L1 and L2 regularization in LASSO, Ridge & ElasticNet regression — You are not alone if you had a hard time understanding what exactly Regularization is and how it works. Regularization can be a very confusing term and I’m attempting to clear up some of that in this article. In this article I’ll do three things: (a) define the problem that…

Intuition and use cases of Gaussian, Binomial and Poisson distribution — As a data scientist if you are asked to find the average income of customers, how’d you do that? Having ALL customer data is of course “good to have”, but in reality, it never exists nor feasible to collect. Instead, you get a small sample, take measurements on it and…

From simple intuition to complex model building process — Logistic regression is amongst the most popular algorithms used to solve classification problems in machine learning. It uses a logistic function to model how different input variables impact the probability of binary outcomes. The technique is quite convoluted as described in the available literature. …

Methods, functions and use cases of Python lists — After writing a few pieces on topics like econometrics, logistic regression and regularization — I’m back to the basics! Many sophisticated data science algorithms are built with simple building blocks. How quickly you will level up your skills largely depends on how strong is your foundation. In the next few…

A checklist of 11 feature selection techniques — Imagine that you have a dataset containing 25 columns and 10,000 rows. After some feature engineering, finally you got 45 columns. Out of those 45 features, how many do you get to keep? Too many features increase model complexity and overfitting, and too few features underfit the model. …

Techniques and algorithms to fight back financial fraud — Financial fraud is an “art” and crime of deceiving and scamming people in their (financial) transactions. Committing fraud is criminal behavior, but it’s also an art — the lengths fraudsters are willing to go require a lot of creativity. If you’ve watched the movie Catch Me If You Can, you…

Find your niche, teach what you learn, network with your community — Data science is like the shiny new object in town that people are easily attracted to. But soon after you are into the journey, it can feel overwhelming, exhausting and sometimes you feel clueless, not knowing which direction to go. The more you learn algorithms, programming fundamentals, and the libraries…

A synthesis of iterative processes in data science projects — To someone new to the field of data science, someone who’s taking an online course, or enrolled in a bootcamp, the following scenario may sound familiar. First, you learn an algorithm along with the theories and mathematics behind it. Then you are given a take-home case study for practice, such…

How decision trees split data for class and numeric predictions — Humans make binary decisions, all the time, with “if..then..else..” structure of decision-making process. If it rains, bring an umbrella; if it can fly, it’s a bird; if the bird sounds quack, it’s a duck; if an animal has four legs….well we need more information, there’re many four-legged animals out there. …