Friday, September 8, 2017


Phase i: One show fits all
“Fifty years ago, if you walked down any street in America on a warm Monday night you'd hear I love Lucy coming out of every house, on every block” this is the beginning of a great sales pitch by Bob Munro (Robin Williams) to the Alpine Beverage Co. in the movie RV.

Phase ii: Statistical clustering
A few years ago, CBS aired “I love Lucy” reruns and based on the ratings it reported that it was tied for second place as far as the key 18-49 demographic goes.

Phase iii: Personalized matching of content to individual people
Today, if you walked down any street in America on a warm Monday night, you probably won’t find two households watching the same TV show, heck, you won’t even find individuals in the same household watching the same TV show (if they are watching TV altogether).

Products as Content
In the world of content it is easier to understand a person based on their past preferences as content is rich with attributes related to one’s personality and motivation and tells a story about their readers and viewers. By contrast, in the world of product retailing, the 2-dimensional objects, traditionally, tell no story and the only attributes they share are of size and color and the like.
So, as the world moves from the Coca Cola phenomenon of “whoever you are, whatever you do, think of Coca Cola” one size fits all approach to a very personalized matching of products to individual people, what eCommerce companies fail to recognize is that the next era of online buying calls for marketing product-as-content.

Why will the future look like Etsy?
This type of personalization needs to be rooted in a whole new approach and philosophy and one eCommerce merchant has that approach and set out to raise the bar on personalization. Hyper individualized marketplaces like Etsy are more inclined to be “Netflix” (content) than “Amazon” (product) in the way they sell one-of-a-kind products to their shoppers. This is the foundation of their amazing success.

Psychology and Product Discovery
A new Era where shoppers want to be recognized as individuals and not as another member of the mass market or of a particular cluster, requires new tools.
Statistical personalization is not sufficient to transform a product and enrich it with attributes that will tell a story about its shoppers. Even micro segmentations and deep learning systems are failing to do so. Understanding an individual’s personality and motivational traits requires a deeper understanding of Why they buy no just What they buy.

Cognilyze Psychology based Personalization
Cognilyze is the 1st and only psychology based personalization and recommendation system that knows why people buy and therefore can provide personalization that is highly precise and relevant.

Using AI, Cognilyze combines psychology and technology to reach a deep understanding of the shopper building an individual "psychological profile" for each and every shopper.
Psychology based recommendations are agnostic to popularity and what other people buy and therefore, products surface throughout the long tail of your inventory to include, cross category, niche and new products as well.

To enhances shoppers' experience throughout his or her shopping journey. From "search pages" that intuitively understand the shopper's motives and reasons, through very relevant recommendations that include new, niche and cross category products and finally our "Discovery Pages" pleasantly surprising the shopper with unique products that speak to their deeper wants and desires.

So, what does the future hold? Taking Etsy’s philosophy and approach and a complimentary Cognilyze philosophy of technology, we vision a world with Etsy-like shops and Cognilyze-like technology where matching a product to a person will be as individual as matching two people for a date.  

Monday, July 17, 2017

Technology for Sale: Using Artificial Intelligence & Psychology to Understand Customers and Recommend Products

Since its inception 3 years ago and its formal founding 2 years ago, Cognilyze has developed and released innovative technology for customer modeling, personalization and product recommendation. Our core technology is based on Artificial Intelligence, Cognitive Science and Psychology, and is the only solution on the market that does individualized one-by-one analysis of customers and the products to recommend them, without any statistics or clustering comparing customers. Our deployed solution ran in a scalable manner on Google Cloud, and handled millions of users a day in a production trial on, owned by Bluestem Brands.

Our trial confirmed that our Cognitive Science based technology can understand and model shoppers in a much deeper and more comprehensive manner than the leading solutions on the market. Our solution processed over 80,000 unique customers per day, displayed over 23.5 million product recommendations, and achieved 2.7x the added value from recommendations of the market leader in a direct A/B test. Our recommendations successfully sold products cross-category, pre- and post-purchase, on revisits to a site or after browsing, and in e-mail and mobile promotions. Our technology is also perfect for promoting new products, even before any statistics are gathered for them, and in marketplaces where statistics are similarly unavailable.

Despite our successful deployment with Bluestem, Cognilyze was not successful in generating cashflow or follow-on investment. Our challenge was finding customers willing to leave the market leaders to work with smaller vendors, regardless of whether we had built a better mousetrap. We did, however, have significant interest from platform companies and integrators in partnering with us. Because of this, we realize that our technology will succeed better as part of a bigger, more comprehensive package of digital solutions offered by larger providers or integrated by e-commerce sites.

We have therefore decided to focus on finding a new home for the technology and intellectual property that we developed. This includes the technology built by our development team, under the direction of CTO Bruce Krulwich, a veteran technologist with a PhD in Artificial Intelligence, our U.S. patent application, and our cognitive models built under the direction of our Chief Scientist Professor David Leiser, Founder of the Center for Decision Making and Economic Psychology at Ben Gurion University and President of the United Nations IAAP Chapter on Economic Psychology. We are offering all interested parties the opportunity to buy our technology, cloud-based solution and U.S. patent application. Incorporated into broader solutions or platforms, our technology can enable you to better understand shoppers, model their interests and motivations and target them more effectively.

