 Welcome to the video series, Data Science for Beginners. Data science can be intimidating, so I'll introduce the basics here without any equations or computer jargon. In this first video, we'll talk about the five questions that data science can answer. Data science uses numbers and names, which are also called categories or labels, to predict answers to questions. And it might surprise you, but there are really only five questions that data science answers. Is this A or B? Is this thing weird? How much or how many? How is this data organized? And what should I do next? Each one of these questions is answered by a separate family of machine learning methods called algorithms. It might be helpful to think about an algorithm as a recipe. You put your data as the ingredients and the algorithm tells you how to combine and mix them to get an answer. And computers are like a blender. They do most of the hard work of the algorithm for you and they do it really fast. So let's start with a question. Is this A or B? This family of algorithms is called classification. And when there's only two choices, it's two class classification. It's useful for any question that has just a couple answers. For example, will this tire fail in the next thousand miles? Yes or no? Which brings in our customers a $5 coupon or a 25% discount? This question can also be rephrased to include more than two options. Is this A or B or C or D? And this is called multi-class classification. It's useful when you have several or even several thousand possible answers. Multi-class classification will go through and choose the most likely one. The next question the data science can answer is is this weird? This question is answered by a family of algorithms called anomaly detection. If you have a credit card, you've already benefited from it. Your credit card company analyzes your purchase pattern so that they can alert you to possible fraud. Charges that are weird might be a purchase at a store where you don't normally shop or buying an unusually pricey item. This question can be useful in lots of ways. For instance, you might want to know is this pressure gauge reading normal, especially if it's in the tire of your car? You might want to know is this message from the internet typical? Anomaly detection flags unexpected or unusual events or behaviors and it can give you a clue where to look for problems. Machine learning is also used to answer the question how much or how many? Algorithms that answer these questions are called regression and they make numerical predictions such as what will the temperature be on Tuesday? What will my fourth quarter sales be? They help answer any question that asks for a number. Now the last two questions that data science can answer are a little bit different. Sometimes you just want to understand the structure of a data set and you ask how is this organized? For this question, you don't have examples that you already know the outcomes for. There are a lot of ways to tease out the structure of the data. One is called clustering and it separates the data into natural clumps for easier interpretation and with clustering, there's no one right answer. Common examples of clustering questions are which viewers like the same types of movies or which printer models fail in the same way? By understanding how data is organized you can better understand and predict behaviors and events. The last question, what should I do now? Use as a family of algorithms called reinforcement learning. Reinforcement learning was inspired by how the brains of rats and humans respond to punishment and rewards. These algorithms learn from outcomes and decide on the next action. Typically reinforcement learning is a good fit for automated systems that have to make lots of small decisions without human guidance. Questions and answers are always about what action should be taken, usually by a machine or a robot. Examples are, in a temperature control system adjust the temperature up or down or leave it where it is. In a self-driving car at a yellow light, brake or accelerate. Or with the robot vacuum cleaner, heat vacuuming or go back to the charging station. Reinforcement learning algorithms gather data as they go, learning from trial and error. So that's it, the five questions data science can answer. Be sure to check out the other four videos in the Data Science for Beginners series from Microsoft Azure Machine Learning.