Nuances of Logistic Regression - Sample Selection

In earlier sessions, you learnt how to build a logistic regression model in Python, and how to evaluate it. However, even before you start building a model, you have to decide what kind of data would be appropriate for building it.

Let's listen to Hindol on what nuances you should keep in mind while doing so:

So, to summarise, selecting the right sample is essential for solving any business problem. As discussed in the lecture, there are major errors you should be on the lookout for while selecting a sample. These include: 

1. Cyclical or seasonal fluctuations in the business that need to be taken care of while building the samples. E.g. Diwali sales, economic ups and downs, etc.

2. The sample should be representative of the population on which the model will be applied in the future.

3. For rare events samples, the sample should be balanced before it is used for modelling.

So, these were the nuances of sample selection. Are there any other nuances you need to be aware of? Yes. In the next segment, you will learn about the various nuances of segmentation.