Can someone help me get this started with the understanding of what type of data to use, how to cleanse data, and how to create an exponential forecasting model?

First identified in Wuhan, China, in December 2019, COVID-19 has since become a pandemic wreaking havoc around the globe. The outbreak has become one of the most serious disruptions that have occurred during the last ten decades and has resulted in substantial loss of lives and financial losses across all sectors of the global economy.

The case is a work in process as it is under development and not a finished product that has been analyzed and vetted before deployment. As such we expect imperfections in the case study and are not expecting perfection from our students. Our plan is to incorporate some of the analysis done by students to make this a better product for the next offering of the course.

The purpose of this comprehensive case is to collect data on Covid-19 cases and deaths from Italy, New Zealand, South Korea, and the United States cleanse the collected data, use visual and descriptive analytics to summarize the collected data to draw some preliminary conclusions, use a forecasting technique to forecast the number of daily cases cumulative cases and deaths, determine an error metric for the daily cases, cumulative cases and the number of deaths and use these to summarize the findings for each country. Popular media has been reporting that the early measures adopted by New Zealand and South Korea helped keep the number of cases and fatalities low while delays in testing and mitigation efforts in Italy and the US are partly responsible for a large number of cases and deaths.

Steps:

Collect data on the number of Covid-19 related cases and deaths for Italy, New Zealand, South Korea, and the United States from the start of the outbreak to April 25^th, 2020. The COVID-19 dashboard maintained by the coronavirus resource center at Johns Hopkins University and Medicine is considered to be a trusted source. A 17-year-old student from Washington State launched a homemade website to track the movement of coronavirus and is available at ncov2019.live

You can also search Google using search criteria such as COVID-19 CASES IN USA. Cleanse collected data, if needed, and apply visual and descriptive analytics to summarize the data for each country. Use this to draw any initial conclusion. Use an appropriate forecasting model to forecast the daily cases, cumulative cases, and the number of deaths for each country and determine the Mean Absolute Deviation (MAD) for the daily case, cumulative cases, and the number of deaths for each country. Hint: an exponential forecast model will be an appropriate model. The Gompertz Curve is an example of an exponential model and you will have to research how to use the model.