Manali Dhoot

In US hospitals dont get paid on the number of days a patients stay in the hospital but based on the cause of admission. this can be a good use case for hospitals and even add Gen AI to do data anaylsis what type of patients stayed longer and what measures can be taken to provide those service early

6

Lowe’s is pioneering the use of data science and AI to transform the retail experience from insight to impact! #Lowes #AI #DataScience #Innovation

17

Unlocking the Power of Change Data Capture (CDC) in Snowflake 🚀 In today’s data-driven world, speed and accuracy are everything. Businesses no longer have the luxury of waiting hours—or even minutes—for their data pipelines to refresh. Real-time insights are the new competitive edge, and that’s where Change Data Capture (CDC) in Snowflake comes into play. 🌐 What is CDC in Snowflake? Change Data Capture (CDC) is a technique that tracks and captures changes—INSERTS, UPDATES, and DELETES—in your data sources. Instead of reloading entire datasets, CDC ensures that only the changed rows are processed. In Snowflake, CDC is powered by Streams and Tasks: Streams: Record row-level changes in a source table. Tasks: Automate the execution of SQL statements to process those changes on a schedule.Together, they create a seamless pipeline for incremental data processing. ⚡ Why Does CDC Matter? Without CDC: You reload entire tables, which is costly and time-consuming. With CDC: You only process the delta (the changed data), making pipelines faster, cheaper, and more efficient. This efficiency is critical for: ETL/ELT pipelines Data replication across systems Real-time analytics and dashboards AI/ML model training with fresh data 🔑 Key Benefits of Snowflake CDC Scalability: Handles massive datasets without performance bottlenecks. Cost Optimization: Reduces compute and storage costs by avoiding full reloads. Flexibility: Works across diverse data sources and use cases. Reliability: Ensures data integrity with transactional consistency. 🛠️ Example Use Case Imagine a retail company tracking customer orders. Instead of reprocessing millions of rows daily, Snowflake CDC captures only the new or updated orders. This enables near real-time dashboards for sales teams and accurate demand forecasting for supply chain managers. 🚀 The Future of Data is Incremental As organizations scale, the need for real-time, cost-effective, and reliable data pipelines will only grow. Snowflake’s CDC capabilities are not just a technical feature—they’re a strategic enabler for modern data-driven enterprises.

3

My first six months at Amazon AGI at CBG in the role of Senior Machine Learning Data Associate, a milestone that offers a meaningful opportunity for reflection. Over the past six months, this experience has been a period of significant professional growth, continuous learning, and valuable collaboration. Being part of the Amazon AGI at CBG team has provided an environment where innovation, collaboration, and high standards of excellence are deeply embedded in everyday work. Contributing to machine learning data processes and supporting the development of reliable and responsible AI systems has been both intellectually stimulating and professionally rewarding. Reflecting on this journey so far, a few key lessons stand out: 1. Growth Through New Challenges Stepping into unfamiliar challenges and embracing responsibility has been instrumental in developing both confidence and capability. Meaningful growth often begins just beyond one’s comfort zone. 2. The Importance of Continuous Learning Working alongside highly skilled colleagues has been an invaluable source of learning. Each discussion, review, and collaborative effort contributes to a deeper understanding of machine learning systems, data quality, and problem-solving approaches. 3. Supportive and Thoughtful Leadership I feel fortunate to be part of a team where leadership genuinely supports professional growth. The managers within the team create an environment that encourages curiosity, ownership, and development. I am especially grateful to my manager for the guidance, encouragement, and support they have provided, recognising individual perspectives and helping create opportunities to continue growing. 4. Curiosity as a Driver of Progress Maintaining intellectual curiosity has been central to this journey. Exploring evolving areas such as responsible AI, improving workflows, and continuously refining technical understanding keeps the work both engaging and meaningful. 5. Focusing on Impact in the Present In a dynamic and forward-looking environment like Amazon, the most effective approach is to focus on delivering meaningful work today while learning from the remarkable people around us. As I look ahead, I remain committed to continuing to learn, contribute, and grow, while supporting the broader mission of building impactful and responsible machine learning systems. #Amazon #AI #MachineLearning #ProfessionalGrowth #ContinuousLearning #DataScience

