程序代写代做 html BAN210- Final Assessment

BAN210- Final Assessment
Winter 2020

In this assessment, you will be implementing and documenting a Predictive Analytics model for predicting interesting and useful information about COVID-19. You will show your understanding of the predictive methods, their strength and their limitations. This is NOT a group work.

Deliverables
• A summary report (3 pages) *** MOST IMPORTANT ****
• A detailed report
• SAS Enterprise Miner files

Instructions
• Visit Kaggle Datasets and search for “COVID-19” or “Coronavirus”:
https://www.kaggle.com/datasets
For example:
• https://www.kaggle.com/anjanatiha/corona-virus-time-series-dataset
• https://www.kaggle.com/sudalairajkumar/novel-corona-virus-2019-dataset
• https://www.kaggle.com/kimjihoo/coronavirusdataset
You could also use any other sources for relevant data, e.g.:
• https://www.canada.ca/en/public-health/services/diseases/2019-novel-coronavirus-infection/health-professionals/epidemiological-summary-covid-19-cases.html

• Choose one or more datasets to work with, and specify them in your report. Explore the data to find interesting patterns.

• Based on your findings in step 2, propose a Predictive Analytics problem that could be solved with above data. See tasks in COVID-19 Challenge for some ideas:
COVID-19 Open Research Dataset Challenge (CORD-19)
(These are just ideas. Your task does not need to be complex, but needs to be a PA problem.)
• Throughout the course, you learned many methods of prediction and implemented them in SAS Enterprise Miner. Choose two methods for prediction. In your report, specify the methods and the reason you chose them.

• Implement the methods in SAS Enterprise Miner. Report the learned models and evaluation results.

• This is your final assessment. Please apply and show the concepts you have learned in this course by applying to this problem. Explain your design decisions.

Summary report
Include in your summary report (maximum 3 pages), the following subsections:
• Dataset source(s)
• PA Application:
• What’s predicted:
• What’s done about it:
• Features used in prediction (inputs, or independent variables)
• Methods for prediction, including SAS Enterprise Miner diagrams
• How you avoided overlearning
• Evaluation results