Crowdfunding platforms are an emerging and important context of micro-funding.

Case situation:
Crowdfunding platforms are an emerging and important context of micro-funding. New ventures, in general, lack financial resources to implement their ideas. Traditional venture capitals are only available to a few selected organizations, but crowdfunding platforms are readily accessible to any ventures with creative ideas and allow them to fundraise from a crowd of dispersed individuals. Kickstarter.com and Indiegogo.com are the two representative crowdfunding platforms. Assume that you are interested in understanding underlying factors that give rise to crowdfunding success and have collected data from both websites on crowdfunding results of previously launched campaigns. The datasets are Indiegogo.csv and Kickstarter.csv.
Part1: Analysis of Indiegogo Data. Consider the Indiegogo.csv file.

1. Explore variables (i.e., columns of the dataset) of the Indiegogo dataset and explain what each variable presumably represents. (This is a conceptual question that does not require coding. Visit Indiegogo.com and guess the meaning/definitions of each column of the dataset)
2. Explain which variable can be a candidate for the dependent variable and why. Explain which variables can be independent variables and which cannot. Explain the reason.
3. If you create new numeric variables using existing variables, what would they be? Explain the implications of the new variables. Write R or Python code to create the new variables.
4. Write R or Python code to create a data frame that only contains variables that you have selected and created from Q2 – Q3. Also, write code to return the first six rows of the data frame you have created. Include the result of the first six rows in your answer.
5. If you create a new numeric variable from ‘tags,’ what would it be? Explain the implications of the new variable. Write R or Python code to create the new variable.
6. If you create new numeric variables from ‘description,’ what would they be? Explain the implications of the new variables. Write R or Python code to create the new variables.
7. Write R or Python code to generate descriptive statistics of the variables that you have selected and created from Q2 – Q6. Report the results. Explain what you have found interesting.
8. Write R or Python code to graphically show the relationship between the dependent variable and one of the independent variables. Include the graph in your answer.
9. Write R or Python code to run proper models based on the variables that you have selected and created from Q2 – Q6. Report the results and interpret the meanings of the result. You can employ any statistical model.
10. Based on the result of the model from Q9, write R or Python code to predict a value of the dependent variable given arbitrary values of independent variables. Report the results.
    Part2: Analysis of Kickstarter Data. Consider the Kickstarter.csv file.
11. Explore variables (i.e., columns of the dataset) of the Kickstarter dataset and explain what each variable presumably represents. (This is a conceptual question that does not require coding. Visit Kickstarter.com and guess the meaning/definitions of each column of the dataset)
12. If you collect more data from campaign pages on Kickstarter, what other variables would you get in addition to the existing variables? Why is collecting such variables important to you?
13. How can you conceptually define crowdfunding success? Write R or Python code to create a new variable named success following your definition.
14. Explain which variable can be a candidate for the dependent variable and why. Explain which variables can be independent variables and which cannot. Explain the reason.
15. Write R or Python code to create a data frame that only contains variables that you have selected and created from Q3 – Q4. Also, write code to return the first three rows of the data frame you have created. Include the result of the first three rows in your answer.
16. If you create new numeric variables from ‘description,’ what would they be? Explain the implications of the new variables. Write R or Python code to create the new variables.
17. Write R or Python code to generate descriptive statistics of the variables that you have selected and created from Q3 – Q6. Report the results. Explain what you have found interesting.
18. If you collect more data from campaign pages on Kickstarter, what other variables would you get in addition to the existing variables? Why is collecting such variables important to you?
19. How can you conceptually define crowdfunding success? Write R or Python code to create a new variable named success following your definition.
20. Explain which variable can be a candidate for the dependent variable and why. Explain which variables can be independent variables and which cannot. Explain the reason.
21. Write R or Python code to create a data frame that only contains variables that you have selected and created from Q3 – Q4. Also, write code to return the first three rows of the data frame you have created. Include the result of the first three rows in your answer.
22. If you create new numeric variables from ‘description,’ what would they be? Explain the implications of the new variables. Write R or Python code to create the new variables.
23. Write R or Python code to generate descriptive statistics of the variables that you have selected and created from Q3 – Q6. Report the results. Explain what you have found interesting.

Sample Solution