Writing
Essays on data, decisions, and the work in between.
-
Simple vs. Stratified Sampling What's the Difference?
In research, the best data you can feed a model is the whole population. After a decade of working with data, working with the entire population is almost never the case. For most of the analyses we create, we end up working with a sample.
-
The Statistical Trick That Lets 1,000 People Represent Millions
Growing up, watching the first presidential elections after the military dictatorship in Brazil caught my attention. I watched a very young governor take the lead in the general elections
-
Central Limit Theorem
The central limit theorem (CLT) is, arguably, the most important theorem in statistics. It is, in many cases, an introductory statistics course.
-
All Models Are Wrong!
”All models are wrong, but some are useful.” Charles Box
-
What Universal Optmization Works Best? No-Free-Lunch Theorem
There are hundreds, if not thousands, of algorithms and statistical methods. When I first started in this field, the first method I tried in every single dataset was K-means. It was my go-to algorithm.
-
Unweighted and Weighted Logistic Regression Models
Even after so many years, I still remember one of my very first logistic regression projects. I was so proud of it. Until my supervisor kicked it back and told me that I had to weigh it.
-
The AI Bubble Nobody Wants to Talk About
There isn't one day when I open the news or social media that I don't come across AI news.
-
What Are Vector Embeddings?
Is vector embedding one of those buzzwords in data science? What are they and why are they important? In short, they are decoders or translators, essential for machine learning.
-
Why P-Values Don't Mean What Most People Think They Mean
Very early in my PhD program, I began working with and testing hypotheses. One of the first challenges I had to overcome was understanding the p-value.
-
What is Bias and Variance Tradeoff
You don't want the model to over- or under-fit. You have to strive to find the right balance between the two. That is the bias-variance tradeoff.
-
Why Data Science Projects Fail and How to Avoid It
Not long ago, I sat with an apartment owner who had taken over 144 units. There were 15 vacant, 12 on move-out notice, and four evictions for the end of the month. If the notices and evictions were to go through, the occupancy rate would be at 78 percent.
-
Amazon Ships Before You Order—Here's How Your Business Can Do the Same
Amazon ships products before you order them. And it's been doing it for over a decade.
-
Property Files #2: When the System Fails Everyone
I debated whether to share this story. Evictions are one of the most difficult parts of property management—and one of the least understood or perceived as corporate greed. From the outside, it looks simple: the resident doesn't pay, the landlord kicks them out. Landlord wins, residents lose.
-
The Silent Profit Killer: How Utilities Drain Multifamily NOI
As a vendor in the multifamily industry, I was constantly visiting properties, talking to managers, maintenance technicians, and occasionally, owners.
-
Property Files #1: Becoming a Manager
54% occupancy. 20% delinquency. 4 hours of training. My first property management job taught me why data matters—the hard way.
-
Pareto Analysis in Action: Optimizing Multifamily Maintenance Operations
Italian economist Vilfredo Pareto found that 20% of Italy's population received 80% of the country's income. This became known as Pareto's principle, also known as 80/20 rule.
-
Why Your Property Needs a Dashboard
The multifamily industry is heavy on reporting. None of the most common software packages provides the reports that most owners or managers require. That's why I've created Catalyzer. It is a dashboard that not only provides robust real-time reporting but also has machine learning algorithms for enhanced forecasting.
-
The Hidden Lesson of Operation Analysis
There is never a dull moment when working in the multifamily industry. Many years ago, my first job right out of college was for a property management company who managed about 1,000 doors.
-
How Can Data Help Save Cracker Barrel?
When I moved to America in the Spring of 2002, the very first sit-down restaurant I visited was Cracker Barrel. The food was fantastic. But it was the experience that was remarkable. That night, when the manager heard it was my first ti…
-
Frequentist vs Bayesian A/B Testing Thinking
Every business decision is a gamble—some just have higher stakes than others. Personally, I tend to be decisive and rarely get lost in "what ifs." Now, in business, the infinite possibilities are always screaming for attention.
-
The Last Mile Problem in Data Science Communication
The crowded conference room, filled with dark suits, looked at me blankly. Somewhere along the way, I had lost my audience. It was not until I went back a slide that I was able to pinpoint the culprit.
-
The Rise of Vibe Coding: Why is AI Changing How We Work?
I'm an lifelong learner. I love to delve into new things. I'm captivated by knowledge. That is part of the reason why I became fascinated with data. It has not always been that way. Once upon a time, I had no desire to learn anything.