PolyAnalyst is a system used to create scenarios for text and data analysis, to build machine learning and artificial intelligence models, to develop complex intellectual solutions to work with data. PolyAnalyst does not require programming skills (No-code / Low-code paradigm). PolyAnalyst also provides a construction tool to create interactive graphical reports (BI model).

Use PolyAnalyst to access data from databases and files, make changes to the data, analyze the data with statistical models, and create reports that summarize your findings.

Our users have varied backgrounds. Some have significant experience in data analysis, and/or doctorates in various technical fields, whereas others might come from a liberal arts or business background. Some are self-employed, and some work for large companies. Our users are located all around the globe.

The documentation assumes only a minimal amount of experience with data processing and statistics. The documentation is written so as to prioritize understanding, and strives to provide simple explanations, with the hope that you become self-proficient and empowered. However, certain concepts, such as the inner-workings of an algorithm, can only be simplified to a certain extent. Where possible, the documentation uses analogies to explain a feature, even if such explanations do not stand up to a stricter mathematical rigor.

The documentation is organized to serve as both an introduction and a reference. A good place to start is with the Introduction to PolyAnalyst topic. If you just want to know how a particular node works, skip to the Node reference section.

PolyAnalyst by Megaputer Intelligence, Inc. extracts insights and knowledge from large and complex datasets.

PolyAnalyst is used in a variety of industries including finance, healthcare, marketing, and government agencies to support decision-making and gain a deeper understanding of complex datasets.

PolyAnalyst supports advanced machine learning and natural language processing techniques to automatically analyze unstructured data such as text documents, social media posts, emails, and more. It can also handle structured data such as spreadsheets and databases.

PolyAnalyst provides a wide range of analysis capabilities including data visualization, sentiment analysis, topic modeling, clustering, classification, and predictive modeling. Users can also customize and automate their analysis processes using PolyAnalyst’s scripting and automation features.

The software provides a graphical user interface (GUI) that allows users to perform various data analysis tasks such as data preprocessing, data exploration, feature extraction, and modeling without the need for coding.

PolyAnalyst is a low-code platform that required very little programming knowledge to use. However, programming knowledge can be helpful in some cases. Additionally, it is possible to run Python or R scripts within PolyAnalyst to perform custom data transformations or modeling.

Some nodes require the use of a very simple proprietary language called SRL, and many of PolyAnalyst’s text analytics features use feature extraction languages called PDL (pattern definition language) and XPDL (extended pattern definition language).

Yes. PolyAnalyst is designed to process and analyze large volumes of data quickly and efficiently. It supports import from a variety of data sources so that you can combine and analyze data from multiple sources at the same time.

You can present your data and to visualize the results of your work in the form of interactive PolyAnalyst Reports. You also may use special visualization nodes to present the results in various charts.

However, the time required to process a dataset may depend on the power of your machine. If your dataset is too big to be processed by a single machine, we recommend that you upgrade to PolyAnalyst Grid, which supports cluster computing.

PolyAnalyst provides secure connection with the HTTPS protocol and corresponding certificates. Your sensitive data are stored in in encrypted form and can be transferred from the client to the server only. You can also control access to your data at various security levels, e.g. at the level of a project, a node or a dataset. Moreover, administrative user can enhance data security and privacy with the operating system tools.