Authors: Steven Harenberg and Amy Becker The total solar eclipse taking place across a thin band of the United States on April 8, 2024, is going to be a stellar event. In this post, we will help plan a journey to see the total solar eclipse. We will use algorithms available in the NETWORK procedure and action set in SAS Viya to solve various path problems over the United States road network. A total eclipse is a truly rare and special event, occurring only about once every 18 months somewhere in the world. Each occurrence produces a narrow viewing path, and this year, the path of totality span ..read more

Overview In this blog post, we will be looking at how to leverage Large Language Models (LLM) through SAS Viya. Though LLMs are powerful, evaluating their responses is usually a manual process. Thus, they are sometimes prone to misinterpretation and can present information that is incorrect and potentially nonsensical. One strategy that is often employed to ensure better responses from an LLM is prompt engineering, which is the idea that crafting and structuring the initial input, or prompt, can be done deliberately to retrieve better quality responses. While there are many such strategies to ..read more

Authors: Varun Valsaraj and Julia Moreno In 2023, the Applied AI Modelling (AAIM) team established a reusable LLM-SAS Integration framework for a digital assistant. It uses natural or conversational language input interpreted by a Large Language Model (LLM) to carry out tasks and scenario analysis from SAS Optimization on SAS Viya. In this post, we will demonstrate how we built a digital assistant for a warehouse space optimization use case. By using the LLM-SAS Integration framework, we enabled both technical and non-technical users to interact with an optimization model and view the output b ..read more

Regarding natural language processing and text analytics, we can accomplish tasks quickly, rigorously, and without fuss by using SAS Visual Text Analytics. It offers out-of-the-box options like topic modeling, sentiment analysis, and linguistic rules-based approaches. Likewise, many data science goals can be achieved by using any programmatic or interface-based models available in SAS® Viya®. This post will review a popular manufacturing optimization use case that can be solved by using a SAS Optimization model. Using natural language conversation, we will demonstrate how we can use generative ..read more

The National Institute of Standards and Technology (NIST) has released a set of standards and best practices within their AI Risk Management Framework for building responsible AI systems. NIST sits under the U.S. Department of Commerce and their mission is to promote innovation and industrial competitiveness. NIST offers a portfolio of measurements, standards, and legal metrology to provide recommendations that ensure traceability, enable quality assurance, and harmonize documentary standards and regulatory practices. While these standards are not mandatory or compulsory, they are designed to ..read more

Can we use Computer Vision (CV) to recognize the identity of over 500 Galapagos sea turtles by using just an image? This was the question asked of SAS by researchers at the University of North Carolina at Chapel Hill’s (UNC) Center for Galapagos Studies. Literature suggests that it should be possible because sea turtles have a unique set of facial scales, like a human fingerprint. Therefore, no two turtles share the exact same scale pattern. In partnership with UNC, the SAS Data Ethics Practice decided to find out. This Data for Good project offered the opportunity to explore and analyze vast ..read more

In a previous post, we explored the intricacies of panel data regression. We unveiled a range of panel models and demonstrated their application in estimating cigarette demand by using the CPANEL procedure. However, achieving reliable insights in the realm of panel data regression requires addressing practical challenges. These would include such things as the potential heteroscedasticity and serial correlation among observations within the same panel unit. In this post, we will continue to use the cigarette demand example. We will delve into the critical task of generating robust standard err ..read more

Panel data are commonly used in today’s economics research. Panel data regression stands out as a powerful tool that aids in unraveling trends and patterns that evolve over time. This tool is particularly valuable when considering hidden factors in the investigations of cause-and-effect relationships. In this post, you will be given a simple introduction to panel data regression which will showcase the user-friendly CPANEL procedure available in SAS Econometrics. This procedure will be used to explore the intricate dynamics of cigarette demand. Panel Data Regression Panel data, also called lon ..read more

This post will demonstrate how the %FiniteHMM macro can automatically preprocess input data and postprocess output tables for finite Hidden Markov Models (HMMs) by using PROC HMM. First, you will be introduced to finite HMMs models and PROC HMM. Next, a brief description will be given of the %FiniteHMM macro. Finally, a couple of examples will presented on how to use the macro. Introducing Finite HMM with PROC HMM The HMM procedure supports HMMs which have been widely applied in economics, finance, science, and engineering. A finite HMM is one type supported by PROC HMM. In theory, a finite HM ..read more

In his book, “The Unicorn Project,” Gene Kim presents five ideals that teams can use when embarking on their DevOps transformational journey. This post will explore the first ideal of “Locality and Simplicity.” We will examine it analytically to help understand why Kim suggests it as a good ideal to follow. The basis of this analysis will be through the lens of causation, rather than correlation. It will follow the principles outlined in a paper co-authored by Craig Statham and Stephen Walters (Field CTO at GitLab). By using graph theory for analysis, our paper “Value Stream Reference Architec ..read more