9 THOUSAND INFECTION AND SIGNIFICANT SLOWDOWN AROUND APRIL 15th. FORECAST OF CORONAVIRUS PANDEMIA IN POLAND – EXMETRIX MODEL. March 24, 2020 – Posted in: analyses, carousel, lifestyle, Our forecast, posts, Uncategorized
The model developed by the ExMetrix company dealing with economic and social forecasting shows that the number of people infected in Poland can reach about 9,000 and should be reached around April 20th, 2020. The model therefore suggests that the duration of the epidemic in Poland will be slightly longer than in China. It will probably be around 48 days from the first recorded case to the maximum of infections, in China it was about 40 days. The fastest increase in the number of infected people can be around 400 per day and will occur from 28/03/2020 to 08/04/2020 (between the 25th and 35th day of the epidemic) After April 8th, the number of cases should increase at a slower pace, and very clear inhibition should be seen around April 15th.
How the forecasting model was created
“In the prepared forecas we included a wide spectrum of factors influencing the development of the COVID-19 epidemic. Our forecasting model, in addition to data describing the course of the epidemic itself, also uses information about the health condition of the society, the state of medical care, meteorological conditions and the discipline of the society in the face of an extraordinary situation, “says Zbigniew Łukoś, CEO of ExMetrix. “Our models predict a milder epidemic than western and southern Europe. For this to happen, a social effort is needed to comply with the introduced restrictions and limitations, especially because the ExMetrix models forecast that we are entering a key phase of the epidemic. ”
Building the epidemic model in Poland, we analyzed spread of virus in countries where COVID- 19 developed earlier than in Poland, i.e. in China, South Korea, Japan, some European countries and the United States.
The following information areas have been taken into account in the construction of the virus epidemic model:
- Current state of pandemy in many countries.
- Meteorological factors.
- State of health care in a given country.
- State of health and condition of the society, with particular emphasis on risk factors such as oncological, cardiological diseases, diabetes and obesity.
- Demographic structure of society. We especially paid attention to the percentage of elderly people.
- Level of restrictions applied by the authorities and compliance by citizens.
The model was built using artificial intelligence technology (including but not limited to proprietary neural networks and simulated annealing methods). This technology allowed to estimate the impact of information from areas listed above on such parameters of the infection rate curve as:
– slope – reflecting the increase in the number of infected at a given time
– spread – allowing to determine the maximum ceiling for the number of cases and the duration of the epidemic
Assumptions, risk of verifiability:
When building the model, we assumed that statistics in COVID-19 affected countries have not been suppressed or artificially modified.
Source of data on the number of infections:
Johns Hopkins University
Data sources describing particular areas included in the model:
As the situation develops and new data flows, especially from countries where the epidemic started earlier than in Poland, we will update the model and will take into account any additional information to make it as precise as possible.
ExMetrix is a company creating a new generation of software for statistical data analysis and forecasting. ExMetrix is a data analysis system using the latest statistical and numerical models based on Machine Learning and Artificial Intelligence. ExMetrix gives access to ready made predictive models and allows to create own models based on 80 million data streams available in the system or any of data sets provided. Dozens of organizations of various sizes use ExMetrix, including Azoty Group. The software is also used to educate students at top Polish Universities – UEK and UMCS.
Ryszard Łukoś, Chief Analyst at