get shown the content for that rule. Other rules are not evaluated.
In the context of Acoustic Personalization, segments are dynamic and can be created by specifying conditions. Visitors who satisfy the conditions belong to that segment and can be targeted for personalization.
For example, the marketer can specify a segment such as "If the visitor views product like Swiss watch, then the segment includes all visitors who view a Swiss watch."
You can use Product Recommendations feature of Acoustic Personalization to generate relevant product recommendations for your channel visitors based on their behavior on the channel and their browsing history.
Product Recommendations ensures that each visitor receives a personalized experience. Recommended products can increase visitor engagement and overall sales on your website by showing them the products they need, when they need them in real time and help them delve more deeply into the product line without having to search manually. It also increases the overall sales of your website.
Using the Acoustic Personalization - Product Recommendations, you can:
- Create a primary strategy for each zone that defines the type of algorithm you want to use for recommendations.
- Create a fallback strategy for the same zone to provide recommendations in the event that the primary strategy doesn't have enough recommendations.
- Preview the output of the recommendation algorithms and business rules applied, before you publish the strategy.
- Analyze how effective your recommendations are by tracking the number of times each recommendation was applied and how many times that product was clicked.
Lookback time frame
Lookback time frame is the number of days of historical visitor behavior data that is used by the various algorithms to generate product recommendations.
You can set the value for Lookback time frame to either 1 day, 7 days, or for 30 days.
On a high-traffic website with millions of hits per day, you can choose a shorter time window of 1 day. However, if there are not as many active visitors on the website, you should select a bigger time frame (7 days or 30 days) so that your recommendations are more accurate. A shorter window enables product recommendations to be more responsive to changes in the market. However, recommendations are based on the number of visitors on your site and get more accurate with more visitors.
For example, consider a corporation that sells cutting-edge consumer technology. If the marketing channel owner for this corporation decides to start a new campaign that targets new visitors as potential buyers, then the channel owner can select an area (zone) on the website to display the personalized content. The zone can be in the form of a header or a side bar or in any other form as the channel owner desires.
In the case of Multi-Page Applications, the zone ID is specified by the website developer while creating the HTML source code for the web page.
In the case of Angular Single-Page Applications, the channel developer must identify the components where personalization is to be applied and subscribe those components for personalization by passing a unique ID that is same as the Zone ID specified in Acoustic Personalization.
When registering a zone for personalization, you must provide this Zone ID.
The combination of zone name and the Zone ID must be unique within the channel being personalized.
The valid characters for a Zone ID are A-Z, a-z, 0-9, hyphen (-), and underscore (_).
Zone ID should not contain a space, or special characters, except hyphen (-) and underscore (_) characters.
To view a zone ID in a website, complete the following steps:
- Open the website that you want to personalize in a web browser, for example Google Chrome.
- On the website, decide the section (zone) that you want to personalize. For example, header banner.
- Right-click on the selected zone and click Inspect from the context menu in Google Chrome. If you are using Mozilla Firefox or Microsoft Internet Explorer / Edge browsers, click Inspect Element.
The div element associated with the zone is highlighted.
- Note the unique ID for the HTML element. For example, div id = “WelcomeBanner”
This is the zone ID that you need to specify during zone registration.
If the website that you want to personalize does not have unique identifiers for the section, then it is recommended to assign a unique zone ID to each HTML element that needs to be personalized.