DAT650 (Milestone One)

.docx

School

Southern New Hampshire University *

*We aren’t endorsed by this school

Course

650

Subject

Business

Date

Apr 3, 2024

Type

docx

Pages

5

Uploaded by DeaconSeaLionMaster750

Report
MILESTONE ONE DAT 650 USE CASES 3/7/2024 SNHU Destiny Denson
In response to the financial crisis of 2008–2009, GE’s credit branch is undergoing a strategic reassessment of its credit risk assessment methods. The primary goal is to develop a robust predictive analytic model to determine the likelihood of default for new credit applications. This model aims to provide valuable insights to business users, helping them assess and mitigate the risks associated with extending credit to applicants. I. Identify data sources and analytic structures that generate business value. a. The given data sources, including past credit applicant data stored in an Oracle database and an Excel spreadsheet, provide a rich foundation for generating business value. The CRISP-DM (Cross-Industry Standard Process for Data Mining) framework will guide our approach, ensuring systematic execution through phases such as business understanding, data understanding, data preparation, modeling, evaluation, and deployment. b. The purpose behind employing descriptive and predictive analytic structures is to gain actionable insights into credit default drivers and develop a robust predictive model tailored to GE’s organizational context. Descriptive analytics will help in understanding historical trends and patterns, while predictive analytics will enable proactive risk assessment and mitigation strategies. This structure aligns with GE’s goal of making data-driven decisions and optimizing credit risk management processes. c. For this project, we propose leveraging advanced analytic tools such as Python with libraries like scikit-learn and TensorFlow for modeling and analysis. Python’s versatility, vast ecosystem
of libraries, and robust machine learning capabilities make it an ideal choice for developing predictive models. Additionally, tools like Tableau or Power BI can be used for visualizing insights and communicating findings effectively. d. Additional data fields that could add value to the model include customer behavior data (e.g., transaction history, payment patterns), economic indicators (e.g., GDP growth, inflation rates), and industry-specific factors (e.g., regulatory changes, market trends). Incorporating these fields can provide a more comprehensive understanding of credit risk drivers and enhance the predictive power of the model. II. Evaluate potential ethical implications for the chosen data analytic structure. a. Ethical implications of the data set include fields related to personal demographics (e.g., age, gender, marital status), which could potentially lead to discriminatory practices if used improperly. Utilizing such sensitive information without proper safeguards could result in biases or unfair treatment of applicants. b. To address these ethical implications, a strategy involving transparency, accountability, and fairness is crucial. Highlighting the ethical aspects during the model development process and involving stakeholders in ethical reviews can help ensure responsible use of data. Additionally, implementing measures such as anonymization or aggregation of sensitive fields and regular audits of the model’s performance can mitigate potential risks and uphold ethical standards.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help