Introducing the problem statement
In this chapter, we will build an engine that can recommend jobs to any user. This is the simplest goal we want to achieve. How we are going to build it? In order to answer this question, let me give you an idea about what kind of approaches we will take in order to build a job recommendation system.
For our baseline approach, we will scrape resumes of dummy users and try to build a job recommendation engine based on the scraped dataset. The reason we are scraping the dataset is that, most of the time, there will not be any dataset available for many data science applications. Suppose you are in a position where you have not found any dataset. What you will do then? I want to provide a solution for these kinds of scenarios. So, you will learn how to scrape the data and build the baseline solution.
In the revised approach, we will be using a dataset hosted by Kaggle. Using the content-based approach, we will be building a job recommendation engine. For the...
