Boardwiser NLG incorporates best-in-class machine learning and natural-language generation (NLG) to ensure that the relevant driver factors behind KPI changes are detected and communicated without the need for manual analysis. It automatically and accurately identifies report-worthy outliers and summarizes them for easy subsequent analysis and reporting.
Boardwiser NLG
Boardwiser NLG Anomaly Detection and Summation
What Boardwiser NLG Does

Key Features
Flexible and portable
Configurable to your insight needs
On-demand, easy-to-consume data
Automates and streamlines analytical tasks
Architecture

Boardwiser NLG can use various kinds of input data (structured text, database, etc.) and has configuration storage as well, which can store parameters for the anomaly detection, the credentials for a database, etc. The scheduler triggers the solution to run the underlying algorithms, find relevant details and create a textual summary. It can also use external data sources to enrich the organization’s proprietary data. Boardwiser NLG’s output can be used in different ways, including sent via email or embedded in a dashboard or a webpage.
The Starschema Difference
Proven onboarding methodology
Experience in large environments
Flexible service models
Tools-based approach
Complete data lifecycle management
Ask the Expert
Balazs Zempleni
Data Scientist at Starschema
Balazs specializes in digital image and signal processing, and in recent years he has focused on developing a natural-language processing solution to improve internal business processes based on textual data. In addition to his work, Balazs is an avid presenter at data science meetups and conferences.

Recommended
Automating BI Analytical Tasks with Anomaly Detection and NLG Summation
Learn how to design and implement a complex solution that automatically identifies anomalies in organizational data, provides relevant context and communicates it all in an easy-to-consume form to augment analysts' work.
Starschema Inverba NLG™
As humans, we think and communicate in narratives. Numbers and visualizations help, but taken on their own, they often don’t tell the full story. A good dashboard may be useful for showing trends and conveying metrics, but it’s words that resonate with decision-makers and provide them with important context and situational awareness
Data Science Project Planning Worksheet
This downloadable worksheet contains five categories of requirements and conditions that a client-side stakeholder in a project involving data science services needs to define to ensure timely delivery, optimized cost and valuable outcomes.
On-demand Webinar: Tableau-based Workflows Most Data Leaders Don't Consider
Failing to take full advantage of Tableau to drive organizational effectiveness leads to unnecessary overhead for users and missed opportunities for innovation and profit. This webinar helps data leaders to identify and implement more effective approaches to using Tableau by demonstrating an ideal framework for dashboard-based workflows.