Recombee | Recommendation as a Service, REST API + SDK

Why Recombee

Save time and money developing own recommender system
Rather use the most advanced engine tailored by data scientists

Real time recommendation as a service

Our API/SDK returns the recommendations immediately after user’s action at your website or in your app in less than 200 ms.

Scalable solution

We can deliver the service no matter how large is the traffic at your website. Our system is capable of delivering more than 500 recommendations per second.

User interface

You can check the key performance indicators in near real-time using our intuitive graphical user interface (GUI).

Domain independence

Our system is successfully used for recommending movies, news, cultural events, books, songs, job advertisements, or products in eshops. It is easily adaptable to any other domain.

Easy setting of rules

You can express your business or any other rules by our simple query language ReQL. The filter and the booster can be set independently for each recommendation request.

Research and improvements

We use sophisticated algorithms in the core of our recommendation engine. The models are continuously managed and improved by the Artificial Intelligence.

Use cases

Website Personalization
Personalized Emails
Cross-domain Recommendations
Multi-channel Recommendations
Product Recommendations
Big Data Recommendations
Behavioral Analytics
Faster Product Discovery

Benefits

Increased Conversion Rate
Higher Profits
Increased Loyalty
Increased Retention
Improved User Experience
Increased Lifetime Value
Reduced Churn and Confusion
AI Driven A/B Testing

Domain expertise

Jobs, Career Recommender
Cultural Events
Video on Demand/Streaming
Music/Song Recommendation
News and Articles
Consumer Products
Sport Equipment
…

…and many others.

Thanks to Recombee, by continuous changes in our website and emailing, we managed to lift the total number of responses.

Recombee opened us many new possibilities in recommending relevant events, places, and artists, to our customers. It works great.

@showmaxonline what did you guys do to your recommendations engine??? it's flipping awesome. Discovered so much. #innovation.

How to use

The recommendations are provided via RESTful API and we provide SDKs for multiple programming languages.

client = RecombeeClient.new('database-id', secret_token)

# Send purchase of item 'item_x' by user 'user_42'. Create user and/or item if it doesn't exist yet.
client.send( AddPurchase.new('user_42', 'item_x', 'cascadeCreate' => true) )

# Get 5 recommended items for user 'user_42'. Recommend only items which haven't expired yet.
recommended = client.send( UserBasedRecommendation.new('user_42', 5, 'filter' => " 'expires' > now()") )

See Recombee API Client for Ruby on Github

RecombeeClient client = new RecombeeClient("database-id", secretToken);

// Send purchase of item "item_x" by user "user_42". Create user and/or item if it doesn't exist yet.
client.send(new AddPurchase("user_42", "item_x").setCascadeCreate(true));

// Get 5 recommended items for user "user_42". Recommend only items which haven't expired yet.
Recommendation[] recommended = client.send(new UserBasedRecommendation("user_42", 5).setFilter(" 'expires' > now()"));

See Recombee API Client for Java on Github

client = RecombeeClient('database-id', secret_token)

# Send purchase of item 'item_x' by user 'user_42'. Create user and/or item if it doesn't exist yet.
client.send( AddPurchase('user_42', 'item_x', cascade_create=True ) )

# Get 5 recommended items for user 'user_42'. Recommend only items which haven't expired yet.
recommended = client.send( UserBasedRecommendation('user_42', 5, filter=" 'expires' > now()") )

See Recombee API Client for Python on Github

$client = new Client('database-id', secret_token);

// Send purchase of item 'item_x' by user 'user_42'. Create user and/or item if it doesn't exist yet.
$client->send( new Reqs\AddPurchase('user_42', 'item_x', ['cascadeCreate' => true]) );

// Get 5 recommended items for user 'user_42'. Recommend only items which haven't expired yet.
$recommended = $client->send( new Reqs\UserBasedRecommendation('user_42', 5, ['filter' => " 'expires' > now()"]) );

See Recombee API Client for PHP on Github

var client = new RecombeeClient("database_id", secretToken);

// Send purchase of item "item_x" by user "user_42". Create user and/or item if it doesn't exist yet.
client.Send( new AddPurchase("user_42", "item_x", cascadeCreate: true) );

// Get 5 recommended items for user 'user_42'. Recommend only items which haven't expired yet.
var recommended = client.Send( new UserBasedRecommendation("user_42", 5, filter: " 'expires' > now()") );

See Recombee API Client for .NET on Github

# Send purchase of item 'item_x' by user 'user_id'. Create user and/or item if it doesn't exist yet.
POST http://rapi.recombee.com/database_id/purchases/
Data: {'userId': 'user_42', 'itemId': 'item_x', 'cascadeCreate': true}

# Get 5 recommended items for user 'user_42'.
# Recommend only items which haven't expired yet (filter: 'expires' > now()).
GET http://rapi.recombee.com/database_id/users/user_42/recomms/?count=5&filter=expires%27%20%3E%20now()

See more API Documentation

Personalized recommendations in less than 10 minutes using Recombee

Explore full documentation

Pricing

Free

$0 / month

Great for trying our service out

Full API functionality
99,999 free recommendation requests/month

Create instant account

Standard

From $100 / month

Serious usage in real business

Full API functionality
Nearly unlimited number of recommendation requests according to the price list
Guaranteed response time and availability
Full support
Service Level Agreement
Optimization of models by the AI

Order from $100 / month

Alternative

We can also offer performance pricing (part of the generated additional revenue) for higher volumes. Please contact us for further info.

Team

We’re ahead in innovations and focus on data products. You’ll benefit from 15+ years of our data science experience and top machine-learning research results.