These are the methods I used to analyze data about covid-19 in the Tippecanoe county from 3/19 to 10/20 for a data science hackathon, below are some information about the hackathon.
COVID-19 has impacted the social and economic activity of faculty and students at Purdue. The Protect Purdue initiative has implemented a range of measures that keeps classrooms safe. However, the risk outside of the classroom, in bars, restaurants, churches, gyms, grocery stores, etc. remains. Thus, the "social concentration" of people in places in our region creates concerns. An increase in foot traffic at public places around Purdue, in Tippecanoe County, suggest the normalization of daily routines. At the same time, it also indicates an increase risk of virus spread due to social crowding in closed buildings. Indeed, recent students published in NATURE suggest that a high concentration of people inside closed buildings nurtures the spread of the virus.
Thus, the IronHacks team in collaboration with its partners (Protect Purdue, State of Indiana, the City of Lafayette, etc.) reach out to you, aspiring data scientists, to help them monitor and predict the foot traffic at thousands of places of interest (POIs) in Tippecanoe County.
A place of interest (POI) is a public place with an address and a name where people spend time (and sometimes also money). For example, the gym YMCA Downtown in downtown Lafayette is a POI. And the restaurant Revolution Barbecue is another POI.
They ask you to predict the weekly foot traffic using historical data about social movements, social distancing, policy interventions as well COVID-19 incident data. The data are unique: they are big, they are granular, and they are real, and also allow you to consider spatial movements. With such predictions, you have the unique opportunity to help us fight the COVID-19 pandemic.
Your major task is to build a statistical model using the historical movement, COVID-19 incident and policy intervention data collected from week 11 to week 43 to predict the foot traffic in week 44 for 1804 places of interest (POIs) in Tippecanoe County. In other words, you have to predict the raw_visit_countsof visitors at those POIs (We picked week 11 as a starting date, as this was the week when the State of Indiana reported the first COVID-19 case. However, you might not need all those historical data in your modeling).
You can use a statistical model of your choice to make those predictions using a historical data that we will provide you with. Indeed, we ask you to explore a variety of models - from different kinds of regressions, time-series models, deep-learning models, network models, etc. there is no limit to your effort to experiment. Indeed, we want to see a VARIETY of models being used.
Check out https://lnkd.in/eXJaBn2