Modern analytics solutions succeed to understand and predict phenomenons in a large diversity of software systems, from social networks to Internet-of-Things platforms. This success challenges analytics algorithms to deal with more and more complex data, which often heavily evolve over time. GreyCat emerges after several years of research to efficiently analyze large-scale data in live. It is designed as a toolset to develop customized operational decision-making tools, able to run on big data centers but also on commodity hardware.
Create Digital Twins of your production tools by learning their behavior from their historical data, to produce prediction and simulation engines which accuracy outruns theoretical models by taking into account all your business' specificity.
Models can be trained continuously to reflect the most recent evolution of your business, and take into account the impacts of seasonality, markets trends, shifts, etc. so their predictions are always up-to-date. And by the way, learning this way is cheaper than learning by huge batches.
Give a try to machine learning and data analytics with GreyCat without investing in a huge infrastructure. We made sure that learning can run on commodity hardware, leveraging a great team work between storage disks and RAM. Then, if you want to scale, GreyCat will make the best of the resources at its disposal to accelerate the data processing.
GreyCat provides state-of-the-art machine learning algorithms, like neural networks and Gaussian mixture models, specifically adapted to take advantage of its temporal graph and empower your businesses with insights refined from your data.
GreyCat can be embedded in applications, deployed on a server on premises, embedded on edge computing platforms, or run in the cloud; you decide what suits you best.
As former researchers, we continuously look at the most advanced methods to solve your challenges. We keep a very strong connection to research institutions around the world.
Analyzing Complex Data in Motion at Scale with Temporal Graphs: T. Hartmann, F. Fouquet, M. Jimenez, R. Rouvoy, Y. Le Traon
Reasoning at runtime using time-distorted contexts: A models@ run. time based approach: T. Hartmann, F. Fouquet, G. Nain, B. Morin, J. Klein, Y. Le Traon
A native versioning concept to support historized models at runtime: T. Hartmann, F. Fouquet, G. Nain, B. Morin, J. Klein, O. Barais, Y. Le Traon
Stream my models: Reactive peer-to-peer distributed models@ run.time: T. Hartmann, A. Moawad, F. Fouquet, G. Nain, J. Klein, Y. Le Traon
Beyond discrete modeling: A continuous and efficient model for IoT: A. Moawad, T. Hartmann, F. Fouquet, G. Nain, J. Klein, Y. Le Traon
Polymer: A Model-Driven Approach for Simpler, Safer, and Evolutive Multi-Objective Optimization Development: A. Moawad, T. Hartmann, F. Fouquet, G. Nain, J. Klein, J. Bourcier
Enabling Model-Driven Live Analytics For Cyber-Physical Systems: The Case of Smart Grids: T. Hartmann
Model-Driven Analytics: Connecting Data, Domain Knowledge, and Learning: T. Hartmann, A. Moawad, F. Fouquet, G. Nain, J. Klein, Y. Le Traon, J.M. Jezequel