Open Source Ensemble of Predictive Engines
data ownership is not negotiable
comprehensible insights & forecasts
add-on to your existing data environment
customizable and extensible to your needs
From audience discovery to one-to-one relationship
Discover and leverage the most relevant hidden relations in large-scale datasets
Leverage context-sensitive information for more personalized recommendations
Predict the best decisions among multiple choices and identify their decisive factors
Uncover the intents of human behavior and reach the ultimate customer understanding
Find anomalies in large-scale datasets and human behavior for advanced risk reduction
Discover and leverage the most relevant patterns in human activity sequences
Find similarities in dynamic activity sequences and identify customers by their journeys
Determine and leverage actual trends from social media platforms in real-time
Determine look-alike ensembles from your customers' behavior
Language-agnostic semantic concept detection for semantic targeting
Near Real-time Analytics
Predictiveworks leverages the power of Apache Spark for scalable & distributed in-memory data analytics and machine learning.
New Algorithms
Predictiveworks adds Association Rule Mining, Factorization Machines, Markov Models, Sequence Mining and more to Apache Spark.
Reactive by Design
Predictiveworks is a highly concurrent, distributed and resilient application based on Typesafe Akka.
Event Tracking
Predictiveworks adds Event Tracking capability to Apache Spark based on Elasticsearch.
Unified Data Access
Predictiveworks unifies the data access to Cassandra, Elasticsearch, HBase, MongoDB, Parquet and JDBC data sources.
RESTFUL API
Predictiveworks offers a common REST API to ingest data, control machine learning and get analytics results.
Redis Data Hub
Predictiveworks leverages a common data structure server to share mining results & predictive models.
Elasticsearch API
Predictiveworks functionality can be accessed leveraging the Elasticsearch API.
Elasticsearch
Distributed real-time search & analytics platform
MongoDB
Open source NoSQL document database
Redis
Fast & distributed data structure server
Scalding / Cascading
Scala integration layers on top of Hadoop
Typesafe Akka
Actor-based runtime environment for message-driven applications
- Concurrent & Distributed
- Elastic & Decentralized
- Resilient
- Extensible
- High Performance
Typesafe Spray
REST/HTTP integration layers on top of Akka
Apache Cassandra
Scalable, highly available NoSQL database
Apache HBase
Distributed & scalable Hadoop database
Apache Kafka
Distributed publish-subscribe messaging system
Apache Parquet
Common columnar storage format for Hadoop
Apache Spark
Distributed in-memory processing large-scale data processing
Apache Spark MLlib
Scalable machine learning library
Apache SQL
SQL-based query engine for distributed data
Apache Spark Streaming
Complex event processing
Preparation
We prepare your data for optimal use with Predictiveworks.
Integration
We integrate Predictiveworks. into your technical environment.
Development
We adapt Predictiveworks. to your specific analytical needs.
Association Analysis
Discover and leverage the most relevant
hidden relations in large scale datasets.
Context-Aware Analysis
Leveraging context-sensitive information
is crucial for personalized predictions.
Intent Recognition
Uncover the intents of human behavior and reach the ultimate customer understanding.
Outlier Detection
Find anomalies in large-scale datasets and human behavior for advanced risk reduction.
Similarity Analysis
Find relevant similarities in activity sequences and identify customers by their journey.