20

Analytics teams and business users aim for the same outcome: better decisions - but they’re working across different platforms to get there. Analytics teams need the freedom to: - Build analytical pipelines quickly - Maintain data governance as business needs change - Scale themselves to handle the constant stream of ad-hoc requests Business users need: - Faster access to datasets - Confidence they’re looking at the right numbers - Quick analysis so they can make the right decisions Now imagine a single place where analytics teams build and govern data, and business users consume it - quickly, clearly, and consistently. One unified platform acting like a data expert in your pocket. - Scale your teams - Faster access to data - Lower spend

8

1 Comment

Today in my series on planning, estimates, and delivery, we dig into how teams are using data from past work to create smarter forecasts — and how you can start experimenting with this too. Monte Carlo Part 2 – Predicting the Future Without a Crystal Ball Predicting the future is hard but not impossible. Monte Carlo simulation isn’t just a fancy name. It’s a way to say: “Based on how things usually go, here’s what’s likely this time.” This isn’t theoretical — companies are using it right now to: Model delivery timelines Set realistic expectations Make smarter prioritization calls It starts simple: Track how long your teams usually take for certain types of work Use that data to simulate ranges (not fixed dates) Embrace variability instead of hiding from it Planning doesn’t need a crystal ball. It needs honest inputs and regular updates.

9

2 Comments

Learning always comes from failures and hard ways - One mistake I did in my early Analytics journey . I focused on accuracy more than usability . A 99% accurate model that no one trusts = zero impact . Today I optimize for - Explainability - Adoption - Business Confidence Accuracy can be fed post usability as we progress . #DataAnalytics #Analytics #DataScience #BusinessIntelligence #FindingPatternsInChaos

5

Snowflake Intelligence: From Data to Decisions - Atrium's AI: AI projects fail when data quality is poor and siloed. At its core, the Snowflake platform solves this by giving access to unified insights with ...

1

1 Comment

I heard Sam Altman speak at the Snowflake Summit and it blew my mind. Here are few key highlights from his conversation: 🔹 ChatGPT today is like an intern – it can help for a few hours. But in a few years? It’ll be like a full-time 𝐞𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞𝐝 𝐬𝐨𝐟𝐭𝐰𝐚𝐫𝐞 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫 working for days nonstop. 🔹 We’ll soon have 𝐀𝐈 𝐬𝐜𝐢𝐞𝐧𝐭𝐢𝐬𝐭𝐬 – agents that can discover new science on their own. That’s not just impressive… it’s world-changing. 🔹 AI will 𝐬𝐨𝐥𝐯𝐞 𝐫𝐞𝐚𝐥-𝐰𝐨𝐫𝐥𝐝 𝐩𝐫𝐨𝐛𝐥𝐞𝐦𝐬 that even teams of humans can’t figure out. That’s how powerful the next few years could be. 🔹 His thoughts on AGI (Artificial General Intelligence):    • Codeex was launched recently – Sam called it a “feel the AGI” moment.     • If you went back to 2020, today’s ChatGPT would already look like AGI.     • The definition of AGI isn’t as important as the speed at which we’re progressing.     • Sam’s version of AGI: “A system that can discover new science on its own and speeds up scientific progress 4x.” 🔹 His advice to business leaders? 💡 Companies that have highest iteration speed and fastest rate of learning will win in this rapidly changing world. Catch the full conversation betwen OpenAI CEO Sam Altman and Snowflake CEO Sridhar Ramaswamy here. https://lnkd.in/gCMZqbrM

63

12 Comments

We’re learning a lot at Snowflake, very quickly, about what it actually takes to deliver high quality, high-performance agentic analytics in the real world. Rajhans Samdani and I collaborated to write this latest post, which captures some of those learnings, especially around the emerging “context layer” and why it is becoming foundational for trustworthy data agents. https://lnkd.in/g-8TMcmD What’s been most interesting is how consistently the same themes show up across customer engagements. Whether it’s Semantic Views, Cortex Analyst, our Agent Framework, or Snowflake Intelligence, the same pattern keeps reinforcing itself. You can’t get to reliable, scalable outcomes without a strong, well-defined layer of context that connects data, business meaning, and user intent. This is one of those moments where the pace of change is hard to overstate. The space is evolving quickly, and we’re seeing ideas move from early experimentation into real customer impact in a matter of weeks. Being able to take what we’re learning directly from customers, feed that back into the platform, and then see it improve results is what makes this work so exciting right now. If you’re thinking about how to build or scale agentic analytics, I hope you’ll find this perspective useful.

337

9 Comments