Загрузка видео...

Не удалось загрузить видео

На главную

You can use ChatGPT in Excel or Google Sheets for data analysis with Numerous AI for things like: • Reformatting phone numbers • Classifying customer review topics • Removing names from support emails • Sentiment analysis of customer reviews Here are some more examples:

239,336 просмотров • 1 год назад •via X (Twitter)

Комментарии: 12

Фото профиля Future Stacked
Future Stacked1 год назад

BREAKING NEWS!!!! ChatGPT now works in Excel and Google Sheets. No need to memorizing formulas & functions. Here’s how to use AI to EXCEL at Excel!

Фото профиля Future Stacked
Future Stacked1 год назад

Numerous is an add-on that can prompt ChatGPT inside Excel or Google Sheets for many tasks such as writing, researching, translating, rewriting, and more. It can help you streamline your work and increase productivity. Here's how it works:

Фото профиля Future Stacked
Future Stacked1 год назад

1. =AI command. You can use the =AI (...) command to run ChatGPT on a lot of things at once. Just drag it down to use ChatGPT multiple times.

Фото профиля Future Stacked
Future Stacked1 год назад

2. =INFER command. You can make things automatic by using the =INFER (...) command in Numerous. Provide a few examples, and ChatGPT will handle the tasks for you. It's really easy.

Фото профиля Future Stacked
Future Stacked1 год назад

3. =WRITE command. You can use this command to make ChatGPT write marketing texts, SEO descriptions, or other business-related stuff.

Фото профиля Future Stacked
Future Stacked1 год назад

Don't hesitate! Try this amazing tool today!

Фото профиля Future Stacked
Future Stacked1 год назад

Get the latest AI and Tech updates in your inbox for FREE. Join our Tech and AI community of 15,000+ readers:

Фото профиля Future Stacked
Future Stacked1 год назад

If you enjoyed this thread: Follow and turn on notification for @FutureStacked for more valuable contents like this. Pease don’t forget to engage with the first post by bookmarking, liking, commenting, and reposting.

Фото профиля Future Stacked
Future Stacked1 год назад

Vibe coding just went next level

Фото профиля IDI Consulting
IDI Consulting1 год назад

Turn data into actionable insights with IDI Consulting’s Analytics services. We help you unlock the power of your data to drive smarter decisions and achieve better outcomes. Contact us today to get started.

Фото профиля Manish
Manish1 год назад

Can chat gpt create interactive dashboards in Excel using pivot or slicers and other themes?

Фото профиля Marcel • ᴗ •
Marcel • ᴗ •1 год назад

That's not ChatGPT, that's Gemini!

Похожие видео

Data teams spend weeks on simple requests. (This AI answers them in minutes.) Most data analysis is repetitive manual tasks. Data teams spend more time on setup than actual analysis. The workflow usually looks like this: → Run some exploratory data analysis in a local Jupyter notebook or environment → Pull data from multiple disconnected sources → Write code from scratch for every analysis → Export static charts that stakeholders can't explore (or wrestle with legacy BI to create a dashboard) → Manually send updates via email or Slack when data changes → Start over for each new request Most teams accept this as "how data analysis works." While business decisions wait for insights. That's where Fabi changes the entire approach. It's a powerful, AI-native platform built for teams that want to boost productivity and supercharge their data workflows. Instead of working on separate tools and manual processes, you collaborate on analysis that automatically delivers insights where teams work. Here's what makes Fabi different: AI-Native Analysis Environment ↳ SQL and Python work together with AI assistance that handles coding and debugging automatically. Smart Automation Workflows ↳ Automatically send AI-powered reports and summaries right where business works in Slack, email, and spreadsheets. Universal Data Integration ↳ Analyze data from files, Google Sheets, Airtable, plus your data warehouse and databases in one place. Collaborative Data Apps ↳ Create interactive dashboards that stakeholders can explore and ask follow-up questions directly. What you can do with Fabi that legacy BI can't: ➟ Send AI-generated insights directly to Slack channels ➟ Automatically email data summaries to stakeholders ➟ Analyze uploaded files without complex ETL processes ➟ Collaborate on analysis like Google Docs for data ➟ Build workflows that push insights to spreadsheets Perfect for teams that want to move beyond the constraints of legacy and increase their impact. Teams using Fabi see immediate results: ✓ Insights delivered in minutes instead of days ✓ Reduced context switching between tools ✓ Stakeholders explore data independently ✓ Workflows automated to save hours of manual work From analysis to automated delivery - all in one AI-native environment. 📌 Try Fabi today: 👉 Follow Fabi.ai and marc for Fabi updates. 🔄 Repost to help other teams streamline data analysis #DataAnalysis #ModernBI #DataOps #InteractiveDashboards #FabiPartnership #SponsoredByFabi

Andrew Bolis

36,504 просмотров • 9 месяцев назад

Big step forward for root cause analysis in real-world applications! There’s a new method that will help identify the causes of a problem or event. It uses causal discovery, boosting trees together with TDA. This is crucial to enable root cause analysis in tasks like the following: • Fraud detection • Drug discovery • Customer behavior analysis • Energy and sustainability • Financial analysis and risk management • Failure analysis in engineering systems Topological data analysis (TDA), on the other hand, studies the topological properties of data sets. You can use TDA for clustering, classification, and anomaly detection. The team DataRefiner developed a new approach to integrating causal discovery with TDA segmentation, and they are getting the best results from anything in the market right now. For the first time, there's a tool where users can choose clusters and get a focused causal dependency graph. They use boosting trees to estimate causal effects in complex systems. They complement this approach with TDA by offering insights into potential causal pathways. With TDA, users can visualize and understand the relationship between variables. Most open-source systems struggle with categorical parameters or values with different scales. This new approach doesn’t have those problems. Look at the attached video to understand what you can do with this. Here is a link to a post with all of the details. It contains three detailed examples that will drive the idea home: Thanks to DataRefiner for sponsoring this post.

Santiago

234,763 просмотров • 2 лет назад