# Answer in the next quiz is wrong? If right then explain how?

In the quiz next to this lesson a question is asked that which among the following is considered data science but not machine learning? The correct answer marked was sales forecasting which I guess is not correct at all. In the process of forecasting sales we are required to perform various algorithms, formulas and analysis of past data which is done with the help of ML. So hence Sales forecasting is considered within Machine Learning.

I had the same concern about this question.

The instructor does provide a kind of a disclaimer that these classifications are not 100%. So, I would not be using these in the real-world/interviews. This is the instructor/365datascience's view.

ML has the least to do with creating Dashboards as they are mere UI for the ML (processed) data.

Having said that, the best explanation I can think of for sales forecasting not being ML is that it is independent of the ML process. We can have the complete ML process without Sales Forecasting. Regression will only provide analysis insights, so past. Forecasting is future/analytics. To sum up, Sales Forecasting can be seen as an application of ML.

Even the term Sales Forecasting is more of a business term, technically we would refer it to Time Series Forecasting.

I am not sure, if I am right.

I think you're right we can't do sales forecasting without machine learning

I think the answer to question number 1 and the classification represented in the slides should be revised. Sales forecasting can be done with regression, which is part of the ML algorithm. Actually, forecasting is one of the applications of ML.

Thank you so much for these answers and perspectives. As a novice there have instances where I have selected "the incorrect answer" to later see that my reasoning was not wrong. Frankly, I was being put off as I was beginning to think this course is not for me but as a prior commentator pointed out, "The instructor does provide a kind of a disclaimer that these classifications are not 100%. So, I would not be using these in the real-world/interviews. This is the instructor/365datascience's view." Thanks for reiterating this point! Onwards and upwards :)