Mid-term Individual Project BUDT758D Spring 2024 Visualizing Fannie Mae Mortgage Data Fannie Mae is one of the largest purchasers of home mortgages from banks and sellers of mortgage-backed securities (a financial instruments created by bundling and selling mortgages to investors) on the secondary market in the United States. In exchange for a fee, Fannie Mae guarantees the payments of principal and interest on the book of loans it sells. As Fannie Mae bears the losses in the event of borrower defaults on a mortgage, its future profitability is significantly influenced by borrower default rates.In September 2008, at the peak of the financial crises, Fannie Mae was piling up significant losses. A wave of mortgage defaults posed a severe threat to Fannie Mae and, consequently, the entire U.S. financial system. To save the system, the U.S. government stepped in and placed Fannie Mae under conservatorship, a form of bankruptcy overseen by the Federal Housing Finance Agency (FHFA). This move transformed Fannie Mae from a government-sponsored entity to a government-owned entity. From 2008 to 2011, the U.S. Treasury injected 13 billion, and held the largest market share, accounting for 40% of the issuance of single-family mortgage-backed securities (MBS).“To promote better understanding of the credit performance and acquisition of Fannie Mae mortgage loans,” Fannie Mae released each quarter updates to its data related to mortgages, such as the prepayment of MBS and loan performance data (the primary focus of this assignment). On October 27, 2023, Fannie Mae updated its loan performance data through Q2 2023. This data includes a subset of 16 million mortgages, all with terms of 30 years or less. These mortgages are fully amortizing, full documentation, single-family, conventional fixed- rate loans, generally considered the lowest rick in Fannie Mae’s portfolio. The loans within this dataset were acquired between January 1, 2000, and June 30, 2023.Analyzing this dataset represented a significant challenge, even for sophisticated investors who owned Fannie Mae stock. How could such investors use this data to understand default rates within Fannie Mae’s single- family guaranty book of business? Which fields in the data were drivers of loan defaults and individual interest rates? How can we visually analyze Fannie Mae’s loan performance?In this assignment, we will work with a smaller subset of the data obtained fromFannie Mae’s data portal (please note that registration is required to access the original data directly). To access the statistical summary of the entire data set, you can find the “FNMA_SF_Loan_Performance_Stat_Summary_Primary.pdf” file on ELMS. For a comprehensive list of fields contained in the original data, refer to the “crt-file-layout-and- glossary.pdf” file on ELMS (the fields used for this assignment are listed at the end of this document). For further details about the data, you can visit theFannie Mae Single-Fam代 写BUDT758D Spring 2024 Mid-term Individual Project ily Loan Performance Datawebpage. Additionally, apart from loan performance data, Fannie Mae also provides data on Mortgage-Backed Securities (MBS), Single-Family Connecticut Avenue Securities (CAS), and Single-Family Credit Insurance Risk Transfer (CIRT) on their data portal.Assignment Guidelines Assignment Name: Mid-term Individual Project Points: 150 Submission Type: ELMS and Tableau Public Submission Date: March 17, 2024 at 11:59pm Data For this assignment, you will have access to the following three datasets. You have the option to use either two or all three of them in the assignment. The first two datasets are small samples randomly drawn from the data for specific periods, representing approximately 17% and 12% of the entire data for Q4 2007 and Q4 2019, respectively. You can refer to Exhibit 1 and 2 for a detailed list of the fields included in each dataset.• “2007Q4.rds” contains information on 50,000 fixed-rate single-family amortizing loans with terms of 30 years or less. These loans were either owned or guaranteed by Fannie Mae during the fourth quarter of 2007,a period marked by a significant increase in loan defaults at Fannie Mae.• “2019Q4.rds” includes information on 50,000 Fannie Mae loans of the same type as the previous data file, but specific to the fourth quarter of 2019 – the last quarter before the onset of COVID.• “default_rate_ts.csv” Provides a time series of quarterly default rates for the same types of loans as in the previous two datasets. The default rate is calculated by dividing the number of loans that defaulted during the quarter by the total number of loans in the dataset for that quarter. The entire dataset provided by Fannie Mae was used, as opposed to just samples as in the previous two datasets.If you intend to incorporate supplementary data, you are only allowed to use those available on Fannie Mae’s data portal. Assignment Overview Write a report summarizing your findings from visualizing the provided data. Identify a cohesive focus for your report that interests you. For instance, you can explore topics such as: How has the default rate of loans acquired by Fannie Mae evolved over time? What factors drove loan defaults in 2007, and are they similar to those in 2019? Are the characteristics of borrowers and houses for Fannie Mae-acquired loans the same in 2007 and 2019? These are just examples to spark ideas, and you're welcome to explore other topics of interest. Keep in mind your audience—choose a topic that tells an engaging story and is suitable for discussion in a professional context.As part of the assignment, you are also required to generate an interactive chart. Please refer to the detailed instructions provided below.Instructions Report and Charts (135) The report should include a title, the main body of the report, and 4-6 visualizations to support your analysis. Use the R markdown file “Midterm-Report-Template.Rmd” available on ELMS to create your report.The report's title should accurately represent the chosen topic. The main body of the report should comprise an introductory paragraph explaining the problem's significance for business decision-making, several paragraphs detailing findings from the visualizations, and a concluding paragraph summarizing your analysis and providing managerial WX：codehelp
