Launched by OpenAI at the end of November, chatGPT has changed the perception of what’s possible using Artificial Intelligence. Its disruptive impact on the public consciousness has been compared to the launch of the iPhone in 2007. No doubt you’re already familiar, but what’s new is how generative pre-trained language model (GPT) can transform analytics—and how at Sisense, we’re taking the lead in supercharging analytics with all the power that GPT has to offer. In this article, you’ll learn how to use it to save time and effort from your operational analytics processes and gain more insight.
Built on top of GPT–3.5 as a Generative Pre-training Transformer language model, chatGPT generates responses to a broad range of user inputs and has opened up a massive array of use cases, from automating coding, customer service responses, providing language translation, and more. It’s even poised to change how to fundamentally get answers to simple questions and queries that we currently use Google for today.
chatGPT is early in the process of changing the way we work and is currently available for research preview only. At Sisense, we immediately saw a new undiscovered use case for generative pre-trained Transformers, one that analytics professionals and operations face every day: automating enriching and augmenting analytics with new fields, segmentations, and classifications, all on-demand. It has the potential to eliminate much of the pain and effort associated with traditional data preparation and, in the process, enables analysts to enable teams to segment and slice data in new ways, on-the-fly.
It’s only feasible if you tightly integrate GPT with your analytics tooling, and we’ll show you how it works with Sisense in this post. Seamlessly integrating GPT-3 to supercharge your analytics for you and your team is now possible. It’s easy to do, and we think you’ll find it’s a game-changer.
Why you need to integrate GPT with your analytics tooling
Teams often spend way too much time in manual data prep and enrichment today. Estimates range as high as business and data analysts spending 70 to 80% of their time getting data ready for analytics, a large portion of that spent enriching and labeling data and creating new attributes to aid analysis. It’s often incredibly onerous work. Adding new fields to the data sets for analysts to slice and dice by is often painful. For example, consider a seemingly simple query:
“What’s the breakout of my customers by industry?”
It’s the kind of question that’s critical to make decisions about entering new markets and launching new products. But what if the thousands of customers in the data set haven’t been segmented by industry in the data beforehand? Industry isn’t a field in the data or data model. As an analyst, it almost certainly usually means you’re out of luck without investing significant time and effort.
It typically means going back to the data, adding that classification to the data set, and reloading it in your data warehouse, and that’s incredibly time-consuming. In many cases, it requires manually matching with third-party data sets, repetitive Google searches to tag customer records manually, and often painful convoluted IF () and VLOOKUP () formulae in Excel or custom Python script. Not to mention updating your data model.
Worse, if teams subsequently need to classify and label data in a new way – such as by zip code or county, then it’s back to manually prepping the data again.
Here’s the thing, GPT can do that work for you and do it automatically. But it has to be woven into your analytics experience to make it truly useful. The opportunity is to have your own AI-powered always-on personal data prep and data analyst bot as part of your analytics experience, so you can extend and augment your data and data model by simply asking GPT.
Achieving it creates a massive opportunity for teams, freeing them from manual work prepping and augmenting data, using GPT to do the lifting to spend time on more value-added and strategic work. But more importantly, beyond freeing up time, there’s transformational value to be had―enabling teams to be much more fluid in their analytical queries, segmenting data in new ways, with GPT doing the work behind the scenes.
Sisense + GPT-3: A new way to supercharge your analytics
We wanted to bring this exact power directly within Sisense Fusion by seamlessly integrating GPT-3. The new integration leverages the uniquely flexible capabilities of Sisense Fusion by building and running Python code from Sisense to phrase dynamic queries to GPT-3, automatically generating new database tables and relationships in the Sisense ElastiCube based on the results from GPT-3.
We’ve created a brand-new UI that uses Sisense’s flexible APIs to provide an interactive Q&amp;A environment in Sisense BloX, so your Sisense users can tell GPT-3 how they want to augment the data set and model, and do so directly in their dashboards, and Sisense and GPT-3 will immediately handle the rest.
Let’s see how it all works by answering the question we began this post with, “What’s the breakout of my customers by industry?”—when the customer attribute industry doesn’t appear in your data model or data set. We will use Sisense and GPT-3 to fill the gap.
