AI-enabled Conversations with Analytics Tables

Published in Towards Data Science

Preview:
In recent years, the amount of data powering different industries, and their systems has been increasing exponentially. Majority of business information is stored in the form of relational databases that store, process, and retrieve data. Databases power information systems across multiple industries, for instance, consumer tech (e.g. orders, cancellations, refunds), supply chain (e.g. raw materials, stocks, vendors), healthcare (e.g. medical records), finance (e.g. financial business metrics), customer support, search engines, and much more.

It is imperative for modern data-driven companies to track the real-time state of its business in order to quickly understand and diagnose any emerging issues, trends, or anomalies in the data and take immediate corrective actions. This work is usually performed manually by business analysts who compose complex queries in declarative query languages like SQL to derive business insights stored in multiple tables. These results are typically processed in the form of charts or graphs to enable leadership teams to quickly visualize the results and facilitate data-driven decision making.

Although the most common SQL queries that address fundamental business metrics are predefined and incorporated in commercial products like PowerBi that power insights into business metrics, any new or follow-up business queries still need to be manually coded by the analysts. Such static interactions between database queries and consumption of the corresponding results require time-consuming manual intervention and result in slow feedback cycles. It is vastly more efficient to have non-technical business leaders directly interact with the analytics tables via natural language queries that abstract away the underlying SQL code.

 👉 Here is the full article