Introducing the random forest algorithm
The method discussed in this section is based on the concept of ensemble learning, where multiple models (in our case, classifiers) are generated and combined to solve a particular problem. You can think of ensemble learning as having diverse people who bring different perspectives to the table for a decision. Ultimately, you want to harness those different perspectives and ensure a joint decision is reached.
A real-world example should shed some light on this type of learning. Suppose that you visit a city for the first time. After an exhausting day, there is finally some free time for dinner. One possible strategy in front of many dining choices is to walk around the city to find a good restaurant, a bistro, or a takeaway. Wandering around, the aim is to make the best possible choice for dinner based on several criteria (as in features), such as the quality of service, the ambience, and menu prices. Essentially, your brain runs a classification...
