This wizard guides you through uploading your products catalog, setting up product interactions monitoring to assign visitor interest, and designing the look, feel, and placement of your recommendation widgets.
These product recommendations are able to be embedded anywhere on your site, and multiple recommendation widgets can be placed on a single page, each with its own algorithm.
The algorithms included in our solution cover every recommendation need you may have, including cross-sales, up-sales, products recently viewed, the cheapest product in a category, most popular based on recent interest, etc., with many filters.
In the unlikely event that you need an algorithm that isn’t already possible in our system, please inquire with your account manager or support@personyze about building a custom algorithm for you.
Steps
Product Catalog
Here is where you upload your product catalog (if not already uploaded). Your account only has one catalog, so if you’ve already done this, you don’t need to do it again.
Personyze uses raw data to synchronize with your product catalog/feed, so it doesn’t matter what product management platform you use. All you need is a spreadsheet or other feed with your product data. Google Merchant links generally work, and SFTP is the best format for rapid updating.
Personyze can also crawl your site to create a feed if need be; if you don’t have any existing feed, please speak to your account manager or support@personyze to discuss crawling your site.
The more data your feed contains, the more rich and dynamic your product recommendations will be. The most essential things to include are:
- Product Title
- Product Listing URL
- Product Image URL
- Price
- Product Description
- Interest Categories for each product (click here to read more about interests)
- Product ID (SKU, or similar unique ID)
Some additional product data that are helpful to have are:
- Sale Price
- Cross-Sale SKUs
- Up-Sale SKUs
- Brand
- Secondary Interest Categories
- Seasonal product associations (sells more in the Summer/Winter)
- Availability (In Stock or not)
You’ll also need to tell Personyze which column corresponds to which value, in your Personyze product feed.
Product Interaction Event Tracking
How does Personyze know what a visitor is interested in? The answer is by tracking product interaction events. This allows Personyze to know both what individual visitors are interested in, as well as the general trends among all visitors, or visitors of various demographics, etc.
What is a product interaction event? The most common examples include product views, favoriting or saving, adding to cart, and checking out or purchasing the product.
In order for Personyze to track these events, you have to tell it how to know when a visitor is viewing a product, when a visitor is adding to cart, etc. Since this is different for all websites, it has to be manually set.
Note: You only have to do this once, and then the same logic is applied to all of your product pages. You can also request that the Personyze team do it for you, as part of onboarding with any package. This is a normal aspect of onboarding, for anyone with whom we have had discussions leading up to their sign-up. However, even if you have not been talking to us previously, you can always request it by contacting support@personyze.
If you want to set this up yourself, you can read more about setting up product interaction event tracking here.
Content (For JSON Recommendations for Personalization)
This is where you create the actual display widget design which you will use to show the recommendations on your site. Personyze comes with some templates as starting points, but virtually any HTML/CSS product display carousel designs can be used by our system. Note that there is another JSON recommendation option, where you use Personyze simply to “tell” your CMS display which items to show, via JSON.
When creating the display, you will also be prompted to choose the algorithm which makes the most sense for your current application. You can read more about the various product recommendation algorithms here.
This is another aspect of your account setup that can be outsourced to the Personyze team. Once you create the recommendation design(s) that look good on your site, they can be used to show any algorithm on any page, with the same design.
Target
If you want your recommendations to only be displayed to a certain targeted audience, you can insert targeting rules here. For instance, you may only want to show “Buy It Again” recommendations to users who have made a purchase, and for this to be invisible to all others.
This portion of the wizard is the same as any other targeting wizard, and you have access to the full array of targeting parameters that Personyze is capable of, to limit the audience of this recommendation campaign.
QA
QAing your recommendation campaign is much the same as QAing any other type of campaign in Personyze. You can click here to read more about the QA process.
Campaign Performance Dashboard
Get a comprehensive campaign performance view, with metrics such as impressions, click through rate, bounce rate, conversion rate, recommendation revenue, time it took to buy from the first click, etc. Filter down to see detailed statistics by recommendation algorithms, list of products or content, and various user data parameters like demographic and location.
*By default, Personyze also reports campaign performance in real time to Google Analytics.
