PolyAnalyst

Can load and merge data from diverse sources including databases (OLE DB, ODBC), Microsoft Office files, PDF, OCR, web pages, emails, XML, JSON, Facebook posts, Twitter feeds, CSV, and flat files.

Includes capabilities for imputing missing values, correcting spelling errors, deduplication, handling outliers, and ensuring data quality (validity, accuracy, completeness, consistency, uniformity).

Offers a broad selection of algorithms for tasks like classification, clustering, prediction, anomaly detection, affinity grouping, network analysis, and time series modeling (e.g., neural networks, decision trees, Bayesian networks, SVM, CHAID, logistic regression, adaptive boosting, MARS).

Features for accurately extracting facts and relationships, performing sentiment analysis, entity recognition, document classification, clustering, keyword extraction, and handling multiple languages.

Creates stunning reports that summarize and communicate insights in graphical form.

Specifically designed for accurate extraction of facts and relationships, clustering, and sentiment analysis on free text documents, supporting multiple languages (over 16) and document formats.

Builds models that predict outcomes of future situations, training on a mixture of structured attributes and free text.

Delivers analytical results in simple graphical form to numerous non-technical users via a browser-based, interactive interface with 24/7 accessibility.

Allows preferences on color, graph type, drill-down information, company logo, and provides personalized administrative control over sensitive information.

Reports can be programmed to update at specified intervals, providing near real-time information.

Supports analyzing Big Data on a cluster of low-grade machines by splitting tasks and executing them in parallel.

Allows users to perform complex analysis through a visual drag-and-drop interface without writing complex code.

Provides tools for normalization, aggregation, sampling, partitioning, and derivation of new attributes.

Supports building OLAP cubes for slicing data across multiple dimensions, including on free text.

Provides a variety of machine learning engines.

Offers visual tools for developing multi-step data analysis scenarios.

Designed to handle huge amounts of data efficiently, with cluster implementation options for Big Data.

Operates on a client-server architecture with encrypted TCP/IP communications.

Features user name and password authentication, support for LDAP and MS Windows authentication, user activity logging, and HIPAA compliance.

Analytical scripts can be scheduled for automated execution and reports for automated publishing.

Supports built-in, imported, and user-defined dictionaries for phrases, stop-words, synonyms, and semantic relations.

Powerful query syntax for information retrieval.

Supports categorization based on taxonomies.

Performs binary and hierarchical text clustering.

Extracts keywords, entities (over 30 standard types), facts (over 40 standard types), and relationships from text.

Analyzes the sentiment expressed in text.

Automatically detects and classifies languages.

Includes various graphical outputs like histograms, scatter plots, line charts, thermal charts, rule graphs, link charts, and trend graphs.