Machine Learning Solutions

Building the baseline approach

In this section, we will be building the baseline approach. We will use the scraped dataset. The main approach we will be using is TF-IDF (Term-frequency, Inverse Document Frequency) and cosine similarity. Both of these concepts have already been described in Chapter 4, Recommendation System for e-commerce. The name of the pertinent sections are Generating features using TF-IDF and Building the cosine similarity matrix.

As this application has more textual data, we can use TF-IDF, CountVectorizers, cosine similarity, and so on. There are no ratings available for any job. Because of this, we are not using other matrix decomposition methods, such as SVD, or correlation coefficient-based methods, such as Pearsons'R correlation. ...