Software, data and business teams build solutions together, seamlessly combining their technical and domain expertise
Trusted by financial and telecom companies to handle heavy data processing and decision making
Business Team
Apply Your Domain Knowledge with Zero-Delay
Express decision algorithms with self-explanatory flow diagrams |
Use spreadsheet-like formulas for even the most complicated data transformations and boolean conditions |
Verify your ideas instantly using one-click deployment and testing functionalities |
Data Team
Productionize ML Inference for Demanding Workloads
Focus on ML insights, not ML model deployment |
Use RAG, add model pre and postprocessing and ensemble multiple models |
Infer models in your favourite format: Python, ONNX, or PMML |
Software Team
Engage Stakeholders in Data Processing without Compromising Technological Advancements
Set up integrations and let domain experts make use of the data |
Use the power of Flink while keeping it under the hood |
Adjust to your specific needs - add UDFs and specialized components |
Product
Ease of Use
flow diagrams for decision algorithms
less code with powerful expression language
autocompletion and validation
real-time monitoring and metrics
rapid testing tools
easy migration across environments
one-click process deployment
version history management
customisable and extensible
exposed REST API for automation and integration
Deployment Flexibility
Run on-premises or on K8s, with support for both deployment modes
unifies both streaming & batch processing
integration with Ververica Platform
Kafka® source and sink interfaces, integration with platforms like Confluent® Cloud, Azure Event Hubs® and Aiven®
data lakes & warehouses support by Flink's connectors
databases source & sink interfaces
REST (OpenAPI) and database (JDBC) enrichments
ML models inferring enrichments → how to?
open source with enterprise extensions
on premises and cloud → play with it
Nussknacker is a graphical tool to define, deploy and monitor Apache Flink jobs. Job logic is expressed by a graph, with SpEL used for data transformations and boolean conditions.
Nussknacker supports various data sources - Kafka streams, files, databases, HTTP APIs, and many others, either natively or via Flink connectors.
Use Cases
Real-time Marketing
Communications with customers in real-time, providing event-driven offers and actions
RTM Automation
Fraud Management
Mitigating fraud by running detection algorithms on network or device signals
Fraud Monitoring
Next Best Action
Assisting the Point Of Sale, displaying suggestions about what to offer and how to proceed with a customer
Recommendation System
Customer Data Processing
Decisioning on dynamic customer data in
- dynamic pricing
- order status management
- instant credit scoring
Internet of Things
Automating actionable data in
- predictive maintenance
- inventory management
- smart devices
Gaming Engagement
ML Models Deployment
Infer Machine Learning models from within complex decision algorithms
ML Inference
Offer
Freemium
Hosted by Nussknacker
Quick solution for straightforward yet demanding data streaming tasks without exhausting investment decisions
Pro
Hosted by Nussknacker
Ready-to-use collection of features and integrations for advanced data environments with affordable infrastructure maintenance expenses
Enterprise
Self-hosted / On Premise / BYOC / by Nussknacker
Extensible tool fitted for superior technology stacks where unique data integrity is required
Blog
Integrate Azure Databricks MLflow for machine learning model management and inference
This text provides a comprehensive guide on integrating Nussknacker Cloud with Azure Databricks' managed MLflow service, enabling users to easily incorporate machine learning models into their data processing workflows.
How to train and register ML models in Azure Databricks
This article explains how to train and register a machine learning model in Azure Databricks that can later be used for credit card fraud detection in Nussknacker Cloud.
Next-Generation Real-Time Rating Systems
This blog post explains the rationale behind the shift from asynchronous architectures to stateful stream processing in real-time rating systems.
Next Steps
see the demo in action
try it yourself
feel free to contact us