Dataset Airbnb Links to an external site. is a company that provides an online

Dataset
Airbnb
Links to an external site.
is a company that provides an online marketplace for short-term rentals of homes and apartments. Much of the data from Airbnb’s website has been compiled and made publicly available on the website Inside Airbnb
Links to an external site.
. For this assignment, you will analyze a sample of the Airbnb listings from Washington, DC, scraped in July 2023. Each row in this dataset represents a single Airbnb listing. You can download the data dictionary here: Data Dictionary.xlsx
Download Data Dictionary.xlsx
.
Goal
Your assignment is to build a predictive model of the price of the listings included in this dataset, AirbnbListings.csv
Download AirbnbListings.csv
, deliver a report, and upload all project files as described below. In your report, be sure to support your responses. Please make sure I can transfer the codes to R, this is a team effort so I would need to be able to share my codes and make sure they open please. Please do the code first and send, before report. I need the codes in 24 hours please.
Key Requirements and Questions
Preprocess the data and prepare it for the running neural network. (30 points)
Train two different neural network models using the ‘neuralnet’ package and the ‘caret’ package (based on the ‘nnet’ method or another neural network package that caret supports). (30 points)
Compare the results of these models by their model evaluation metrics (RMSE, R-squared, and MAE). Which one is a better model, and why? (Hint: caret package has a function that calculates these three regression measures.) (15 points)
You previously ran two different regression models on the price of the listing (on the same dataset) as part of your Programming I final project. Revisit your findings and comment on the difference between your new models compared to what you ran before. Are the results comparable? What are the shortcomings and the advantages of each approach? Which approach or model is more reliable for prediction? Explain. (15)
Important notes:
Neural networks are extremely sensitive to the scale of the variables. Make sure all the variables, even the predictor, are scaled. The most common scaling for neural nets is min-max normalization.
The evaluation metrics of the test data should be calculated based on the actual scale of the target variable. So if predicted values are in a range of 0 to 1, they should be scaled back to the original scale before calculating predictive measures.
Your report should include plots of actual prices versus predicted prices for both of the two trained models.
The instructor and the TAs may not answer debugging questions regarding other neural network packages that are not discussed in class.
Deliverables
A written report answering the questions and explaining your findings (submitted as a PDF document). This report should clearly define the problem statement, data processing steps, your approach and any assumptions you make, the results of analyses you have performed, and the insights you have gained by performing these analyses. In writing it, imagine that you are a consultant submitting the report to your client. This report should not be more than 3 pages long (excluding the cover page or table of contents). If needed, you can have up to 2 pages of an appendix with supporting exhibits. Include your names on top of the first page, or add a cover page with the names.
Your fully-functional and annotated R code(s) with proper name(s). In your R file(s), highlight the different steps/questions by including annotations or section titles. Also, make sure your submitted code can be executed (with no errors) by just reading the AirbnbListings.csv file.
Rubric:
Your project will be graded based on:
Timeliness:
Submitting the complete assignment on or before the deadline. (faculty may not accept late submissions or penalize them in other ways.)
Analysis and Recommendations:
Clearly stating the scope and objectives.
Answering all study questions clearly and completely.
Demonstrating appropriate use of concepts and techniques and properly following machine learning training and testing steps.
Depth of the analysis.
Clarity and quality of the findings and recommendations.
To summarize:
Correctness of your approach, your code, answering the questions, and following the steps. (90 points)
Format of the report and your R code. (10 points)