Catalyst
Unstructured data transformation for optimal outcomes
lyrical Catalyst™ is an industry-leading unstructured data transformation engine and semantic intelligence platform. Catalyst uses lyrical’s core technology for a variety of data integration, transformation, and activation use cases. For text and speech recognition and semantic analysis, Catalyst automatically tunes algorithms and their hyper-parameters to produce an ensemble of the best-performing models. The result is an adaptive, audit-capable, and agnostic knowledge discovery tool for prediction, pattern recognition, and insights automation.
Catalyst is a distributed in-memory machine learning and natural language processing system with linear scalability. Catalyst supports the most widely used statistical & machine learning algorithms including gradient boosted machines, generalized linear models, deep learning and more. The lyrical catalyst platform is used by blue chip organizations globally and is extremely popular in both the R & Python communities.
leading algorithms
Algorithms developed from the ground up for distributed computing and for both supervised and unsupervised approaches including Random Forest, GLM, GBM, XGBoost, GLRM, Word2Vec and many more.
access from r, python, flow, and more
Use the programing language you already know like R, Python and others to build models in lyrical, or use lyrical mosaic, a graphical notebook based interactive user interface that does not require any coding.
AUTO ML/NLP
lyrical’s AutoML/NLP can be used for automating the machine learning workflow, which includes automatic training and tuning of many models within a user-specified time limit. Stacked Ensembles will be automatically trained on collections of individual models to produce highly predictive ensemble models which, in most cases, will be the top performing models in the AutoML Leaderboard.
distributed in-memory processing
In-memory processing with fast serialization between nodes and clusters to support massive datasets. Distributed processing on big data delivers speeds up to 100x faster with fine-grain parallelism, enabling optimal efficiency without introducing degradation in computational accuracy.
high-volume data agnostic
No matter how many messages your company gets each day, hour, minute, or even second - lyrical Catalyst can process it in real-time. Catalyst can process any type of streaming text data - contact center interactions, chatbot transcripts, incoming survey responses - in real-time and in fifteen languages.
real-time
You shouldn’t have to wait to understand your data. lyrical Catalyst processes any amount of structured and unstructured data as it hits your data center in real time.
uncover root causes
Machines can see connections where humans do not. lyrical Catalyst finds and groups similarities in streaming data to uncover root causes.
flexible clustering
Leverage supervised, semi-supervised, or unsupervised classification to feed into workflows like agent routing and bot support. Build and automate end-to-end processes, from agent routing to bot support, by connecting multiple catalyst classifiers.
Enterprise Data Transformation
Catalyst works on existing big data infrastructure, on bare metal or on top of existing Hadoop or Spark clusters. It can ingest both structured and unstructured data directly from HDFS, Spark, S3, Azure Data Lake or any other data source into it’s in-memory distributed key value store.
Distributed, In-Memory Machine Learning
lyrical Catalyst takes advantage of the computing power of distributed systems and in-memory computing to accelerate machine learning using it’s industry parallelized algorithms which take advantage of fine grained in-memory map reduce.
Seamless Deployment
Quickly and easily deploy models into production with Java (POJO) and binary formats (MOJO). In addition, lyrical models can be production-ready in a host of different workflows and frameworks custom to your enterprise architecture.
