TransWikia.com

Architecture for sequential data

Data Science Asked on June 3, 2021

I am seeking advice on a solution I am building as a part of my data science course.
I have to build a web application that solves a problem created by COVID-19.

My idea – For the first stage of my project development, I decided to build a solution that tracks hospital resource utilization by state(USA) as an effect of rising COVID cases and gives a warning beforehand in case COVID cases are rising and not enough resources are available.

Datasets – The data i am considering for this project are:

  1. USA Hospital Beds – https://aws.amazon.com/marketplace/pp/prodview-yivxd2owkloha?qid=1599355365023&sr=0-13&ref_=srh_res_product_title
  2. A COVID time-series data(There are many).
  3. Dataset giving population vulnerability and other similar datasets.

I am not very experienced in working with sequential data, to be honest this is my first one. I am confused about which kind of architecture will be appropriate to approach a problem like this.

First i considered time series analysis. but, according to my current understanding time series just looks at trends and seasonality in the data. My problem is much of a cause and effect problem so now I am leaning towards RNN/LSTM/Attention.

Can you validate my choices or provide a suggestion on better alternatives?

Add your own answers!

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP