Skip to content



Touchpoint is any place on your website or app where possible opportunities can happen between you and your customer or prospect. Touchpoint studio is a unique solution for managing personalized experience on any channel. It’s ideal for upselling, cross-selling, keeping customers in the checkout, promoting actions, or just providing information of interest to them.


In the process of making a touchpoint in TP studio you first create a default strategy which will be shown to all customers. By adding new strategy (or strategies) you can choose a specific audience to which this new strategy will be shown. When you have two or more strategies connected to one touchpoint you can sort them by priority order.

Strategy defines rules and recommender types according to which the products will be served to your customer.

Touchpoint types

Smart Recommendations ensure that every user is equipped with relevant recommendations he comes across on every digital platform. Those recommendations are based on your business wisdom, data and artificial intelligence.

Recommender models are the essential part of personalized customer offer. They can be used to present every customer with a relevant recommendation or to find the right buyers for specific products.

Next generation recommender systems give more personalized recommendations, reach customers through multiple channels and give real-time recommendations. They aim to present the right items to a user and at the right time.

Used not only in e-commerce, but in other industries as well, as they find the recommendations powered by intelligence to take crucial part in reaching the goal of personalized targeting. These industries include retail, banking, telecommunications, real estate, etc.

Similar products recommendations

This service uses transaction history and returns N similar products for each product. It recommends the best-fit alternative products based on market basket content. Convenient for search banners and product pages where a specific product is not available or not found, in order to provide alternative and prevent cart abandonment.

This service uses transaction history and returns N similar products for each product. For each product, related products are selected using a certain association rule. This feature recommends products that frequently go together in the basket. Perfect for upselling and convenient for “add-to-cart” banners, POS recommendations, search banners, etc.

Choose a maximum of 15 products to be presented on your web page of choice which will serve recommender outputs according to the recommendation model or rules you have selected. Recommendation model and rules are defined by the goal you chose to be your strategy of this Touchpoint. Your goal can be to boost chosen products, decrease bounce rate or increase cross-sell & up-sell. Carousel is best for category pages, “add-to-cart" pop up screen, etc.

Recommender types

Recommender models are the essential part of personalized customer offer. They can be used to present every customer with a relevant recommendation or to find the right buyers for specific products.

AI starter-pack recommenders

  • Best sellers - recommending top selling products based on specific criteria (most frequently bought products from product catalogue in a given time period). This time period is by default 6 months, but can be configured differently

  • Trending products - recommending products having increasing sales trend based on specific criteria (products from product catalogue in a given time period). This time period is by default 6 months, but can be configured differently

  • Most recommended products - recommending products that are most frequently found as recommendations based on specific recommender algorithm which is convenient when communicating towards a big audience or if there is a cold-start problem. This is best served on homepage/home dashboards shown to new visitors and/or new customers on websites, mobile applications, POS, and where no prior information about the prospect has been collected.

These three recommenders are all convenient for homepage carousel, leaflets, search banner etc.

AI personalized recommenders

  • Community-based recommender - recommending products based on similarities between customers and products they have interacted with. Works best for cross-sell marketing strategies

  • Next-gen recommender - recommending product based on long-term patterns and preferences combined with a real-time occasion/intention of the user. Works best for real-time recommendations and e-commerce platforms

  • Description-based recommender - recommending products based on similarities extracted from their features (description, category, name etc). Works best for ”add-to-cart” banner, search banner, POS recommendations etc.


Smart Search represents a bundle of AI modules used for searching various data types and sources.

The “smart” thing about the Smart search engine is that it works perfectly even though no perfect search terms are provided (or incomplete information in the query is provided) - it is able to catch synonyms, to observe specific attributes are more important than others, and to propose most adequate alternatives when no match is found.

This engine is efficiently incorporated and served through Touchpoint studio in order to ensure intelligent search on digital platforms.


Smart Search ensures that every user while browsing is equipped with an intelligent way to search the content or relevant information available, thus allowing the visitors to freely express and formulate their inquiry or interest in some particular topic.

Smart Search top characteristics:

  • Recognize context - understands what you mean even if you use verbs and adjectives in different grammatical forms

  • Typos tolerant - tolerates typing and spelling mistakes and shows relevant results

  • Multilingual - understands any language you search in

  • Recognize synonyms - understands if you use synonyms, and gives options to define more synonyms specific for each industry

  • Letter agnostic - supports alphabet, cyrillic

  • Configurable training options - you can be involved in the model fine tuning, choose features to boost or define stop words.

How is Smart search integrated

To integrate Smart serarch to your website, follow the next steps:

Step 1 – Create a Touchpoint, type Smart search

Step 2 – Select where you would like to place your Smart search

Step 3 – Select the maximum number of outputs you want to display as seach results, product attributes and the matching score percentage of the search results

Step 4 – Touchpoint overview – take a look at all your settings of this touchpoint and finish if you are satisfied with them.

Smart Search metrics

Metrics collected through Smart Search:

  • Total number of searches in selected period

  • Unique search users

  • Average daily search

  • Product page views from Smart Search

  • Revenue generated from Smart Search

  • Top Query Searches

  • Product page views from Smart Search

  • Avg product visit duration from Smart Search

  • Avg product visit duration not triggered by Smart Search

  • Popular visiting hours (weekly average in selected period)

Navigate to Touchpoint studio > Create new touchpoint > under Touchpoint type choose Smart recommendations > Carousel. In step 3, choose how many slots you want to be served through this touchpoint.

How to add a new strategy

Navigate to Touchpoint studio > choose any created touchpoint from the list or create a new one > Actions > Add new strategy. You can select already created strategy or create new strategy from the button in the top right corner.

Smart recommendations metrics

Metrics collected from Smart recommendations:

  • Number of requests from Smart recommendations

  • Product page view from Smart recommendations

  • Revenue generated from clicked products on Smart recommendations

  • Popular visiting hours (weekly average in selected period)

Use cases

I have product(s) - how to find the right audience?

In this example, we are offering specific products to our customer(s). This is useful for seasonal products that you want to sell in a specific timeframe (e.g. swimming pools, equipment, seasonal fruit etc).

Follow next steps to reach this goal:

  • Navigate to Touchpoint studio and create Carousel touchpoint

  • On step 3 select Boost chosen products goal and number of slots in your carousel

  • Next, under default strategy choose Selected Products from Product Catalogue

  • Search for your products and select them. You can switch their positions by dragging each slot and placing it on a desired position.

Back to top