COVID-19 DEATHS PREDICTION WITH ORACLE MACHINE LEARNING NOTEBOOKS | UPDATE 5


The model predicts the future deaths based on daily deaths reported by the source of information for the next 30 days from the date of calculation onwards.

Source of information: https://opendata.ecdc.europa.eu/covid19/casedistribution/csv

Algorithm: EXPONENTIAL_SMOOTHING

Prediction step: 30 days onwards

Date of calculation: 18th, Jun 2020 23:00 CEST

Prediction tool: Oracle Autonomous Database version 18c, Always Free instance created in Frankfurt datacenter on 4th Apr 2020

Disclaimer: This is not a scientific research work. It is just the output of a set of powerful tools and technologies. As it is, with no warranties. Use it as your own risk.

Note: We only predict deaths, because although it is not clear what the countries are reporting, accurate or not, deaths are countable while infection cases are more controversial because the lack of tests.

See also this post

Deaths prediction for the next 30 days

Total deaths
reported
on 18th jun
Prediction calculated
23/Apr/2020
Prediction calculated
28/Apr/2020
Prediction calculated
3/may/2020
Prediction calculated
10/may/2020
Prediction calculated
17/may/2020
Prediction calculated
18/jun/2020
WORLD450,630338,568281,737368,233399,626433,254647,278
Total deaths prediction table

When world deaths will be virtually zero?

Zero deaths predicted date as of May 17th 2020Zero deaths predicted date as of Jun 18th 2020
WORLDNot in the next 30 daysNever! Ascending ramp!!
Zero line crossing according with today’s data

World prediction graph (jun 18)

A sinusoid with the X axis sitting on a sloping ascending ramp

World prediction graph (may 17)

A sinusoid with the X axis sitting on a sloping descending ramp

Prediction on May 17th 2020

Stay safe!!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.