In my first article on hyperparameter autotuning, I used a cake analogy to show how to use hyperparameter autotuning with Optuna and the sasviya.ml package in Python to improve detecting Higgs bosons in a particle accelerator. SAS Viya Workbench now supports hyperparameter autotuning in SAS code with a variety of
Authors: Shahrzad Azizzadeh, Kaustubh Khandwe, Bahar Biller, and Paul Venditti On large-scale solar farms, power loss is the silent drain on profits. Unoptimized panels chip away at efficiency, causing hidden losses that people often overlook—but those losses are never insignificant. In this post, we’ll uncover how to spot and solve these
SAS empowers modern demand planners with AI-driven tools like SAS Visual Forecasting and SAS Intelligent Planning to meet rising customer expectations through accurate, responsive, and scalable demand planning solutions.
SAS Viya now includes built-in bias mitigation in its machine learning procedures to help users develop ethical and trustworthy AI models by automatically detecting and reducing bias during training.
Let SAS handle the data prep, R take care of the modeling, and skip the environment-hopping so your team can focus on building cool stuff faster.
A practical guide to SAS Procedures in Viya 4, introducing their purpose, showcasing real-world examples, and highlighting a new downloadable cheat sheet that simplifies navigation across SAS’s advanced analytics portfolio.
A previous article discusses a "Catch-22" paradox for fitting nonlinear regression models: You can't estimate the parameters until you fit the model, but you can't fit the model until you provide an initial guess for the parameters! If your initial guess for the parameters is not good enough, the nonlinear
Hyperparameter autotuning intelligently optimizes machine learning model performance by automatically testing parameter combinations, balancing accuracy and generalizability, as demonstrated in a real-world particle physics use case.
Using SAS Viya Workbench for efficient setup and execution, this beginner-friendly guide shows how Scikit-learn pipelines can streamline machine learning workflows and prevent common errors.
A recent article describes the main features of simulation by using the Synthetic Minority Over-sampling Technique (SMOTE). SMOTE was created to oversample from a set of rare events prior to running a machine learning classification algorithm. However, at its heart, the SMOTE algorithm (Chawla et al., 2002) provides a way
Using 47 seasons of Survivor data, this analysis explores what gameplay traits correlate with winning, applying Python and SAS Viya Workbench to build predictive models. While stats like challenge wins and voting accuracy help narrow down potential winners, the findings suggest that intangible social dynamics play the most decisive role.
Generative adversarial networks (GANs) offer a promising solution by creating synthetic data that mimics real datasets, allowing developers to build models without exposing sensitive customer information.
Find out more about the importance and processes involved in model evaluation to become a more productive member of any analytical team
SAS Viya Workbench integrates seamlessly with SAS Model Manager for SAS model deployment and monitoring.
SAS' Sophia Rowland breaks down the roles of each team member in a long-term machine learning project and how they can better combine their efforts to increase efficiency and efficacy
El lavado de dinero se continúa posicionando como una de las principales problemáticas ilegales, por su asociación con actividades ilícitas y crímenes financieros. Un reporte de Global Financial Integraty, titulado “Crímenes Financieros en América Latina y el Caribe: entendiendo los desafíos de los países y diseñando respuestas técnicas efectivas”, estimó
What sets the SAS Model Card apart from previous model cards is the use of descriptive visuals, to make model cards accessible to all personas involved in the analytics process, including data scientists, data engineers, MLOPs engineers, managers, executives, risk managers, business analytics, end-users, and any other stakeholder with access to the SAS Viya environment.
Learn how an intern integrated SAS Viya® and open-source code (Python) into a Machine Learning project to combine their strengths within the context of predictive modeling, and to show off the variety of ways this integration can be accomplished.
SAS Decision Builder is a decision intelligence solution, which means that it uses machine learning and automation to augment human decision-making for better and faster insights that drive tactical and strategic business decisions. It’s a cousin to business intelligence and the next step after data engineering and model training, completing the analytics lifecycle to help achieve business goals.
The new SAS Certified Specialist: Statistics for Machine Learning credential is designed to help you showcase your expertise and commitment to staying ahead in the industry.
Cada vez mais as ferramentas de IA apoiam a tomada de decisão e ajudam na criação modelos que identificam tendências e padrões de comportamentos que, juntamente com regras de negócios, permitem que as empresas tomem decisões mais assertivas, seja qual for sua área de atuação. As análises mais avançadas incluem
Mudança cultural interna precisa ser conduzida pela alta gestão e orientada pela criação de um governo mais ágil A adoção de IA e analytics pelo setor público tem evoluído significativamente a forma como o governo opera e toma decisões. Esta transição não apenas melhora a eficiência das operações nos bastidores,
Developing an accurate understanding of statistics will help you build robust machine learning models that are optimized for a given business problem. SAS launched a new course that provides a comprehensive overview of the fundamentals of statistics that you'll need to start your data science journey. This course is also a prerequisite to many courses in the SAS data science curriculum.
No mundo hiperconectado em que vivemos, os consumidores podem ter múltiplas jornadas de compras, com interações por sites, aplicativos, redes sociais ou até mesmo por uma ligação telefônica. Apesar das muitas opções de canais de contato disponíveis, o mais relevante para o cliente é a qualidade e o nível de
Crear mejores experiencias para los consumidores, llevarlas a nuevos niveles y conectar estrechamente con ellos son las principales premisas sobre las que se fundamenta la hiperpersonalización, un término que hoy domina las sesiones de trabajo de las áreas de marketing. Su objetivo principal es combinar datos sobre el comportamiento histórico
Hi! I’m Daniel, a technical intern at SAS and a student at North Carolina State University. Reinforcement learning is an exciting strategy that is versatile and broadly useful in the fields of data science and machine learning. I implemented an intelligent Minesweeper-playing model using SAS reinforcement learning, and this article
Hoy existen miles de proveedores de plataformas de datos para formular estrategias y campañas de marketing basadas en datos. No obstante, las cookies son cada vez más evitadas por aquellos consumidores que desean proteger sus datos en busca de su privacidad. Tanto Firefox como Safari han bloqueado las cookies de
SAS' Brandon Reese the EURO Meets NeurIPS 2022 Vehicle Routing Competition, which combined efforts of operations research and machine learning experts.
SAS Hackathon team, Data Hack Freaks, created an artificial intelligence (AI) and machine learning (ML) based dynamic pricing approach that allows insurance providers to adjust pricing based on the changing nature of the risk behavior of their customers. This solution has three major components: The loss ratio score, telematics score
IDC 마켓스케이프 보고서에서 MLOps 플랫폼 부문 리더 제품으로 선정된 ‘SAS Model Manager’, DataRobot, Databricks, Dataiku, Domino Data Lab등에 성능 우위 입증 다양한 비즈니스 영역에서 머신러닝의 적용이 점차 활기를 띄며 증가하고 있는 가운데, 많은 IT 리더들은 인공지능과 머신러닝 기술을 선택하고 구현하기 위한 필수 기술로 ‘모델 옵스(이하 ModelOps)’를 지목하고 있습니다. AI타임즈에 따르면,
