Should This Loan be Approved or Denied?

For this case-study assignment, students assume the role of loan officer at a bank and are asked to approve or deny a loan by assessing its risk of default using ML.

UNDER CONSTRUCTION

Stage	Description	Output	Working Docs / Notebooks
Project Setup	Project proposal and High level planning	- Project Proposal	- High level planning docs
ETL I	Data Adquisition, Inspection of the structure and EDA	Primary Data Report Tableau: EDA Insights	- Data Understanding - Conceptualization as Database - Data Preprocess - EDA: Univariate - EDA: Bivariate - EDA: Multivariate
ETL II	Data Imputation, Data Enrichment & Feature Engineering	XXXX Report Tableau: Primary Insights	- Data Imputation: Geographic Data - Data Enrichment: Recession - Feature Engineering
Models	Exploration of diverse data models	Conceptual Web App Final Report	- Factor Analysis - Support Vector Machines - Logistic - Clusterings - Random Forest - Necessary Condition Analysis - Interpretable Rules: Bayesian Networks

Aditional Data And Furter Reading:

1. Find a Location by Address
   • https://learn.microsoft.com/en-us/bingmaps/rest-services/locations/find-a-location-by-address
2. Rural-Urban Commuting Area Codes USDA
   • https://www.ers.usda.gov/data-products/rural-urban-commuting-area-codes
3. MySQL Function to remove accents and special characters
   • https://gist.github.com/jgdoncel/bc20b39b8cd612c4a26dfcaf3bb14dd8
4. La Sierra Tarahumara, epicentro del suicidio en México
   • https://datos.nexos.com.mx/la-sierra-tarahumara-epicentro-del-suicidio-en-mexico/#_ftn2
5. Local Spatial Autocorrelation (tecnica de Tarahumaras)
   • https://geographicdata.science/book/notebooks/07_local_autocorrelation.html
6. https://www.slideshare.net/POOJAPATIL211/should-this-loan-be-approved-or-denied
7. https://www.sciencedirect.com/science/article/abs/pii/S0020025515002960
8. https://analyticsindiamag.com/a-guide-to-inferencing-with-bayesian-network-in-python/
9. https://github.com/hayesall/bn-rule-extraction
10. Probabilistic Approach to Extract Qualitative Knowledge
11. https://saturncloud.io/blog/evaluating-logistic-regression-with-crossvalidation/
12. https://github.com/stelladeecoder/sba_dataset/blob/main/sba.ipynb
13. feature engineering

• Trigonometric feature engineering
• https://feature-engine.trainindata.com/en/1.3.x/user_guide/creation/CyclicalFeatures.html
• https://scikit-learn.org/stable/auto_examples/applications/plot_cyclical_feature_engineering.html

Exercise Proposed & published by:
Min Li, Amy Mickel, and Stanley Taylor
College of Business Administration, California State University, Sacramento, CA
-
JOURNAL OF STATISTICS EDUCATION
2018, VOL. 26, NO. 1, 55–66
https://doi.org/10.1080/10691898.2018.1434342