When a ML model is created, its prediction on the testing set can do surprisingly well, but once it hits real world data it does poorly. In data science, it is said that the model is overfitting. …

The Tableau Certified Data Analyst exam is a 30 multiple choice, 15 question hands on exam with a time limit of 120 minutes that can be taken on site or at home on one’s computer. One needs a 75% or higher to pass and the fee for the test is…

Still being new to recommendation engines, I started this project out of my comfort zone hoping to learn by doing and making mistakes. Although I learned about recommendation systems in my Data Science Bootcamp, I never really practiced it — until now. Though somewhat rusty in my mind, I devised…

Introduction — In Reinforcement Learning (RL) there are two important function types that dictate an agent’s action in its environment. The agent’s action can be controlled using a policy function or a value function. A policy-based RL system uses state/action probabilities to map out its actions on the environment whereas a reward-based…

Deep Reinforcement Learning (RL) can be broken down into two parts. The “deep” refers to the use of neural networks in its purpose while reinforcement learning (RL) is described to be the use of rewards to reinforce a behavior. It is an active branch of AI with new developments every…

In time series data, we make predictions on future data up to a specified time, on past or current data. Time series analysis is unique in that it only uses datetime and a quantitative dependent variable to make predictions on the future. For example, stock prices, CO2 concentrations in the…

The Support Vector Machine (SVM) model in the cases I use it, almost always produces good results. IT IS AN EXCELLENT CLASSIFICATION MODEL. The algorithm logic is sound, fairly easy to implement, has few important parameters to tune, and in its linear model, has coefficients for model explainability. …

Data visualizations for exploratory data analysis is one of the most crucial steps in the data science process. It occurs after we clean our data but before we conduct machine learning. This vital step allows us to see insight into our data by extracting relationships and patterns that only visualizations…

As a data analyst/scientist that reports to stakeholders recommendations using data, the ability to tell a story using that data is crucial to job function. Even though deploying models and predicting data is important to our jobs, a major part of data analytics is to be able to tell a…