Below is the example data with our accounts. But we’re ultimately looking for the percentage split of customers by industry, so we need that industry attribute added, which doesn’t exist in the data.
<img loading="lazy" decoding="async" class="aligncenter wp-image-739967 size-full" src="https://cdn.sisense.com/wp-content/uploads/widget_63c07d89b86f51002cb28844-2-e1673629205323.png" alt="" width="553" height="337" srcset="https://cdn.sisense.com/wp-content/uploads/widget_63c07d89b86f51002cb28844-2-e1673629205323.png 553w, https://cdn.sisense.com/wp-content/uploads/widget_63c07d89b86f51002cb28844-2-e1673629205323-300x183.png 300w" sizes="(max-width: 553px) 100vw, 553px" />
To make it easy to ask questions to GPT-3 for what we need, we used Sisense BloX to build a simple interactive widget on a Sisense dashboard. We’ll use the new UI to phrase what we need to GPT-3:
<img loading="lazy" decoding="async" class="aligncenter wp-image-739932 size-full" src="https://cdn.sisense.com/wp-content/uploads/gpt_connect.jpg" alt="" width="1905" height="654" srcset="https://cdn.sisense.com/wp-content/uploads/gpt_connect.jpg 1905w, https://cdn.sisense.com/wp-content/uploads/gpt_connect-300x103.jpg 300w, https://cdn.sisense.com/wp-content/uploads/gpt_connect-1024x352.jpg 1024w" sizes="(max-width: 1905px) 100vw, 1905px" />
In this example, we’re telling GPT-3 that we want the industry segmentation for a list of companies in natural language. And we provide it with the dashboard, widget, and column name, which ultimately contains the list of companies we want to get the industry labeling on from GPT-3.
The UI then executes a Python script containing the question and the dynamically populated list of customer accounts formatted as JSON and submits it to GPT-3, which retrieves the industry for each customer.  Alternatively, if we want to add GPT-3 enrichment to the scheduled periodic data model refresh, simply executing Python rather than using the Q&amp;A UI, we can do that too.
The result set is passed back from GPT-3 to Sisense Fusion as a JSON document. The Python script dynamically creates new tables in the ElastiCube (or your database) based on the GPT-3 result set and adds new relationships between tables in the model. Ultimately, it transforms hours or days of data enrichment effort into seconds on the fly.
In the example, GPT-3 provides back each customer and their associated industry label in this example in JSON. Then, the script appends this as a new dimension to our data model and automatically joins our fact table of wins and losses with a natural join based on the account name.
<img loading="lazy" decoding="async" class="aligncenter wp-image-739968 size-full" src="https://cdn.sisense.com/wp-content/uploads/widget_63c0851fb86f51002cb28860-e1673629306872.png" alt="" width="310" height="336" srcset="https://cdn.sisense.com/wp-content/uploads/widget_63c0851fb86f51002cb28860-e1673629306872.png 310w, https://cdn.sisense.com/wp-content/uploads/widget_63c0851fb86f51002cb28860-e1673629306872-277x300.png 277w" sizes="(max-width: 310px) 100vw, 310px" />
With augmented data, all added to our data model in hand, it’s simple to continue our analysis. For example, we can quickly create two new visualizations using Sisense Fusion that show us the distribution of our customers by industry.
<img loading="lazy" decoding="async" class="wp-image-739969 size-large aligncenter" src="https://cdn.sisense.com/wp-content/uploads/widget_63c080a6b86f51002cb2884d-1-1024x273.png" alt="" width="1024" height="273" srcset="https://cdn.sisense.com/wp-content/uploads/widget_63c080a6b86f51002cb2884d-1-1024x273.png 1024w, https://cdn.sisense.com/wp-content/uploads/widget_63c080a6b86f51002cb2884d-1-300x80.png 300w, https://cdn.sisense.com/wp-content/uploads/widget_63c080a6b86f51002cb2884d-1.png 1439w" sizes="(max-width: 1024px) 100vw, 1024px" />The whole integration enables us to complete the analysis in a few minutes instead of weeks. Using the interactive BloX widget, it’s simple to augment and enrich any other data powered by GPT-3, all using natural language.
And one more thing. If you’re a software company, you can add GPT-3 supercharged analytics to Sisense Fusion Embed by embedding the BloX widget in your product. So, you can differentiate and wow your customers and prospect with an in-product embedded analytics experience powered by GPT-3.
The unique flexibility of Sisense Fusion is critical for this kind of GPT-3 integration, and we’ve made it simple to try it all out for yourself and start your Sisense + GPT-3 journey.
After receiving a lot of interests from corporates around the world to use this extremely powerful language model, OpenAI has come up with corporate accounts which allow the corporate users to sign a special Memorandum of Understanding (MoU) and Data Privacy Agreement (DPA) with OpenAI to overcome the concerns around the data leaks and data privacy. Please reach out directly to OpenAI to inquire about these corporate accounts and how to best protect your data.

How to Supercharge Your Analytics with GPT Language Models

LinkedIn

Twitter

GitHub

curve-image-unique-image-unique

curve

3-dark-2-image-unique-image-unique

3 DARK 2

Get the latest in analytics right in your inbox.

Article