Montgomery bank & trust ailey ga

Decision Tree

Build a decision tree based on the attached dataset. See the attached two other milestones to get an idea of my current thinking.

Final Project Milestone Two

A clear description of the structure and purpose of the decision tree model that you choose.

Bank failures in the future are the leading debate in the United States. The failure will lead to the closure of many saving and withdrawal banks in the US that depend on the US government to protect customer data against breaches and hacking confidential information. A financial crisis is looming in the United States when the banks fail to employ proper strategic measures to protect their clients. In recent studies, the financial predicament has hit the US from 2001 up-to-date (FDIC, 2020). The issue has raised controversies concerning banks' effectiveness and the security of depositors in the investment industry. The problem of analyzing, identifying preventive measures of bank failures, restoring client trust, productivity, and improving the banking industry's performance has become one of the hot topics in the US with numerous unresolved cases of bank failures.

Tackling the menace requires the ICT department to formulate measures that include using a tree decision model that states the underlying causes of bank failures within the investment industry. The Data Envelopment Analysis (DEA), Decision Tree Algorithms, and Federal Deposit Insurance Corporation (FDIC) are some of the decision tree models an IT expert can use to protect vulnerabilities, which cause bank failures (Appiahene et al., 2020). In collaboration with the FDIC, the DEA has established parameters in the works as effective methods to increase bank proficiency and performance. The FDIC has clearly stated the list of banks that closed due to bank failures. The combination of the FDIC and the DEA aims to analyze bank failures and several ways of increasing the cybersecurity of individual data in the US's banking industry (FDIC, 2020). After comparing the outcomes of the research form the DEA, the findings suggested that the DT decision model tree and its C5.0 algorithms provide an exceptional predictive model of bank failures. However, the FDIC decision model tree is the best model for analyzing risks in bank failures. The FDIC's primary purpose is to hold information concerning the number of banks/ financial institutions that failed in the past. The FDIC is a government entity and has credible data about banks that cannot carry out their duties because of data insecurity or lack of Cybersecurity (FDIC, 2020). Additionally, the FDIC ensures that its information is easily accessible by any IT expert who wants to analyze threats that cause bank failures. Documentation refers to potential complications in the analysis process, in an outline or bulleted format. This should be clear, concise, and thorough.

Potential challenges exist in the analysis processes. After the Great Recession, regulators and IT experts continue to face challenges in repairing a financial system and paving the way for frameworks that help control and prevent bank failures. The implementation and ongoing refinement of improvements occupy a major challenge to both investors and supervisors to assure the public about their data and money's cybersecurity. The continuation of developing macroprudential frameworks in the US remains an impossible mission up-to-date. It implies that the supervisor must continue assessing individual bank threats, which is a problematic complication affected by monetary policy, economic drivers, and technology advancement.

First, the low-interest rate is a significant complication in the establishment of bank failures in the US. The presence of monetary policies that aid economic growth and the persistence of low-interest rates since 2001 has negatively affected bank productivity. The banks should establish proper strategies that monitor money spending during economic decline (Christodoulakis, 2015). When it fails to have software that stimulates such expenditures, customers might spend more, which leads to the pumping of more money in the market. The primary obligation of software is to control the circulation of money. The current economic environment saw before this complication and weakened the demand for loans. This complication affects the net interest margins of the bank. Second, rapid change landscape for lending and payments mechanisms.

An individual can refer to this complication as a disruptive technology. The technology change may negatively or positively influence bank productivity in monitoring vulnerabilities that cause bank failures in the United States (Appiahene et al., 2020). Sometimes the advancement of technology might enhance productivity and efficacy across all bank industries and financial institutions even if it affects existing banks. In the banking industry, the rise of technology, such as cybersecurity, challenges existing banks that lack competent IT departments that deal with banks' confidential information for lending and payment models (Garg et al., 2018). The existence of online and mobile banking methods promotes efficient and easy ways for consumers to access banking services at no cost. However, it is costly to design, implement, and protect consumers' privacy data who prefer using such platforms to transact money in small banks. As a result, most clients complain about the presence of fraudsters in online services who use hacking methods to steal money from people (Garg et al., 2018). Such acts may cause small banks to fail since many customers will shun from using their services because of a lack of advanced technology that protects clients from hackers. An evaluation of the model results includes a discussion of whether or not the results are reasonable and the model is accurate, whether or not there are elements that are not present or needlessly present, and any errors that may be present.

The results are reasonable and accurate since the information held by the FDIC is compatible and successful. The FDIC website has quarterly banking profiles that provide an inclusive summary of FDIC-insured banks' financial results (FDIC, 2020). Such graphical information about the FDIC model makes it a viable source of data needed in the research. Additionally, the FDIC is a hundred percent accurate in predicting bank failures from 2001 up-to-date because of technological advancement. The data provides varying information on the financial industry in the US applied to predict bank failures. The only error in the model is the lack of proof about the causes of bank failures in the US, whether it is through cyber insecurity or hacking of individual accounts.

References

Appiahene, P et al. (2020). Predicting bank operational efficiency using machine learning

algorithm: Comparative study of decision tree, random forest, and neural networks.

Advances in Fuzzy Systems, 20(1), p. 1-12. doi.org/10.1155/2020/8581202

Christodoulakis, N. (2015). How crises shaped economic ideas and policies: Wiser after

the events? Springer.

Federal Deposit Insurance Corporation. (2020). Failed bank list. FDIC,

https://www.fdic.gov/resources/resolutions/bank-failures/failed-bank-list/

Garg, N. et al. (2018). Towards the impact of hacking on cyber security. IIOAB Journal , 9(2), p. 61-77.