We are now considering all offers for our technology, code, intellectual property and solution.

Feel free to e-mail us at and we will send you materials describing our intellectual property, solution distinction, production trial and more.

Thursday, November 17, 2016

Psycho-Search: Finding Products that Fit the Customer's Interests

Studies show that most on-line shoppers start their shopping with a search. Sometimes this search is for a specific product ("Samsung Galaxy S7"), sometimes the search is for the characteristics of what they want ("big reliable smartphone") and sometimes the search is for whatever the customer has in mind ("smartphone that teenage girls like"). Ultimately the customer's goal is to find products that fit what they want.

But do product search results satisfy customers? Some certainly do. Search any electronics site for "Samsung Galaxy S7" and you'll get the devices and accessories you want. But some searches are not handled as well by the industry leaders.

For example, search for "reliable sturdy smartphone" and here is what you'll see on one site:

Failed search for reliable study smartphone

Where are the smartphones? Are these the three most reliable or sturdy products on the site? The point of the user's search seems to be missed.

Here is another example, searching for "flashy smartphone" this time:

Failed search for flashy smartphone

Again the site missed the user's interest in smartphones, and in this case completely missed what the word "flashy" meant.

Enter PsychoSearch from Cognilyze, the psychology-based big data company. PsychSearch uses our psychological profiles of both products and customers to give you the products you want for searches such as these. PsychoSearch results can be displayed as search results or as recommendations along the side.

First, we see that the word "smartphone" relates to several product categories, and we narrow the scope to smartphones, smartphone accessories and the like.

Second, we see that words like "flashy," "reliable" and "sturdy" relate to attributes of products. Our unique product analysis engine associates products with a wide variety of attributes, each of which identifies a possible reason that the product is purchased. So even if the word "sturdy" doesn't appear on a product's web page, we know which products are sturdy based on the materials they are made of, the way they are made, and the reviews that the products get from previous buyers. Even if the word "flashy" doesn't appear on a product's web page, we know if it's flashy based on lots of other indicators, such as the color, the size, comments in reviews about friends noticing, etc. Smartphones with Gorilla Glass 4 and metal cases are sturdy regardless of whether the word "sturdy" appears on the page, and hot pink phones are flashy regardless of whether the word "flashy" appears on the page.

Third, we add in our profile of the customer's (searcher's) motivations and preferences. Cognilyze always has a few thousand products ready to recommend each customer, each of which matches that customer's preferences and motivations. Before searching the store's whole product inventory for search matches, we search the products that we know match the customer's profile. In this way, the top search results will be those that the user is most likely to want.

Cognilyze is seeing great interest in Psycho-Search, as e-commerce sites are looking at how search can better deliver what customers want. If Google gives different search results for different users, why shouldn't product search on on-line stores give personalized results for the customer searching?

Want to know how Psycho-Search can help your customers find the products they want? Contact us now!

Sunday, November 13, 2016

Telling Customers Why Products are Recommended

Anyone browsing at on-line stores these days sees recommendation bars such as these:

Recommendations such as these used to come with headlines like "recommended for you," but the industry discovered that customers want to know why these products are being recommended, and moved to headlines like "customers who bought this item also bought" and "popular items from your favorite categories." These headlines make it clear why the recommended products are being shown.

But what if the system knew why the customer would want the recommended products? What if the headlines could really cut to the chase, and tell the customer precisely why he will (or may) like the recommended products.

Cognilyze is the first personalization system that understands the why underlying each customer's shopping. The Cognilyze engine understands the motivations and preferences that relate to each product, and analyzes which motivations and preferences are the most likely explanation of each customer's shopping.

The results are outstanding. Customers clicked on product recommendations 3.5x more when those recommendations were shown with headlines that connected with the customer's interests. Customers liked that the system understood them, and were attracted to recommendations that reflected this understanding. And this interest paid off - Cognilyze delivered 14% better conversion when psychology-based headlines were used.

Other product recommendation systems, all of which are based on statistical approaches, cannot generate tag lines such as these because they do not use any explicit motivations or preferences in generating their recommendations. Only a psychological approach such as Cognilyze has the basis for tag lines such as these.

This ability to select promotional lines of text based on the customer's psychology is also useful for the subjects of promotional e-mails, SMS or mobile promotions, call center scripts, and much more.

Want to learn more about Cognilyze's psychological approach to e-commerce personalization and marketing? Contact us now, we're happy to talk anytime.

Monday, September 12, 2016

Cognilyze at RetailWeek in London and in Berlin

Cognilyze is exciting to be exhibiting at RetailWeek, Sep 14 & 15, in London. We'll be describing our psychology-based product recommendation engine, the first recommendation engine that understands products and people on a 1-by-1 basis, not by comparing them to others.

