I'm trying to forecast Real estate Price , it's not a prédiction. But a forecast Like the Price of a an appartement in 2023 or 2024, i'm asking about how should be my dataset ? Can I use a dataset from 2018 to 2021 of 13 columns You can find the dataset here:


Date, area, kitchen_are, nb_rooms Please note that every row is a new house indépendant from others, I'm having this dataset by scrapping a website of ads announcements and my data is not related, i don't have like a history of the price of each apartment it's not like the price was 1 million euros in 2018 and become for the same apartment 1.5 million euros Can I don't multivariate time series with my dataset ? Can I use neural fb prophet ? Which algorithm can solve my problem ?


1 Answer 1


This is the typical problem where you have to really model the phenomenon. You are supposed to use a pencil and paper and actually do some choices.

One thing you can do is to create a function with an aggregated price over time depending on features. By doing so, you are able to have a "price curve" over time for each feature. And so you can actually forecast.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.