Provide the Most Personal User Experience Possible.
The recommendation engine builds a unit of recommendations for each visitor based on personal data combined with predictions based on other visitors, producing dynamic recommendations pushed in real time at every touchpoint to give the visitor the most relevant products/content at every moment.
A Personal, Unique Cross-Channel Visitor Journey.
Send personalized email drips with product/content recommendations, targeted content, and promotions directly from Personyze, or embed them into emails with your third-party provider.
Build Workflow and Integrate Seamlessly Into Your Logic.
You can use built-in wishlists to let visitors save recommended products to a Personyze hosted wishlist, and then show it later on their cart page, or send it in a reminder email. Use Personyze’s smart forms to ask visitors to save their preferred sizes, or to send them a reminder of their cart content. Trigger recommendations right after a product is added to cart, with a list of items bought together. Leverage your customer expertise to fine-tune recommendations
Easy to Use, Integrates Into Your Site in Minutes.
After a 5-minute installatation, our step-by-step wizards guide you through the process of creating recommendations, and industry best practice responsive templates make the process even easier.
Personyze can present both AI generated product or content recommendations on the site, using simple widgets embedded anywhere on your website
Integrate your in seconds with your existing email provider and campaigns. Simply Add code snippet into your email template.
Send personalized email drips with product/content recommendations, targeted content, and promotions directly from Personyze.
Add recommendations and targeted promotions for apps built on iOS and Android.
With Personyze, our teams around the globe can now deliver new targeted promotions and messages within hours instead of weeks. Moreover, our local marketing teams around the world are empowered to manage their own marketing campaigns without the involvement of our core development team!
We use Personzye for clients from the financial industry to deliver a personalized experience with content and calls to action which are aligned with visitors’ interest and location. The managed service team was very helpful in the implementation with some of our more complex use cases.
Leverage the Power of
AI Powered Recommendations & Personalization Engine
Imagine going to a store where the front shelves are stocked only with products that you like, or reading a newspaper where the stories you’re interested in move to the front page. This isn’t possible in the brick-and-mortar or print world, but with our powerful recommendations, this is easy to set up on your website.
See how Boomdeal uses interest-based product recommendations to create a personalized experience in their online store.
See how Global News Today personalizes their home page for a visitor’s known interests.
This category of algorithms involves showing visitors what is most popular (according to views, adds to cart, likes, comments, purchases, etc.), based on an item that the visitor is currently viewing, a category that they are known to like, or other options.
This recommendation shows products that the visitor may like, because other visitors with similar characteristics viewed, added to cart, or purchased them often.
This recommendation shows items that are popular among other visitors from the same geographic region, or from the same referrer(s).
This recommendation shows popular items which have recently lowered in price, based on the visitor’s ranked interests from past browsing.
This shows the visitor the newest items from categories they have viewed or purchased from in the past.
This type of recommendation is to remind a visitor to purchase perishable items again, after a certain period of time.
This recommendation shows items that were popular among visitors who purchased the same item as the visitor’s most recent purchase.
This recommendation uses machine learning to find patterns in the crowd data, and shows each visitor what they are most likely to be interested in based on these detected patterns.
This recommendation will show the visitor other products that were frequently bought together with the product currently being viewed.
This recommendation will show the visitor products which have an up-sell association in the product catalog with the product that is currently being viewed.
This functionality allows the visitor to add one or more products to their wishlist, to be purchased at a later time, and used in remarketing emails or wishlist recommendations on the site.
This recommendation shows products that were popular among those who bought and viewed items in the category of the item currently being viewed.
This recommendation shows the visitor what they are most likely to be interested in, based on their ranked set of interests derived from previous content interactions.
Shows visitors on a content page what other posts have been most popular among other visitors who read the current post.
Shows the visitor the most viewed, commented, favorited etc. content from the same category as the content currently being viewed.
This recommendation will show a list of most popular content based on those categories most recently read by the visitor.
This recommendation will show the content that is most popular recently.
This type of recommendation will show the newest content from the same author, interest, or category as the content currently being viewed.
You can show recommendations that are popular for users from the same geographic region, which is especially useful for new/anonymous visitors.
When you have demographic information on visitors, such as gender or age, you can show items that were popular among their similar demographics. Demographic/CRM variables can be any custom variable you have on your visitors.
Show visitors items which they previously read but did not scroll to the bottom of the page, across devices.
Show the visitor the most clicked, viewed, commented etc. content which has the same topic tag as the content currently being viewed, good for content pages.
This recommendation is good for guide and info pages, and shows products frequently bought by visitors who read the same content currently being read.
This will show the visitor the most viewed/commented/liked content from their most read author on the site.
This recommendation shows the visitor items that have recently changed in price, based on what they previously interacted with or left in their cart.
This type of email recommendation reminds the visitor of items they left in their cart, as well as recommends similar items, in emails sent at intervals determined by you.
This recommendation type reminds the visitor to re-stock perishable items, and can be sent only at certain intervals determined by you.
This email recommendation suggests items based on a previous purchase, using what other visitors who purchased the same product also bought.
This email recommendation uses machine learning to detect patterns in the crowd data, and based on the visitor’s characteristics will show them what they are most likely to be interested in.
This email recommendation suggests items which other visitors who made the same purchase as this visitor’s most recent purchase also bought, or items which have a cross-sale association in the catalog with the visitor’s most recent purchase.
This email recommendation will suggest items to the visitor that have been newly added, which go together with items previously purchased.
This button on the site allows the visitor to opt-in for their cart to be sent to their email, as a reminder. If their email is not known yet, it can trigger an email form to be launched in the form of a popup, which can then be used for other remarketing emails, as well.
This recommendation type shows visitors the most popular content based on the visitor’s ranked interests from previous content interactions.
The most commented or read content from the past weeks, based on the visitor’s ranked interests.
This recommendation show the overall most popular content on the site.
This recommendation takes all of the visitor’s past reading, and recommends the most popular content that was also read by those who read all this past content.
This algorithm utilizes machine learning to determine what the visitor is most likely to be interested in, by finding patterns in crowd data.
This recommendation type shows the visitor the newest content from their most frequently read author(s).
This recommendation shows the visitor content that is most popular among other visitors with similar data profiles, such as similar location, referrer, etc.