Want to learn how Cognilyze recommendations can increase your store's conversion rate and revenue per customer? Contact us now to schedule a meeting at the show.

Cognilyze is also available for meetings the following week, Sep 20-22, in Berlin. Contact us to arrange a meeting.

Sunday, September 11, 2016

Cognilyze engine serves its 10 millionth product recommendation

Cognilyze is happy to tell our followers that our psychology-based product recommendation engine has recently served its 10 millionth product recommendation.

Other product recommendation engines on the market are based fully on statistics, and recommend products based on what other customers bought. Only the Cognilyze recommendation engine analyzes each customer's individual motivations and preferences, and recommends products that match those motivations and preferences, regardless of what how each customer compares to the masses. 

Cognilyze has built our system for huge scale, using Google's Cloud, and is designed for blindingly fast real-time response, so customer see product recommendations as quickly as they see the web page they're on.

Our system is in trial use with several e-commerce sites worldwide.

Contact us today to find out how the Cognilyze psychology-based recommendation engine can service shoppers on your site.

Wednesday, August 10, 2016

Targeted Recommendations of New Products in Online Stores and Marketplaces

Or, Why Only Cognilyze can Recommend New Products Online

Real-world “brick and mortar” stores are always promoting new products. Talk to a salesperson about what you want, and if they can tell you “this just came out, and it is exactly what you want,” they will.

Unfortunately, when it comes to on-line product recommendation, new products are never at the forefront. Stores do promote new products on their homepage and have sections for new products. But as you browse around on-line stores, you constantly see recommendation bars promoting popular products, such as products most often bought by people who share your interests, or products most often bought by people who browsed the same product you are looking at right now. But on-line stores rarely recommend new products in these recommendation bars.

If promoting new products is such a staple of sales in the retail world, why wouldn’t online store want to copy the success, and recommend new products whenever they try to give recommendations?

Consider what actually happens when a salesperson in a physical store recommends a new product that matches your interests. That salesperson has seen the new products received that day or that week, and has understood what is interesting, different or beneficial about each new product. Likewise, he intuitively knows his customers’ wants and needs. This understanding enables the salesperson to recommend the new products to people who would benefit from  them.

Online recommendation systems, however, work very differently. While human salespeople think about reasons and interests, virtually all online recommendations are based on statistical correlations. Recommendation labels such as “Customers like you purchased…” or “Customers who browsed this item purchased…” are doing exactly what they say - recommending the products that have been bought the most by customers that are similar to you in some way.

On the surface, this makes sense. If the majority of people that purchased the same things that you bought went on to purchase other specific products, it stands to reason that those things would interest you. Likewise, if the majority of people who browsed the products you’re looking at now ended up buying a few specific other products, it is logical to recommend those products to you.

This is not possible, however, for new products. Simply put, new products by definition have not yet been purchased by a lot of people at that store, so there will not be statistics available to indicate when they should be recommended. Without such statistics, new products can be promoted on a home page or a page for that category of product, but cannot be targeted at individual people, since there are no statistics available to indicate when the new product should be recommended.

For on-line stores, the inability to recommend new products means lost opportunities to sell exactly the products that should be most promoted. For on-line marketplaces, however, such as auction sites and sites that sell products created or sold by individual sellers, the problem is much more serious. New products are the backbone of these sites. On marketplace sites, new products are generally sold and leave the site before they have the chance to build up a base of statistics. For this reason, the ability to recommend new products is important for all stores but particularly critical for marketplace sites.

Cognilyze is the only online product recommendation system that can recommend new products to individual shoppers. This is because Cognilyze is the only recommendation engine that recommends the way human salespeople do, based on reasons and interests and not statistics. While other recommendation engines use statistics, Cognilyze uses psychology.

Cognilyze’s engine recommends new products the same way it recommends all products. First, it analyzes all the products in a store to determine the motivations, preferences and interests that most likely drive each product’s purchase. We call this the “psychology” of each product. Second, takes the collection of products that each user has purchased or otherwise expressed interest, and the psychology of each of those products, and computes a psychological profile of each user. A user’s psychological profile is made up of the motivations, interests and preferences that are inferred from the products that the user purchased or browsed. Third, it finds the products that the user has not yet purchased that match each user’s profile. Since each product is analyzed independently in terms of its underlying psychology, new products can be matched to user profiles just as easily as old products, to find the products that match the psychology of each customer.

With Cognilyze’s recommendation engine, new products can be targeted at customers the first minute that they are available on the site, at the same time that they are being promoted on the homepage and new products tab. And in marketplaces, products added to the listings can recommended to customers as soon as they are added to the site.

Cognilyze’s product recommendation engine was launched with our first client in the summer of 2016, delivering a higher customer conversion rate from the first day it was launched. Mimicking human salespeople, by truly understanding products and customers, beats statistics. The ability to recommend new products in on-line stores and marketplaces is only one of the many advantages of Cognilyze’s psychology-based big data.