Financial fraud is a high-stakes issue in banking, where schemes are becoming increasingly sophisticated and costly. As a result, detecting anomalies quickly and accurately is a top priority. But traditional data-driven fraud detection models face challenges such as data scarcity, privacy constraints, and model bias. This is where synthetic data
I have previously written about the moment-ratio diagram as a graphical tool for modeling univariate distributions and also as a tool for examining the distribution of the skewness and kurtosis statistics for distributions. The simple moment-ratio (M-R) diagram from my book (Wicklin, 2013, Simulating Data with SAS, Chapter 16) is
How I collected birdsong detection data from BirdNET-PI and used SAS to visualize the bird visits across the seasons.
This is the first in a five-part blog post series that delves into modernizing marketing strategies through the integration of advanced marketing platforms. I had the pleasure of interviewing Shaun Memon of Munvo for this series, where we discuss a wide range of topics, from fragmented MarTech stacks, first-party data
Let’s be real: no single language rules the world anymore. It’s all about the right tool for the job. You’ve seen the lists: “Top Programming Languages of 2024.” “Python vs. Rust: The Ultimate Showdown.” “Why Java Refuses to Die.” But you rarely see SAS on these lists. And I get
Agentic AI is more than just the next step in automation. It’s a shift toward systems that don’t just respond to commands – they reason, decide and act with a blend of analytics and embedded governance. This marks an evolution in how we think about AI maturity: we are moving
Many of today’s fraudsters are figuring out how to use AI to automate and structure scams that are unique to each person they target. If fraudsters can analyze your data, learn your patterns, track your interests, and exploit who you trust – how can you combat them? According to SAS
This article shows how to classify a set of high-dimensional data into orthants. An orthant is the d-dimensional generalization of a quadrant. For 2-D Euclidean space, there are four quadrants, often labeled by Roman numerals I-IV. The quadrants are open sets that are defined by the signs of each coordinate
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.
Authors: Bahar Biller, Jagdishwar Mankala, and Jinxin Yi Managing spare parts inventory is a critical aspect of asset performance management, especially in industries where equipment downtime is costly. This post, based on a real-world project with a major aircraft manufacturer, explores how to optimize spare parts inventory under uncertainty. We
A hands-on introduction to SAS Notebooks in SAS Viya Workbench, showing how to combine code, SQL, and Markdown for a more productive and interactive coding experience.
AI is only as powerful as the data behind it. You’ve probably heard the phrase “garbage in, garbage out.” That’s always been true in analytics, but in today’s AI-driven world, the consequences of poor data are greatly amplified. Flawed models, biased predictions and opaque decision-making all trace back to one
Hosting can come with many different emotions for each of us. Often, as we plan and prepare to invite people into our homes, it can be stressful. We are tasked with preparing, shopping, cooking, and cleaning — all before anyone even rings the doorbell. If you’re anything like me, these
I’m a credit card transactor – I pay off my balance in full each month and use credit purely as a payment method to avoid interest. Recently, a major payment processor experienced an outage that disrupted many money movement services. As a result, my scheduled electronic payment was converted into
When creative minds come together to solve real-world problems using the power of analytics, great things happen. The SAS Hackathon is more than just a competition; it’s a global innovation experience that brings together coders, domain experts and big thinkers from across industries and backgrounds. What we’ve been up to
This article shows how to use SAS to implement the ISO algorithm to generate (and validate) a Universal Loan Identifier (ULI). A ULI is a long string of numbers and letters that serves as a unique identifier that is used for certain financial transactions. The ISO standard ensures that banks
Machine learning engineers are among the most sought-after professionals in the data analytics and AI space today. But behind the buzzwords and job titles lies a role that requires data literacy and a range of skills in statistics, software deployment, critical thinking and ethical judgement. If you're wondering what this
Government productivity and transparency are hot topics, with trust in public institutions declining worldwide and global public debt levels nearing 100 percent of global gross domestic product. Managing fraud, waste and abuse (FWA) is key to public sector productivity. The British Government estimates that £39.8 billion to £58.5 billion of
Has your organization invested in a customer data platform (CDP) only to find that it's not living up to its promise? You're not alone. In fact, Digiday reports that only 10% of marketers who have a CDP believe it’s fit for purpose, while an even smaller amount (1%) feel certain
Model governance has moved from "nice to have" to a "non-negotiable". As organizations deploy AI across industries like health care, banking and government, the demand for transparency, trust and accountability is louder than ever. SAS experts Briana Ullman, Product Marketing Manager and Vrushali Sawant, Data Scientist, discussed what that looks
On social media, a SAS user reported that SAS could not compute the modulo of an extremely large integer. In SAS, the modulo operation is usually performed by using the MOD function, which computes the remainder of dividing an integer, N, by another integer, d. (In symbols, the remainder is
Enforce SAS code standards using SASjs and GitHub Actions to maintain secure, readable, and maintainable code. Automated linting blocks non-compliant code from merging into protected branches.
SAS' Enhanced Support model is structured into five progressive levels, ranging from Limited Support—designed for outdated software versions—to Premium Support, which offers the highest service standards, including enhanced SLAs, 24/7 assistance, and direct access to product experts. In particular, the combination of Extended Technical Support and Premium Support has proven to be a winning strategy for many companies undergoing modernization. This approach allows continued support for legacy environments during the migration to newer versions, minimizing operational risks and ensuring service continuity.
There’s nothing like the energy of a first-time experience – especially at SAS Innovate. Whether it was the keynotes, the tech demos, the chance to connect with peers, or just soaking it all in, first-time attendees had plenty to say about what made the event stand out. We caught up with
In the last post, we explored fundamental nutritional habits to manage inflammation, insulin resistance, gut health and stress resilience which can all impact perimenopause symptoms. Now, let’s build on that foundation with advanced strategies to further tackle the effects of fluctuating and fading hormones.
A previous article discusses the Gini-Simpson diversity index and how to compute it in SAS. Suppose you have a sample that contains R classes. (Classes are also called groups or categories.) Intuitively, the sample exhibits "high diversity" if the class sizes are approximately equal. The sample shows "low diversity" if
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.
Accurately identifying lag structures between related time series is essential in public health forecasting, particularly during epidemics where delays between infections and hospitalizations affect planning. Using a simulated SEIR model and SAS Viya’s PROC TSSELECTLAG, distance correlation is shown to outperform Pearson correlation by correctly identifying nonlinear lag relationships—such as the true seven-day lag between new infections and hospital admissions.
We pay a lot of attention – and rightly so – to ways in which emerging and evolving technologies like AI might reinforce existing biases or inequities based on what data the models are trained on. But there’s a flip-side concern that doesn’t get nearly as much notice: What if,
Back when I was in banking, I always looked forward to certain annual vendor meetings and reports. These key partners provided valuable insight into what was happening beyond the four walls of our institution. Their input was essential to helping us assess our market position and refine our strategy. Some
