The SAS Data Science Blog
Advanced analytics from SAS data scientists![How natural language processing transformers can provide BERT-based sentiment classification on March Madness](https://blogs.sas.com/content/subconsciousmusings/files/2023/03/kylie-osullivan-BfaBLVCBTI8-unsplash-1-702x336.jpg)
SAS' Ali Dixon and Mary Osborne reveal why a BERT-based classifier is now part of our natural language processing capabilities of SAS Viya.
![Curious about ChatGPT: Exploring the use of AI in education](https://blogs.sas.com/content/subconsciousmusings/files/2022/06/a-data.jpg)
Editor's note: This article follows Curious about ChatGPT: Exploring the origins of generative AI and natural language processing. As ChatGPT has entered the scene, many fears and uncertainties have been expressed by those working in education at all levels. Educators worry about cheating and rightly so. ChatGPT can do everything
![Accelerating delivery with CI/CD – Navigating the journey](https://blogs.sas.com/content/subconsciousmusings/files/2023/03/carter-banner2-702x336.jpg)
SAS' Mary Carter details challenges and benefits of accelerating the delivery of SAS software.
![Curious about ChatGPT: Exploring the origins of generative AI and natural language processing](https://blogs.sas.com/content/subconsciousmusings/files/2023/02/ChatGPT-love-note-702x336.png)
How did we get to a place where a conversational chatbot can quickly create a personalized letter? Join us as we explore some of the key innovations over the past 50 years that help inform us about how to respond and what the future might hold.
![Innovative contributions to NeurIPS 2022](https://blogs.sas.com/content/subconsciousmusings/files/2023/02/january-xu-banner-702x336.jpg)
NeurIPS 2022 allowed researchers and practitioners to share progress and brainstorm new ideas for advancing machine learning and its related fields.
![Improving the detection of level shifts using the median filter](https://blogs.sas.com/content/subconsciousmusings/files/2023/01/11_The-forecast-plot-below-illustrates-that-the-level-shift-was-captured-and-the-difference-between-the-actual-onset-of-the-level-shift-and-the-predicted-onset-is-relatively-small-702x336.jpg)
Time series data is widely used in various fields, such as finance, economics, and engineering. One of the key challenges when working with time series data is detecting level shifts. A level shift occurs when the time series’ mean and/or variance changes abruptly. These shifts can significantly impact the analysis and forecasting of the time series and must be detected and handled properly.