After training a real-time financial fraud detection model, the next step is to evaluate its performance. This post provides an overview of the most common evaluation metrics and considerations for fraud detection models, including confusion matrix, precision, recall, F1-score, AUC-ROC, AUC-PR, and more.| César Soto Valero
Financial transaction fraud is a pervasive problem costing institutions and customers billions annually. This survey reviews the current state-of-the-art in real-time transaction fraud detection, spanning both academic research and industry adopted solutions.| César Soto Valero
Generative AI has taken the world by storm, offering endless opportunities for innovation. But as with any new technology, there are plenty of pitfalls to avoid. In this post, I dive into the current state of AI startups, shedding light on what works, what doesn't, and why. If you're looking to build something with AI, let’s step back and reflect on where it makes sense to innovate and where it doesn't. From avoiding overhyped general-purpose chatbots to understanding the limitations of AI ...| César Soto Valero
GenAI systems are becoming more and more capable of performing complex cognitive tasks that were once thought to be uniquely human. In particular, LLMs are proven to be very good at writing code. With all the buzz around GenAI replacing software engineers, are our jobs really at risk? In this article, I dive deep into AI's current capabilities and how they stack up against the demands of real-world software development. I discuss the actual potential of GenAI to assist in common development a...| César Soto Valero
Arguably, computers and faster communication systems have changed the world more than any other technology. Yet there have been many scientific failures along the way, some prominent, many minor, and a widening gap between aspirations and reality. This article discusses the problem of pseudoscience in computer science. I discuss Richard Feynman's coined term "cargo cult science," as he said: "Everywhere I see computer scientists that look like they are working on the right thing, but the thin...| César Soto Valero
A few days ago, I had a conversation about my ambitions for the future. At one point, I mentioned that I would like to achieve something remarkable and gain public recognition for it. In retrospect, my answer was quite pretentious. After reflecting deeply on this topic, I realized that what truly drives me is the desire to help and inspire others so they can achieve great things. This blog post lists all the thoughts that crossed my mind as I came to this conclusion.| César Soto Valero
The "last paper myth" emerges once academic supervisors realize that a student is about to earn their PhD and leave. It's one last stronghold for supervisors to capitalize on the time and effort they have invested in their students' scientific training. This relentless push not only detracts from the true purpose of academic research but also imposes significant personal and mental strain on the most successful students. This article explores the expectations versus reality at the end of the ...| César Soto Valero
Have you ever wonder which is most relevant technical skill in your career? It’s not necessarily a programming language or the latest framework. For me, it is Exploratory Data Analysis (EDA). Why? Because being able to manipulate and find relevant information from various data sources has opened me doors to new opportunities in both academia and industry. This post is about my journey, the lessons learned, and the resources I have used to enhance my EDA skills over time.| César Soto Valero
I’ve started writing more Python code lately (because of… AI, you know). In this post, I share the tools, libraries, configs, and other integrations I use for building production-grade Python applications following a frontend-backend architecture.| César Soto Valero